{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T10:47:22Z","timestamp":1769942842037,"version":"3.49.0"},"reference-count":240,"publisher":"Association for Computing Machinery (ACM)","issue":"10","license":[{"start":{"date-parts":[[2024,5,14]],"date-time":"2024-05-14T00:00:00Z","timestamp":1715644800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-sa\/4.0\/"}],"funder":[{"name":"German Federal Ministry of Education and Research","award":["16ME0543"],"award-info":[{"award-number":["16ME0543"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Comput. Surv."],"published-print":{"date-parts":[[2024,10,31]]},"abstract":"<jats:p>Adaptive optimization methods for deep learning adjust the inference task to the current circumstances at runtime to improve the resource footprint while maintaining the model\u2019s performance. These methods are essential for the widespread adoption of deep learning, as they offer a way to reduce the resource footprint of the inference task while also having access to additional information about the current environment. This survey covers the state-of-the-art at-runtime optimization methods, provides guidance for readers to choose the best method for their specific use-case, and also highlights current research gaps in this field.<\/jats:p>","DOI":"10.1145\/3657283","type":"journal-article","created":{"date-parts":[[2024,4,10]],"date-time":"2024-04-10T12:25:49Z","timestamp":1712751949000},"page":"1-40","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":14,"title":["Adapting Neural Networks at Runtime: Current Trends in At-Runtime Optimizations for Deep Learning"],"prefix":"10.1145","volume":"56","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4830-9440","authenticated-orcid":false,"given":"Max","family":"Sponner","sequence":"first","affiliation":[{"name":"Infineon Technologies Dresden GmbH, Dresden, Germany and TU Dresden, Dresden, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0294-8594","authenticated-orcid":false,"given":"Bernd","family":"Waschneck","sequence":"additional","affiliation":[{"name":"Infineon Technologies AG, Neubiberg, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7125-1737","authenticated-orcid":false,"given":"Akash","family":"Kumar","sequence":"additional","affiliation":[{"name":"CFAED, Chair for Processor Design, Technical University Dresden, TU Dresden, Dresden, Germany"}]}],"member":"320","published-online":{"date-parts":[[2024,5,14]]},"reference":[{"key":"e_1_3_3_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00061"},{"key":"e_1_3_3_3_2","first-page":"2549","volume-title":"Proceedings of The 33rd International Conference on Machine Learning","author":"Almahairi Amjad","year":"2016","unstructured":"Amjad Almahairi, Nicolas Ballas, Tim Cooijmans, Yin Zheng, Hugo Larochelle, and Aaron Courville. 2016. Dynamic capacity networks. In Proceedings of The 33rd International Conference on Machine Learning. PMLR, 2549\u20132558."},{"key":"e_1_3_3_4_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_16"},{"key":"e_1_3_3_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/AICAS51828.2021.9458463"},{"key":"e_1_3_3_6_2","doi-asserted-by":"publisher","unstructured":"Manuel Amthor Erik Rodner and Joachim Denzler. 2016. Impatient DNNs - Deep Neural Networks with Dynamic Time Budgets. DOI:10.48550\/arXiv.1610.02850arxiv:1610.02850 [cs].","DOI":"10.48550\/arXiv.1610.02850"},{"key":"e_1_3_3_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3356250.3360044"},{"key":"e_1_3_3_8_2","doi-asserted-by":"publisher","unstructured":"Babak Ehteshami Bejnordi Tijmen Blankevoort and Max Welling. 2020. Batch-Shaping for Learning Conditional Channel Gated Networks. DOI:10.48550\/arXiv.1907.06627arxiv:1907.06627 [cs stat].","DOI":"10.48550\/arXiv.1907.06627"},{"key":"e_1_3_3_9_2","doi-asserted-by":"publisher","unstructured":"Emmanuel Bengio Pierre-Luc Bacon Joelle Pineau and Doina Precup. 2016. Conditional Computation in Neural Networks for Faster Models. DOI:10.48550\/arXiv.1511.06297arxiv:1511.06297 [cs].","DOI":"10.48550\/arXiv.1511.06297"},{"key":"e_1_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.5555\/3305381.3305436"},{"key":"e_1_3_3_11_2","unstructured":"Tolga Bolukbasi Joseph Wang Ofer Dekel and Venkatesh Saligrama. 2017. Adaptive neural networks for fast test-time prediction. (Feb.2017)."},{"key":"e_1_3_3_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00051"},{"key":"e_1_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-12748-9_4"},{"key":"e_1_3_3_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00363"},{"key":"e_1_3_3_15_2","doi-asserted-by":"publisher","unstructured":"Victor Campos Brendan Jou Xavier Giro-i-Nieto Jordi Torres and Shih-Fu Chang. 2018. Skip RNN: Learning to Skip State Updates in Recurrent Neural Networks. DOI:10.48550\/arXiv.1708.06834arxiv:1708.06834 [cs].","DOI":"10.48550\/arXiv.1708.06834"},{"key":"e_1_3_3_16_2","first-page":"406","article-title":"Scaling video analytics on constrained edge nodes","volume":"1","author":"Canel Christopher","year":"2019","unstructured":"Christopher Canel, Thomas Kim, Giulio Zhou, Conglong Li, Hyeontaek Lim, David G. Andersen, Michael Kaminsky, and Subramanya Dulloor. 2019. Scaling video analytics on constrained edge nodes. Proceedings of Machine Learning and Systems 1 (April2019), 406\u2013417.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_3_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01147"},{"key":"e_1_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2903421"},{"key":"e_1_3_3_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3131885.3131906"},{"key":"e_1_3_3_20_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-36708-4_15"},{"key":"e_1_3_3_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3564663"},{"key":"e_1_3_3_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/2809695.2809711"},{"key":"e_1_3_3_23_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_21"},{"key":"e_1_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00939"},{"key":"e_1_3_3_25_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5764"},{"key":"e_1_3_3_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/BigData52589.2021.9671948"},{"key":"e_1_3_3_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/1559795.1559815"},{"key":"e_1_3_3_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00238"},{"key":"e_1_3_3_29_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.pmcj.2022.101594"},{"key":"e_1_3_3_30_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compind.2022.103764"},{"key":"e_1_3_3_31_2","doi-asserted-by":"publisher","unstructured":"Mostafa Dehghani Stephan Gouws Oriol Vinyals Jakob Uszkoreit and \u0141ukasz Kaiser. 2019. Universal Transformers. DOI:10.48550\/arXiv.1807.03819arxiv:1807.03819 [cs stat].","DOI":"10.48550\/arXiv.1807.03819"},{"key":"e_1_3_3_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.205"},{"key":"e_1_3_3_33_2","doi-asserted-by":"publisher","unstructured":"Utsav Drolia Katherine Guo and Priya Narasimhan. 2017. Precog: Prefetching for image recognition applications at the edge. In Proceedings of the Second ACM\/IEEE Symposium on Edge Computing (SEC\u201917). Association for Computing Machinery New York NY USA 1\u201313. 10.1145\/3132211.3134456","DOI":"10.1145\/3132211.3134456"},{"key":"e_1_3_3_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2017.94"},{"key":"e_1_3_3_35_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58285-2_3"},{"key":"e_1_3_3_36_2","doi-asserted-by":"publisher","unstructured":"Maha Elbayad Jiatao Gu Edouard Grave and Michael Auli. 2020. Depth-Adaptive Transformer. DOI:10.48550\/arXiv.1910.10073arxiv:1910.10073 [cs].","DOI":"10.48550\/arXiv.1910.10073"},{"key":"e_1_3_3_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01213"},{"key":"e_1_3_3_38_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2303.08774"},{"key":"e_1_3_3_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/1458469.1458473"},{"key":"e_1_3_3_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/1516360.1516450"},{"key":"e_1_3_3_41_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2010.12.006"},{"key":"e_1_3_3_42_2","volume-title":"Watching a Small Portion Could Be as Good as Watching All: Towards Efficient Video Classification","author":"Fan H.","year":"2018","unstructured":"H. Fan, Z. Xu, L. Zhu, C. Yan, J. Ge, and Y. Yang. 2018. Watching a Small Portion Could Be as Good as Watching All: Towards Efficient Video Classification."},{"key":"e_1_3_3_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/SEC50012.2020.00014"},{"key":"e_1_3_3_44_2","doi-asserted-by":"publisher","unstructured":"Yihao Fang Shervin Manzuri Shalmani and Rong Zheng. 2020. CacheNet: A Model Caching Framework for Deep Learning Inference on the Edge. DOI:10.48550\/arXiv.2007.01793arxiv:2007.01793 [cs eess].","DOI":"10.48550\/arXiv.2007.01793"},{"key":"e_1_3_3_45_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_24"},{"key":"e_1_3_3_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.194"},{"key":"e_1_3_3_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796677"},{"key":"e_1_3_3_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.476"},{"key":"e_1_3_3_49_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1474"},{"key":"e_1_3_3_50_2","doi-asserted-by":"publisher","unstructured":"Xitong Gao Yiren Zhao \u0141ukasz Dudziak Robert Mullins and Cheng-zhong Xu. 2019. Dynamic Channel Pruning: Feature Boosting and Suppression. DOI:10.48550\/arXiv.1810.05331arxiv:1810.05331 [cs].","DOI":"10.48550\/arXiv.1810.05331"},{"key":"e_1_3_3_51_2","doi-asserted-by":"publisher","unstructured":"Nikhil P. Ghanathe and Steve Wilton. 2022. T-RECX: Tiny-Resource Efficient Convolutional Neural Networks with Early-Exit. DOI:10.48550\/arXiv.2207.06613arxiv:2207.06613 [cs eess].","DOI":"10.48550\/arXiv.2207.06613"},{"key":"e_1_3_3_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01535"},{"key":"e_1_3_3_53_2","doi-asserted-by":"publisher","DOI":"10.1145\/3366622.3368147"},{"key":"e_1_3_3_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2986015"},{"key":"e_1_3_3_55_2","doi-asserted-by":"publisher","unstructured":"Hongyu Gong Xian Li and Dmitriy Genzel. 2022. Adaptive Sparse Transformer for Multilingual Translation. DOI:10.48550\/arXiv.2104.07358arxiv:2104.07358 [cs].","DOI":"10.48550\/arXiv.2104.07358"},{"key":"e_1_3_3_56_2","doi-asserted-by":"publisher","unstructured":"Alex Graves. 2017. Adaptive Computation Time for Recurrent Neural Networks. DOI:10.48550\/arXiv.1603.08983arxiv:1603.08983 [cs].","DOI":"10.48550\/arXiv.1603.08983"},{"key":"e_1_3_3_57_2","doi-asserted-by":"publisher","DOI":"10.1145\/3173162.3173185"},{"key":"e_1_3_3_58_2","first-page":"16","article-title":"FoggyCache: Cross-device approximate computation reuse","author":"Guo Peizhen","year":"2018","unstructured":"Peizhen Guo, Rui Li, Bo Hu, and Wenjun Hu. 2018. FoggyCache: Cross-device approximate computation reuse. Living on the Edge (2018), 16.","journal-title":"Living on the Edge"},{"key":"e_1_3_3_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00529"},{"key":"e_1_3_3_60_2","doi-asserted-by":"publisher","unstructured":"Yunhui Guo. 2018. A Survey on Methods and Theories of Quantized Neural Networks. DOI:10.48550\/arXiv.1808.04752arxiv:1808.04752 [cs stat].","DOI":"10.48550\/arXiv.1808.04752"},{"key":"e_1_3_3_61_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2021.08.013"},{"key":"e_1_3_3_62_2","doi-asserted-by":"publisher","DOI":"10.1145\/2906388.2906396"},{"key":"e_1_3_3_63_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3117837"},{"key":"e_1_3_3_64_2","doi-asserted-by":"publisher","unstructured":"Christian Hansen Casper Hansen Stephen Alstrup Jakob Grue Simonsen and Christina Lioma. 2019. Neural Speed Reading with Structural-Jump-LSTM. DOI:10.48550\/arXiv.1904.00761arxiv:1904.00761 [cs stat].","DOI":"10.48550\/arXiv.1904.00761"},{"key":"e_1_3_3_65_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01427"},{"key":"e_1_3_3_66_2","first-page":"4138","volume-title":"Proceedings of the 37th International Conference on Machine Learning","author":"Hazimeh Hussein","year":"2020","unstructured":"Hussein Hazimeh, Natalia Ponomareva, Petros Mol, Zhenyu Tan, and Rahul Mazumder. 2020. The tree ensemble layer: Differentiability meets conditional computation. In Proceedings of the 37th International Conference on Machine Learning. PMLR, 4138\u20134148."},{"key":"e_1_3_3_67_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58583-9_15"},{"key":"e_1_3_3_68_2","doi-asserted-by":"publisher","unstructured":"Sanghyun Hong Yi\u011fitcan Kaya Ionu\u0163-Vlad Modoranu and Tudor Dumitra\u015f. 2021. A Panda? No It\u2019s a Sloth: Slowdown Attacks on Adaptive Multi-Exit Neural Network Inference. DOI:10.48550\/arXiv.2010.02432arxiv:2010.02432 [cs].","DOI":"10.48550\/arXiv.2010.02432"},{"key":"e_1_3_3_69_2","first-page":"9782","volume-title":"Advances in Neural Information Processing Systems","author":"Hou Lu","year":"2020","unstructured":"Lu Hou, Zhiqi Huang, Lifeng Shang, Xin Jiang, Xiao Chen, and Qun Liu. 2020. DynaBERT: Dynamic BERT with adaptive width and depth. In Advances in Neural Information Processing Systems, Vol. 33. Curran Associates, Inc., 9782\u20139793."},{"key":"e_1_3_3_70_2","first-page":"269","volume-title":"13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18)","author":"Hsieh Kevin","year":"2018","unstructured":"Kevin Hsieh, Ganesh Ananthanarayanan, Peter Bodik, Shivaram Venkataraman, Paramvir Bahl, Matthai Philipose, Phillip B. Gibbons, and Onur Mutlu. 2018. Focus: Querying large video datasets with low latency and low cost. In 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18). 269\u2013286."},{"key":"e_1_3_3_71_2","doi-asserted-by":"publisher","unstructured":"Hanzhang Hu Debadeepta Dey Martial Hebert and J. Andrew Bagnell. 2018. Learning Anytime Predictions in Neural Networks via Adaptive Loss Balancing. DOI:10.48550\/arXiv.1708.06832arxiv:1708.06832 [cs].","DOI":"10.48550\/arXiv.1708.06832"},{"key":"e_1_3_3_72_2","doi-asserted-by":"publisher","unstructured":"Ting-Kuei Hu Tianlong Chen Haotao Wang and Zhangyang Wang. 2020. Triple Wins: Boosting Accuracy Robustness and Efficiency Together by Enabling Input-Adaptive Inference. DOI:10.48550\/arXiv.2002.10025arxiv:2002.10025 [cs].","DOI":"10.48550\/arXiv.2002.10025"},{"key":"e_1_3_3_73_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.05.014"},{"key":"e_1_3_3_74_2","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358283"},{"key":"e_1_3_3_75_2","volume-title":"Advances in Neural Information Processing Systems","author":"Hua Weizhe","year":"2019","unstructured":"Weizhe Hua, Yuan Zhou, Christopher M. De Sa, Zhiru Zhang, and G. Edward Suh. 2019. Channel gating neural networks. In Advances in Neural Information Processing Systems, Vol. 32. Curran Associates, Inc."},{"key":"e_1_3_3_76_2","doi-asserted-by":"publisher","unstructured":"Gao Huang Danlu Chen Tianhong Li Felix Wu Laurens van der Maaten and Kilian Q. Weinberger. 2018. Multi-Scale Dense Networks for Resource Efficient Image Classification. DOI:10.48550\/arXiv.1703.09844arxiv:1703.09844 [cs].","DOI":"10.48550\/arXiv.1703.09844"},{"key":"e_1_3_3_77_2","doi-asserted-by":"publisher","unstructured":"Gao Huang Yulin Wang Kangchen Lv Haojun Jiang Wenhui Huang Pengfei Qi and Shiji Song. 2022. Glance and Focus Networks for Dynamic Visual Recognition. DOI:10.48550\/arXiv.2201.03014arxiv:2201.03014 [cs].","DOI":"10.48550\/arXiv.2201.03014"},{"key":"e_1_3_3_78_2","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3132947"},{"key":"e_1_3_3_79_2","doi-asserted-by":"publisher","DOI":"10.1145\/3081333.3081360"},{"key":"e_1_3_3_80_2","doi-asserted-by":"publisher","unstructured":"Yani Ioannou Duncan Robertson Darko Zikic Peter Kontschieder Jamie Shotton Matthew Brown and Antonio Criminisi. 2016. Decision Forests Convolutional Networks and the Models in-Between. DOI:10.48550\/arXiv.1603.01250arxiv:1603.01250 [cs].","DOI":"10.48550\/arXiv.1603.01250"},{"key":"e_1_3_3_81_2","doi-asserted-by":"publisher","DOI":"10.1109\/SEC50012.2020.00016"},{"key":"e_1_3_3_82_2","doi-asserted-by":"publisher","unstructured":"Samvit Jain Xun Zhang Yuhao Zhou Ganesh Ananthanarayanan Junchen Jiang Yuanchao Shu and Joseph Gonzalez. 2019. ReXCam: Resource-Efficient Cross-Camera Video Analytics at Scale. DOI:10.48550\/arXiv.1811.01268arxiv:1811.01268 [cs].","DOI":"10.48550\/arXiv.1811.01268"},{"key":"e_1_3_3_83_2","doi-asserted-by":"publisher","unstructured":"Yacine Jernite Edouard Grave Armand Joulin and Tomas Mikolov. 2017. Variable Computation in Recurrent Neural Networks. DOI:10.48550\/arXiv.1611.06188arxiv:1611.06188 [cs stat].","DOI":"10.48550\/arXiv.1611.06188"},{"key":"e_1_3_3_84_2","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230574"},{"key":"e_1_3_3_85_2","doi-asserted-by":"publisher","unstructured":"Zutao Jiang Changlin Li Xiaojun Chang Jihua Zhu and Yi Yang. 2021. Dynamic Slimmable Denoising Network. DOI:10.48550\/arXiv.2110.08940arxiv:2110.08940 [cs eess].","DOI":"10.48550\/arXiv.2110.08940"},{"key":"e_1_3_3_86_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00222"},{"key":"e_1_3_3_87_2","doi-asserted-by":"publisher","unstructured":"Daniel Kang John Emmons Firas Abuzaid Peter Bailis and Matei Zaharia. 2017. NoScope: Optimizing Neural Network Queries over Video at Scale. DOI:10.48550\/arXiv.1703.02529arxiv:1703.02529 [cs].","DOI":"10.48550\/arXiv.1703.02529"},{"key":"e_1_3_3_88_2","first-page":"3301","volume-title":"Proceedings of the 36th International Conference on Machine Learning","author":"Kaya Yigitcan","year":"2019","unstructured":"Yigitcan Kaya, Sanghyun Hong, and Tudor Dumitras. 2019. Shallow-deep networks: Understanding and mitigating network overthinking. In Proceedings of the 36th International Conference on Machine Learning. PMLR, 3301\u20133310."},{"key":"e_1_3_3_89_2","doi-asserted-by":"publisher","unstructured":"Gyuwan Kim and Kyunghyun Cho. 2021. Length-Adaptive Transformer: Train Once with Length Drop Use Anytime with Search. DOI:10.48550\/arXiv.2010.07003arxiv:2010.07003 [cs].","DOI":"10.48550\/arXiv.2010.07003"},{"key":"e_1_3_3_90_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00982"},{"key":"e_1_3_3_91_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00114"},{"key":"e_1_3_3_92_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.172"},{"key":"e_1_3_3_93_2","doi-asserted-by":"crossref","unstructured":"Alexandros Kouris Stylianos I. Venieris Stefanos Laskaridis and Nicholas D. Lane. 2022. Multi-Exit Semantic Segmentation Networks. arxiv:2106.03527 [cs].","DOI":"10.1007\/978-3-031-19803-8_20"},{"key":"e_1_3_3_94_2","doi-asserted-by":"publisher","unstructured":"Tarun Krishna Ayush K. Rai Yasser A. D. Djilali Alan F. Smeaton Kevin McGuinness and Noel E. O\u2019Connor. 2022. Dynamic Channel Selection in Self-Supervised Learning. DOI:10.48550\/arXiv.2207.12065arxiv:2207.12065 [cs].","DOI":"10.48550\/arXiv.2207.12065"},{"key":"e_1_3_3_95_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00827"},{"key":"e_1_3_3_96_2","doi-asserted-by":"publisher","DOI":"10.1145\/3469116.3470012"},{"key":"e_1_3_3_97_2","doi-asserted-by":"publisher","DOI":"10.1145\/3372224.3419194"},{"key":"e_1_3_3_98_2","doi-asserted-by":"publisher","DOI":"10.4218\/etrij.2020-0112"},{"key":"e_1_3_3_99_2","doi-asserted-by":"publisher","unstructured":"Hankook Lee and Jinwoo Shin. 2018. Anytime Neural Prediction via Slicing Networks Vertically. DOI:10.48550\/arXiv.1807.02609arxiv:1807.02609 [cs stat].","DOI":"10.48550\/arXiv.1807.02609"},{"key":"e_1_3_3_100_2","doi-asserted-by":"publisher","DOI":"10.1145\/3300061.3345455"},{"key":"e_1_3_3_101_2","doi-asserted-by":"publisher","unstructured":"Sam Leroux Steven Bohez Cedric De Boom Elias De Coninck Tim Verbelen Bert Vankeirsbilck Pieter Simoens and Bart Dhoedt. 2016. Lazy Evaluation of Convolutional Filters. DOI:10.48550\/arXiv.1605.08543arxiv:1605.08543 [cs].","DOI":"10.48550\/arXiv.1605.08543"},{"key":"e_1_3_3_102_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-017-1029-1"},{"key":"e_1_3_3_103_2","doi-asserted-by":"publisher","unstructured":"Sam Leroux Pavlo Molchanov Pieter Simoens Bart Dhoedt Thomas Breuel and Jan Kautz. 2018. IamNN: Iterative and Adaptive Mobile Neural Network for Efficient Image Classification. DOI:10.48550\/arXiv.1804.10123arxiv:1804.10123 [cs].","DOI":"10.48550\/arXiv.1804.10123"},{"key":"e_1_3_3_104_2","doi-asserted-by":"publisher","unstructured":"Changlin Li Guangrun Wang Bing Wang Xiaodan Liang Zhihui Li and Xiaojun Chang. 2021. DS-Net++: Dynamic Weight Slicing for Efficient Inference in CNNs and Transformers. DOI:10.48550\/arXiv.2109.10060arxiv:2109.10060 [cs].","DOI":"10.48550\/arXiv.2109.10060"},{"key":"e_1_3_3_105_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00850"},{"key":"e_1_3_3_106_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00609"},{"key":"e_1_3_3_107_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00198"},{"key":"e_1_3_3_108_2","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2018.2842821"},{"key":"e_1_3_3_109_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.684"},{"key":"e_1_3_3_110_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00858"},{"key":"e_1_3_3_111_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.145"},{"key":"e_1_3_3_112_2","doi-asserted-by":"publisher","DOI":"10.1145\/2742647.2742663"},{"key":"e_1_3_3_113_2","volume-title":"Advances in Neural Information Processing Systems","author":"Lin Ji","year":"2017","unstructured":"Ji Lin, Yongming Rao, Jiwen Lu, and Jie Zhou. 2017. Runtime neural pruning. In Advances in Neural Information Processing Systems, Vol. 30. Curran Associates, Inc."},{"key":"e_1_3_3_114_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2017.8050797"},{"key":"e_1_3_3_115_2","doi-asserted-by":"publisher","unstructured":"Chuanjian Liu Yunhe Wang Kai Han Chunjing Xu and Chang Xu. 2019. Learning Instance-wise Sparsity for Accelerating Deep Models. DOI:10.48550\/arXiv.1907.11840arxiv:1907.11840 [cs].","DOI":"10.48550\/arXiv.1907.11840"},{"key":"e_1_3_3_116_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11630"},{"key":"e_1_3_3_117_2","doi-asserted-by":"publisher","DOI":"10.1145\/3300061.3300116"},{"key":"e_1_3_3_118_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS47774.2020.00085"},{"key":"e_1_3_3_119_2","doi-asserted-by":"publisher","DOI":"10.1145\/3210240.3210337"},{"key":"e_1_3_3_120_2","doi-asserted-by":"publisher","unstructured":"Weijie Liu Peng Zhou Zhe Zhao Zhiruo Wang Haotang Deng and Qi Ju. 2020. FastBERT: A Self-distilling BERT with Adaptive Inference Time. DOI:10.48550\/arXiv.2004.02178arxiv:2004.02178 [cs].","DOI":"10.48550\/arXiv.2004.02178"},{"key":"e_1_3_3_121_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.08.082"},{"key":"e_1_3_3_122_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD.2017.49"},{"key":"e_1_3_3_123_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00347"},{"key":"e_1_3_3_124_2","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240697"},{"key":"e_1_3_3_125_2","doi-asserted-by":"publisher","DOI":"10.1145\/3484946"},{"key":"e_1_3_3_126_2","doi-asserted-by":"publisher","DOI":"10.1145\/3371154"},{"key":"e_1_3_3_127_2","doi-asserted-by":"publisher","DOI":"10.1145\/3527155"},{"key":"e_1_3_3_128_2","first-page":"2363","volume-title":"Proceedings of the 34th International Conference on Machine Learning","author":"McGill Mason","year":"2017","unstructured":"Mason McGill and Pietro Perona. 2017. Deciding how to decide: Dynamic routing in artificial neural networks. In Proceedings of the 34th International Conference on Machine Learning. PMLR, 2363\u20132372."},{"key":"e_1_3_3_129_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01199"},{"key":"e_1_3_3_130_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_6"},{"key":"e_1_3_3_131_2","doi-asserted-by":"publisher","unstructured":"Yue Meng Rameswar Panda Chung-Ching Lin Prasanna Sattigeri Leonid Karlinsky Kate Saenko Aude Oliva and Rogerio Feris. 2021. AdaFuse: Adaptive Temporal Fusion Network for Efficient Action Recognition. DOI:10.48550\/arXiv.2102.05775arxiv:2102.05775 [cs].","DOI":"10.48550\/arXiv.2102.05775"},{"key":"e_1_3_3_132_2","volume-title":"Advances in Neural Information Processing Systems","author":"Mnih Volodymyr","year":"2014","unstructured":"Volodymyr Mnih, Nicolas Heess, Alex Graves, and Koray Kavukcuoglu. 2014. Recurrent models of visual attention. In Advances in Neural Information Processing Systems, Vol. 27. Curran Associates, Inc."},{"key":"e_1_3_3_133_2","first-page":"8080","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Mullapudi Ravi Teja","year":"2018","unstructured":"Ravi Teja Mullapudi, William R. Mark, Noam Shazeer, and Kayvon Fatahalian. 2018. HydraNets: Specialized dynamic architectures for efficient inference. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 8080\u20138089."},{"key":"e_1_3_3_134_2","doi-asserted-by":"publisher","DOI":"10.1109\/IoTDI54339.2022.00010"},{"key":"e_1_3_3_135_2","doi-asserted-by":"publisher","DOI":"10.1149\/1945-7111\/ab67a8"},{"key":"e_1_3_3_136_2","doi-asserted-by":"publisher","unstructured":"Mark Neumann Pontus Stenetorp and Sebastian Riedel. 2016. Learning to Reason with Adaptive Computation. DOI:10.48550\/arXiv.1610.07647arxiv:1610.07647 [cs stat].","DOI":"10.48550\/arXiv.1610.07647"},{"key":"e_1_3_3_137_2","doi-asserted-by":"publisher","unstructured":"Peter O\u2019Connor and Max Welling. 2016. Sigma Delta Quantized Networks. DOI:10.48550\/arXiv.1611.02024arxiv:1611.02024 [cs].","DOI":"10.48550\/arXiv.1611.02024"},{"key":"e_1_3_3_138_2","doi-asserted-by":"publisher","unstructured":"Augustus Odena Dieterich Lawson and Christopher Olah. 2017. Changing Model Behavior at Test-Time Using Reinforcement Learning. DOI:10.48550\/arXiv.1702.07780arxiv:1702.07780 [cs stat].","DOI":"10.48550\/arXiv.1702.07780"},{"key":"e_1_3_3_139_2","volume-title":"USENIX Workshop on Hot Topics in Edge Computing (HotEdge 18)","author":"Ogden Samuel S.","year":"2018","unstructured":"Samuel S. Ogden and Tian Guo. 2018. {MODI}: Mobile deep inference made efficient by edge computing. In USENIX Workshop on Hot Topics in Edge Computing (HotEdge 18)."},{"key":"e_1_3_3_140_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00166"},{"key":"e_1_3_3_141_2","doi-asserted-by":"publisher","unstructured":"Bowen Pan Rameswar Panda Camilo Fosco Chung-Ching Lin Alex Andonian Yue Meng Kate Saenko Aude Oliva and Rogerio Feris. 2021. VA-RED$ \\(\\hat2\\) $: Video Adaptive Redundancy Reduction. DOI:10.48550\/arXiv.2102.07887arxiv:2102.07887 [cs].","DOI":"10.48550\/arXiv.2102.07887"},{"key":"e_1_3_3_142_2","first-page":"24898","volume-title":"Advances in Neural Information Processing Systems","author":"Pan Bowen","year":"2021","unstructured":"Bowen Pan, Rameswar Panda, Yifan Jiang, Zhangyang Wang, Rogerio Feris, and Aude Oliva. 2021. IA-RED2: Interpretability-aware redundancy reduction for vision transformers. In Advances in Neural Information Processing Systems, Vol. 34. Curran Associates, Inc., 24898\u201324911."},{"key":"e_1_3_3_143_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2017.2681075"},{"key":"e_1_3_3_144_2","doi-asserted-by":"publisher","DOI":"10.5555\/2971808.2971918"},{"key":"e_1_3_3_145_2","doi-asserted-by":"publisher","DOI":"10.1145\/3007192"},{"key":"e_1_3_3_146_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01217"},{"key":"e_1_3_3_147_2","doi-asserted-by":"publisher","DOI":"10.1109\/CODESISSS.2015.7331375"},{"key":"e_1_3_3_148_2","doi-asserted-by":"publisher","unstructured":"Yongming Rao Zuyan Liu Wenliang Zhao Jie Zhou and Jiwen Lu. 2022. Dynamic Spatial Sparsification for Efficient Vision Transformers and Convolutional Neural Networks. DOI:10.48550\/arXiv.2207.01580arxiv:2207.01580 [cs].","DOI":"10.48550\/arXiv.2207.01580"},{"key":"e_1_3_3_149_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.424"},{"key":"e_1_3_3_150_2","first-page":"13937","volume-title":"Advances in Neural Information Processing Systems","author":"Rao Yongming","year":"2021","unstructured":"Yongming Rao, Wenliang Zhao, Benlin Liu, Jiwen Lu, Jie Zhou, and Cho-Jui Hsieh. 2021. DynamicViT: Efficient vision transformers with dynamic token sparsification. In Advances in Neural Information Processing Systems, Vol. 34. Curran Associates, Inc., 13937\u201313949."},{"key":"e_1_3_3_151_2","doi-asserted-by":"publisher","DOI":"10.1145\/3534580"},{"key":"e_1_3_3_152_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00908"},{"key":"e_1_3_3_153_2","doi-asserted-by":"publisher","unstructured":"Clemens Rosenbaum Tim Klinger and Matthew Riemer. 2017. Routing Networks: Adaptive Selection of Non-linear Functions for Multi-Task Learning. DOI:10.48550\/arXiv.1711.01239arxiv:1711.01239 [cs].","DOI":"10.48550\/arXiv.1711.01239"},{"key":"e_1_3_3_154_2","first-page":"81","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Bulo Samuel Rota","year":"2014","unstructured":"Samuel Rota Bulo and Peter Kontschieder. 2014. Neural decision forests for semantic image labelling. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 81\u201388."},{"key":"e_1_3_3_155_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2021.3136815"},{"key":"e_1_3_3_156_2","doi-asserted-by":"publisher","DOI":"10.1145\/3517207.3526982"},{"key":"e_1_3_3_157_2","first-page":"1","volume-title":"2021 33rd International Teletraffic Congress (ITC-33)","author":"Salem Tareq Si","year":"2021","unstructured":"Tareq Si Salem, Giovanni Neglia, and Damiano Carra. 2021. A\u00c7AI: Ascent similarity caching with approximate indexes. In 2021 33rd International Teletraffic Congress (ITC-33). 1\u20139."},{"key":"e_1_3_3_158_2","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-020-09734-4"},{"key":"e_1_3_3_159_2","doi-asserted-by":"publisher","DOI":"10.1109\/RSDHA54838.2021.00010"},{"key":"e_1_3_3_160_2","first-page":"17456","article-title":"Confident adaptive language modeling","volume":"35","author":"Schuster Tal","year":"2022","unstructured":"Tal Schuster, Adam Fisch, Jai Gupta, Mostafa Dehghani, Dara Bahri, Vinh Tran, Yi Tay, and Donald Metzler. 2022. Confident adaptive language modeling. Advances in Neural Information Processing Systems 35 (Dec.2022), 17456\u201317472.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_3_161_2","doi-asserted-by":"publisher","unstructured":"Roy Schwartz Gabriel Stanovsky Swabha Swayamdipta Jesse Dodge and Noah A. Smith. 2020. The Right Tool for the Job: Matching Model and Instance Complexities. DOI:10.48550\/arXiv.2004.07453arxiv:2004.07453 [cs].","DOI":"10.48550\/arXiv.2004.07453"},{"key":"e_1_3_3_162_2","doi-asserted-by":"publisher","unstructured":"Minjoon Seo Sewon Min Ali Farhadi and Hannaneh Hajishirzi. 2018. Neural Speed Reading via Skim-RNN. DOI:10.48550\/arXiv.1711.02085arxiv:1711.02085 [cs].","DOI":"10.48550\/arXiv.1711.02085"},{"key":"e_1_3_3_163_2","doi-asserted-by":"publisher","unstructured":"Noam Shazeer Azalia Mirhoseini Krzysztof Maziarz Andy Davis Quoc Le Geoffrey Hinton and Jeff Dean. 2017. Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer. DOI:10.48550\/arXiv.1701.06538arxiv:1701.06538 [cs stat].","DOI":"10.48550\/arXiv.1701.06538"},{"key":"e_1_3_3_164_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6025"},{"key":"e_1_3_3_165_2","doi-asserted-by":"publisher","unstructured":"Mengnan Shi Chang Liu Qixiang Ye and Jianbin Jiao. 2021. Feature-Gate Coupling for Dynamic Network Pruning. DOI:10.48550\/arXiv.2111.14302arxiv:2111.14302 [cs].","DOI":"10.48550\/arXiv.2111.14302"},{"key":"e_1_3_3_166_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.11"},{"key":"e_1_3_3_167_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00063"},{"key":"e_1_3_3_168_2","doi-asserted-by":"publisher","DOI":"10.1145\/3240765.3240796"},{"key":"e_1_3_3_169_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_48"},{"key":"e_1_3_3_170_2","doi-asserted-by":"crossref","unstructured":"Sainbayar Sukhbaatar Edouard Grave Piotr Bojanowski and Armand Joulin. 2019. Adaptive Attention Span in Transformers. arxiv:1905.07799 [cs stat].","DOI":"10.18653\/v1\/P19-1032"},{"key":"e_1_3_3_171_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00728"},{"key":"e_1_3_3_172_2","doi-asserted-by":"publisher","DOI":"10.1145\/2934583.2934615"},{"key":"e_1_3_3_173_2","doi-asserted-by":"publisher","DOI":"10.1145\/3412382.3458272"},{"key":"e_1_3_3_174_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASP-DAC52403.2022.9712483"},{"key":"e_1_3_3_175_2","doi-asserted-by":"publisher","unstructured":"Chen Tang Haoyu Zhai Kai Ouyang Zhi Wang Yifei Zhu and Wenwu Zhu. 2022. Arbitrary Bit-width Network: A Joint Layer-Wise Quantization and Adaptive Inference Approach. DOI:10.48550\/arXiv.2204.09992arxiv:2204.09992 [cs].","DOI":"10.48550\/arXiv.2204.09992"},{"key":"e_1_3_3_176_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00558"},{"key":"e_1_3_3_177_2","doi-asserted-by":"publisher","DOI":"10.1145\/2968456.2968458"},{"key":"e_1_3_3_178_2","first-page":"6166","volume-title":"Proceedings of the 36th International Conference on Machine Learning","author":"Tanno Ryutaro","year":"2019","unstructured":"Ryutaro Tanno, Kai Arulkumaran, Daniel Alexander, Antonio Criminisi, and Aditya Nori. 2019. Adaptive neural trees. In Proceedings of the 36th International Conference on Machine Learning. PMLR, 6166\u20136175."},{"key":"e_1_3_3_179_2","doi-asserted-by":"publisher","DOI":"10.1145\/3299710.3211336"},{"key":"e_1_3_3_180_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7900006"},{"key":"e_1_3_3_181_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2017.226"},{"key":"e_1_3_3_182_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9413153"},{"key":"e_1_3_3_183_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_1"},{"key":"e_1_3_3_184_2","volume-title":"USENIX Workshop on Hot Topics in Edge Computing (HotEdge 18)","author":"Venugopal Srikumar","year":"2018","unstructured":"Srikumar Venugopal, Michele Gazzetti, Yiannis Gkoufas, and Kostas Katrinis. 2018. Shadow puppets: Cloud-level accurate {AI} inference at the speed and economy of edge. In USENIX Workshop on Hot Topics in Edge Computing (HotEdge 18)."},{"key":"e_1_3_3_185_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00239"},{"key":"e_1_3_3_186_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00511"},{"key":"e_1_3_3_187_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00236"},{"key":"e_1_3_3_188_2","doi-asserted-by":"publisher","DOI":"10.1109\/SEC.2018.00019"},{"key":"e_1_3_3_189_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"e_1_3_3_190_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"e_1_3_3_191_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_25"},{"key":"e_1_3_3_192_2","first-page":"552","volume-title":"Proceedings of The 35th Uncertainty in Artificial Intelligence Conference","author":"Wang Xin","year":"2020","unstructured":"Xin Wang, Fisher Yu, Lisa Dunlap, Yi-An Ma, Ruth Wang, Azalia Mirhoseini, Trevor Darrell, and Joseph E. Gonzalez. 2020. Deep mixture of experts via shallow embedding. In Proceedings of The 35th Uncertainty in Artificial Intelligence Conference. PMLR, 552\u2013562."},{"key":"e_1_3_3_193_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01594"},{"key":"e_1_3_3_194_2","doi-asserted-by":"publisher","unstructured":"Yulin Wang Rui Huang Shiji Song Zeyi Huang and Gao Huang. 2021. Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognition. DOI:10.48550\/arXiv.2105.15075arxiv:2105.15075 [cs].","DOI":"10.48550\/arXiv.2105.15075"},{"key":"e_1_3_3_195_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2979669"},{"key":"e_1_3_3_196_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00632"},{"key":"e_1_3_3_197_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00346"},{"key":"e_1_3_3_198_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00919"},{"key":"e_1_3_3_199_2","volume-title":"Advances in Neural Information Processing Systems","author":"Wu Zuxuan","year":"2019","unstructured":"Zuxuan Wu, Caiming Xiong, Yu-Gang Jiang, and Larry S. Davis. 2019. LiteEval: A coarse-to-fine framework for resource efficient video recognition. In Advances in Neural Information Processing Systems, Vol. 32. Curran Associates, Inc."},{"key":"e_1_3_3_200_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00137"},{"key":"e_1_3_3_201_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414505"},{"key":"e_1_3_3_202_2","doi-asserted-by":"publisher","DOI":"10.1109\/TETC.2021.3056031"},{"key":"e_1_3_3_203_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_31"},{"key":"e_1_3_3_204_2","doi-asserted-by":"publisher","unstructured":"Ji Xin Raphael Tang Jaejun Lee Yaoliang Yu and Jimmy Lin. 2020. DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference. DOI:10.48550\/arXiv.2004.12993arxiv:2004.12993 [cs].","DOI":"10.48550\/arXiv.2004.12993"},{"key":"e_1_3_3_205_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.8"},{"key":"e_1_3_3_206_2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3119950"},{"key":"e_1_3_3_207_2","first-page":"2048","volume-title":"Proceedings of the 32nd International Conference on Machine Learning","author":"Xu Kelvin","year":"2015","unstructured":"Kelvin Xu, Jimmy Ba, Ryan Kiros, Kyunghyun Cho, Aaron Courville, Ruslan Salakhudinov, Rich Zemel, and Yoshua Bengio. 2015. Show, attend and tell: Neural image caption generation with visual attention. In Proceedings of the 32nd International Conference on Machine Learning. PMLR, 2048\u20132057."},{"key":"e_1_3_3_208_2","doi-asserted-by":"publisher","DOI":"10.1109\/SEC50012.2020.00041"},{"key":"e_1_3_3_209_2","unstructured":"Mengwei Xu Xuanzhe Liu Yunxin Liu and Felix Xiaozhu Lin. 2017. Accelerating convolutional neural networks for continuous mobile vision via cache reuse. CoRR abs\/1712.01670 (2017). arXiv:1712.01670. http:\/\/arxiv.org\/abs\/1712.01670"},{"key":"e_1_3_3_210_2","doi-asserted-by":"publisher","DOI":"10.1145\/3241539.3241563"},{"key":"e_1_3_3_211_2","doi-asserted-by":"publisher","DOI":"10.1109\/MLCAD48534.2019.9142052"},{"key":"e_1_3_3_212_2","doi-asserted-by":"publisher","DOI":"10.23919\/DATE48585.2020.9116235"},{"key":"e_1_3_3_213_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.314"},{"key":"e_1_3_3_214_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2019.2936939"},{"key":"e_1_3_3_215_2","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796984"},{"key":"e_1_3_3_216_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00244"},{"key":"e_1_3_3_217_2","doi-asserted-by":"publisher","DOI":"10.23919\/DATE54114.2022.9774567"},{"key":"e_1_3_3_218_2","doi-asserted-by":"publisher","DOI":"10.1117\/12.2537799"},{"key":"e_1_3_3_219_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.293"},{"key":"e_1_3_3_220_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01054"},{"key":"e_1_3_3_221_2","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892578"},{"key":"e_1_3_3_222_2","doi-asserted-by":"publisher","unstructured":"Adams Wei Yu Hongrae Lee and Quoc V. Le. 2017. Learning to Skim Text. DOI:10.48550\/arXiv.1704.06877arxiv:1704.06877 [cs].","DOI":"10.48550\/arXiv.1704.06877"},{"key":"e_1_3_3_223_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17286"},{"key":"e_1_3_3_224_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00189"},{"key":"e_1_3_3_225_2","doi-asserted-by":"publisher","unstructured":"Jiahui Yu Linjie Yang Ning Xu Jianchao Yang and Thomas Huang. 2018. Slimmable Neural Networks. DOI:10.48550\/arXiv.1812.08928arxiv:1812.08928 [cs].","DOI":"10.48550\/arXiv.1812.08928"},{"key":"e_1_3_3_226_2","unstructured":"Keyi Yu Yang Liu Alexander G. Schwing and Jian Peng. 2022. Fast and accurate text classification: Skimming rereading and early stopping. (Feb.2022)."},{"key":"e_1_3_3_227_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00038"},{"key":"e_1_3_3_228_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_11"},{"key":"e_1_3_3_229_2","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.001.1800506"},{"key":"e_1_3_3_230_2","doi-asserted-by":"publisher","DOI":"10.1145\/3225058.3225103"},{"key":"e_1_3_3_231_2","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2020.2970413"},{"key":"e_1_3_3_232_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2021.3139940"},{"key":"e_1_3_3_233_2","volume-title":"Advances in Neural Information Processing Systems","author":"Zhang Linfeng","year":"2019","unstructured":"Linfeng Zhang, Zhanhong Tan, Jiebo Song, Jingwei Chen, Chenglong Bao, and Kaisheng Ma. 2019. SCAN: A scalable neural networks framework towards compact and efficient models. In Advances in Neural Information Processing Systems, Vol. 32. Curran Associates, Inc."},{"key":"e_1_3_3_234_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-88013-2_34"},{"key":"e_1_3_3_235_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447993.3448628"},{"key":"e_1_3_3_236_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-92307-5_65"},{"key":"e_1_3_3_237_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3007826"},{"key":"e_1_3_3_238_2","first-page":"18330","volume-title":"Advances in Neural Information Processing Systems","author":"Zhou Wangchunshu","year":"2020","unstructured":"Wangchunshu Zhou, Canwen Xu, Tao Ge, Julian McAuley, Ke Xu, and Furu Wei. 2020. BERT loses patience: Fast and robust inference with early exit. In Advances in Neural Information Processing Systems, Vol. 33. Curran Associates, Inc., 18330\u201318341."},{"key":"e_1_3_3_239_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_43"},{"key":"e_1_3_3_240_2","unstructured":"Get Your Footage. 2021. Hands Up Waving Hello Green Screen Effect | Gesture Say Hi Chroma Key in HD 4K."},{"key":"e_1_3_3_241_2","unstructured":"PCV. 2022. Vehicle Detection Dataset. https:\/\/universe.roboflow.com\/pcv-wndzh\/vehicle-detection-bq16s. Visited on 2024-04-09."}],"container-title":["ACM Computing Surveys"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3657283","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3657283","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:39Z","timestamp":1750295859000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3657283"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,14]]},"references-count":240,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2024,10,31]]}},"alternative-id":["10.1145\/3657283"],"URL":"https:\/\/doi.org\/10.1145\/3657283","relation":{},"ISSN":["0360-0300","1557-7341"],"issn-type":[{"value":"0360-0300","type":"print"},{"value":"1557-7341","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,14]]},"assertion":[{"value":"2023-01-18","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-04-02","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-05-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}