{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T14:47:58Z","timestamp":1784645278706,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":89,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,6,24]],"date-time":"2021-06-24T00:00:00Z","timestamp":1624492800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,6,25]]},"DOI":"10.1145\/3469116.3470012","type":"proceedings-article","created":{"date-parts":[[2021,6,24]],"date-time":"2021-06-24T10:10:05Z","timestamp":1624529405000},"page":"1-6","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":106,"title":["Adaptive Inference through Early-Exit Networks"],"prefix":"10.1145","author":[{"given":"Stefanos","family":"Laskaridis","sequence":"first","affiliation":[{"name":"Samsung AI Center, Cambridge"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexandros","family":"Kouris","sequence":"additional","affiliation":[{"name":"Samsung AI Center, Cambridge"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicholas D.","family":"Lane","sequence":"additional","affiliation":[{"name":"Samsung AI Center, Cambridge and University of Cambridge"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2021,6,24]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"Mario Almeida et al. 2019. EmBench: Quantifying Performance Variations of Deep Neural Networks Across Modern Commodity Devices. In EMDL.  Mario Almeida et al. 2019. EmBench: Quantifying Performance Variations of Deep Neural Networks Across Modern Commodity Devices. In EMDL.","DOI":"10.1145\/3325413.3329793"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Konstantin Berestizshevsky et al. 2019. Dynamically sacrificing accuracy for reduced computation: Cascaded inference based on softmax confidence. In ICANN.  Konstantin Berestizshevsky et al. 2019. Dynamically sacrificing accuracy for reduced computation: Cascaded inference based on softmax confidence. In ICANN.","DOI":"10.1007\/978-3-030-30484-3_26"},{"key":"e_1_3_2_1_3_1","article-title":"Do convolutional neural networks learn class hierarchy","volume":"24","author":"Alsallakh Bilal","year":"2017","unstructured":"Alsallakh Bilal et al. 2017 . Do convolutional neural networks learn class hierarchy ? IEEE Transactions on Visualization and Computer Graphics 24 , 1 (2017). Alsallakh Bilal et al. 2017. Do convolutional neural networks learn class hierarchy? IEEE Transactions on Visualization and Computer Graphics 24, 1 (2017).","journal-title":"IEEE Transactions on Visualization and Computer Graphics"},{"key":"e_1_3_2_1_4_1","volume-title":"Class-specific early exit design methodology for convolutional neural networks. Applied Soft Computing","author":"Bonato Vanderlei","year":"2021","unstructured":"Vanderlei Bonato and Christos Bouganis . 2021. Class-specific early exit design methodology for convolutional neural networks. Applied Soft Computing ( 2021 ). Vanderlei Bonato and Christos Bouganis. 2021. Class-specific early exit design methodology for convolutional neural networks. Applied Soft Computing (2021)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Sanyuan Chen et al. 2021. Don't shoot butterfly with rifles: Multi-channel Continuous Speech Separation with Early Exit Transformer. In ICASSP.  Sanyuan Chen et al. 2021. Don't shoot butterfly with rifles: Multi-channel Continuous Speech Separation with Early Exit Transformer. In ICASSP.","DOI":"10.1109\/ICASSP39728.2021.9413933"},{"key":"e_1_3_2_1_6_1","unstructured":"Xinshi Chen et al. 2020. Learning to stop while learning to predict. In ICML.  Xinshi Chen et al. 2020. Learning to stop while learning to predict. In ICML."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Zhourong Chen Yang Li Samy Bengio and Si Si. 2019. You look twice: Gaternet for dynamic filter selection in CNNs. In CVPR.  Zhourong Chen Yang Li Samy Bengio and Si Si. 2019. You look twice: Gaternet for dynamic filter selection in CNNs. In CVPR.","DOI":"10.1109\/CVPR.2019.00939"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411973"},{"key":"e_1_3_2_1_9_1","volume-title":"Proc. IEEE 108","author":"Lei","year":"2020","unstructured":"Lei Deng et al. 2020. Model compression and hardware acceleration for neural networks: A comprehensive survey . Proc. IEEE 108 , 4 ( 2020 ). Lei Deng et al. 2020. Model compression and hardware acceleration for neural networks: A comprehensive survey. Proc. IEEE 108, 4 (2020)."},{"key":"e_1_3_2_1_10_1","unstructured":"Maha Elbayad et al. 2020. Depth-Adaptive Transformer. In ICLR.  Maha Elbayad et al. 2020. Depth-Adaptive Transformer. In ICLR."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3241539.3241559"},{"key":"e_1_3_2_1_12_1","volume-title":"FlexDNN: Input-Adaptive On-Device Deep Learning for Efficient Mobile Vision. In Symposium on Edge Computing (SEC).","author":"Biyi","unstructured":"Biyi Fang et al. 2020 . FlexDNN: Input-Adaptive On-Device Deep Learning for Efficient Mobile Vision. In Symposium on Edge Computing (SEC). Biyi Fang et al. 2020. FlexDNN: Input-Adaptive On-Device Deep Learning for Efficient Mobile Vision. In Symposium on Edge Computing (SEC)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Mohammad Farhadi et al. 2019. A novel design of adaptive and hierarchical convolutional neural networks using partial reconfiguration on FPGA. In HPEC.  Mohammad Farhadi et al. 2019. A novel design of adaptive and hierarchical convolutional neural networks using partial reconfiguration on FPGA. In HPEC.","DOI":"10.1109\/HPEC.2019.8916237"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.5555\/3045390.3045502"},{"key":"e_1_3_2_1_15_1","unstructured":"Xitong Gao Yiren Zhao \u0141ukasz Dudziak Robert Mullins and Cheng-zhong Xu. 2019. Dynamic channel pruning: Feature boosting and suppression. ICLR.  Xitong Gao Yiren Zhao \u0141ukasz Dudziak Robert Mullins and Cheng-zhong Xu. 2019. Dynamic channel pruning: Feature boosting and suppression. ICLR."},{"key":"e_1_3_2_1_16_1","unstructured":"Amir Gholami et al. 2021. A Survey of Quantization Methods for Efficient Neural Network Inference. arXiv preprint arXiv:2103.13630 (2021).  Amir Gholami et al. 2021. A Survey of Quantization Methods for Efficient Neural Network Inference. arXiv preprint arXiv:2103.13630 (2021)."},{"key":"e_1_3_2_1_17_1","volume-title":"Class Means as an Early Exit Decision Mechanism. arXiv preprint arXiv:2103.01148","author":"Gormez Alperen","year":"2021","unstructured":"Alperen Gormez and Erdem Koyuncu . 2021. Class Means as an Early Exit Decision Mechanism. arXiv preprint arXiv:2103.01148 ( 2021 ). Alperen Gormez and Erdem Koyuncu. 2021. Class Means as an Early Exit Decision Mechanism. arXiv preprint arXiv:2103.01148 (2021)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.5555\/3305381.3305518"},{"key":"e_1_3_2_1_19_1","volume-title":"Deep Compression: Compressing Deep Neural Network with Pruning, Trained Quantization and Huffman Coding. ICLR","author":"Song Han","year":"2016","unstructured":"Song Han et al. 2016 . Deep Compression: Compressing Deep Neural Network with Pruning, Trained Quantization and Huffman Coding. ICLR (2016). Song Han et al. 2016. Deep Compression: Compressing Deep Neural Network with Pruning, Trained Quantization and Huffman Coding. ICLR (2016)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/2906388.2906396"},{"key":"e_1_3_2_1_21_1","unstructured":"Yizeng Han et al. 2021. Dynamic neural networks: A survey. arXiv:2102.04906  Yizeng Han et al. 2021. Dynamic neural networks: A survey. arXiv:2102.04906"},{"key":"e_1_3_2_1_22_1","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2015. Deep Residual Learning for Image Recognition. (2015). arXiv:1512.03385  Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2015. Deep Residual Learning for Image Recognition. (2015). arXiv:1512.03385"},{"key":"e_1_3_2_1_23_1","unstructured":"G. Hinton et al. 2015. Distilling the Knowledge in a Neural Network. In NIPSW.  G. Hinton et al. 2015. Distilling the Knowledge in a Neural Network. In NIPSW."},{"key":"e_1_3_2_1_24_1","volume-title":"Sloth: Slowdown Attacks on Adaptive Multi-Exit Neural Network Inference. In ICLR.","author":"Sanghyun Hong","year":"2021","unstructured":"Sanghyun Hong et al. 2021 . A Panda? No, It's a Sloth: Slowdown Attacks on Adaptive Multi-Exit Neural Network Inference. In ICLR. Sanghyun Hong et al. 2021. A Panda? No, It's a Sloth: Slowdown Attacks on Adaptive Multi-Exit Neural Network Inference. In ICLR."},{"key":"e_1_3_2_1_25_1","unstructured":"Samuel Horvath Stefanos Laskaridis etal 2021. FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropout. arXiv:2102.13451  Samuel Horvath Stefanos Laskaridis et al. 2021. FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropout. arXiv:2102.13451"},{"key":"e_1_3_2_1_26_1","volume-title":"Howard et al","author":"Andrew","year":"2017","unstructured":"Andrew G. Howard et al . 2017 . MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications . (2017). arXiv:1704.04861 Andrew G. Howard et al. 2017. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. (2017). arXiv:1704.04861"},{"key":"e_1_3_2_1_27_1","unstructured":"Hanzhang Hu et al. 2019. Learning anytime predictions in neural networks via adaptive loss balancing. In AAAI.  Hanzhang Hu et al. 2019. Learning anytime predictions in neural networks via adaptive loss balancing. In AAAI."},{"key":"e_1_3_2_1_28_1","unstructured":"Ping Hu et al. 2020. Temporally distributed networks for fast video semantic segmentation. In CVPR.  Ping Hu et al. 2020. Temporally distributed networks for fast video semantic segmentation. In CVPR."},{"key":"e_1_3_2_1_29_1","volume-title":"Triple Wins: Boosting Accuracy, Robustness and Efficiency Together by Enabling Input-Adaptive Inference. In ICLR.","author":"Hu Ting-Kuei","year":"2020","unstructured":"Ting-Kuei Hu 2020 . Triple Wins: Boosting Accuracy, Robustness and Efficiency Together by Enabling Input-Adaptive Inference. In ICLR. Ting-Kuei Hu et al. 2020. Triple Wins: Boosting Accuracy, Robustness and Efficiency Together by Enabling Input-Adaptive Inference. In ICLR."},{"key":"e_1_3_2_1_30_1","unstructured":"Gao Huang et al. 2018. Multi-Scale Dense Networks for Resource Efficient Image Classification. In ICLR.  Gao Huang et al. 2018. Multi-Scale Dense Networks for Resource Efficient Image Classification. In ICLR."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"Andrey Ignatov et al. 2019. AI Benchmark: All About Deep Learning on Smart-phones in 2019. In ICCVW.  Andrey Ignatov et al. 2019. AI Benchmark: All About Deep Learning on Smart-phones in 2019. In ICCVW.","DOI":"10.1109\/ICCVW.2019.00447"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.5555\/3327345.3327458"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413701"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3093337.3037698"},{"key":"e_1_3_2_1_35_1","unstructured":"Yigitcan Kaya Sanghyun Hong and Tudor Dumitras. 2019. Shallow-Deep Networks: Understanding and Mitigating Network Overthinking. In ICML.  Yigitcan Kaya Sanghyun Hong and Tudor Dumitras. 2019. Shallow-Deep Networks: Understanding and Mitigating Network Overthinking. In ICML."},{"key":"e_1_3_2_1_36_1","volume-title":"Low Cost Early Exit Decision Unit Design for CNN Accelerator. In 2020 International SoC Design Conference (ISOCC).","author":"Kim Geonho","year":"2020","unstructured":"Geonho Kim and Jongsun Park . 2020 . Low Cost Early Exit Decision Unit Design for CNN Accelerator. In 2020 International SoC Design Conference (ISOCC). Geonho Kim and Jongsun Park. 2020. Low Cost Early Exit Decision Unit Design for CNN Accelerator. In 2020 International SoC Design Conference (ISOCC)."},{"key":"e_1_3_2_1_37_1","article-title":"A 0.22-0.89 mW Low-Power and Highly-Secure Always-On Face Recognition Processor With Adversarial Attack Prevention","volume":"67","author":"Youngwoo Kim","year":"2020","unstructured":"Youngwoo Kim et al. 2020 . A 0.22-0.89 mW Low-Power and Highly-Secure Always-On Face Recognition Processor With Adversarial Attack Prevention . IEEE Transactions on Circuits and Systems II: Express Briefs 67 , 5 (2020). Youngwoo Kim et al. 2020. A 0.22-0.89 mW Low-Power and Highly-Secure Always-On Face Recognition Processor With Adversarial Attack Prevention. IEEE Transactions on Circuits and Systems II: Express Briefs 67, 5 (2020).","journal-title":"IEEE Transactions on Circuits and Systems II: Express Briefs"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"crossref","unstructured":"Alexandros Kouris et al. 2018. CascadeCNN: Pushing the Performance Limits of Quantisation in Convolutional Neural Networks. In FPL.  Alexandros Kouris et al. 2018. CascadeCNN: Pushing the Performance Limits of Quantisation in Convolutional Neural Networks. In FPL.","DOI":"10.1109\/FPL.2018.00034"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.5555\/3408352.3408730"},{"key":"e_1_3_2_1_40_1","volume-title":"Lane","author":"Kouris Alexandros","year":"2021","unstructured":"Alexandros Kouris , Stylianos I. Venieris , Stefanos Laskaridis , and Nicholas D . Lane . 2021 . Multi-Exit Semantic Segmentation Networks . (2021). arXiv:2106.03527 Alexandros Kouris, Stylianos I. Venieris, Stefanos Laskaridis, and Nicholas D. Lane. 2021. Multi-Exit Semantic Segmentation Networks. (2021). arXiv:2106.03527"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3400302.3415698"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3372224.3419194"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3300061.3343410"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3446382.3448359"},{"key":"e_1_3_2_1_45_1","volume-title":"Edge AI: On-Demand Accelerating Deep Neural Network Inference via Edge Computing","author":"E. Li","year":"2020","unstructured":"E. Li et al. 2020 . Edge AI: On-Demand Accelerating Deep Neural Network Inference via Edge Computing . In IEEE Trans. on Wireless Communications (TWC) . E. Li et al. 2020. Edge AI: On-Demand Accelerating Deep Neural Network Inference via Edge Computing. In IEEE Trans. on Wireless Communications (TWC)."},{"key":"e_1_3_2_1_46_1","unstructured":"Fengfu Li and Bin Liu. 2016. Ternary Weight Networks. (2016). arXiv:1605.04711  Fengfu Li and Bin Liu. 2016. Ternary Weight Networks. (2016). arXiv:1605.04711"},{"key":"e_1_3_2_1_47_1","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV).","author":"Hao","unstructured":"Hao Li et al. 2019. Improved Techniques for Training Adaptive Deep Networks . In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV). Hao Li et al. 2019. Improved Techniques for Training Adaptive Deep Networks. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)."},{"key":"e_1_3_2_1_48_1","unstructured":"Xiaoxiao Li et al. 2017. Not All Pixels Are Equal: Difficulty-Aware Semantic Segmentation via Deep Layer Cascade. In CVPR.  Xiaoxiao Li et al. 2017. Not All Pixels Are Equal: Difficulty-Aware Semantic Segmentation via Deep Layer Cascade. In CVPR."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.5555\/3294771.3294979"},{"key":"e_1_3_2_1_50_1","volume-title":"DARTS: Differentiable architecture search. ICLR","author":"Hanxiao Liu","year":"2019","unstructured":"Hanxiao Liu et al. 2019 . DARTS: Differentiable architecture search. ICLR (2019). Hanxiao Liu et al. 2019. DARTS: Differentiable architecture search. ICLR (2019)."},{"key":"e_1_3_2_1_51_1","unstructured":"Jiayi Liu et al. 2020. Pruning Algorithms to Accelerate Convolutional Neural Networks for Edge Applications: A Survey. arXiv:2005.04275 (2020).  Jiayi Liu et al. 2020. Pruning Algorithms to Accelerate Convolutional Neural Networks for Edge Applications: A Survey. arXiv:2005.04275 (2020)."},{"key":"e_1_3_2_1_52_1","unstructured":"Lanlan Liu and Jia Deng. 2018. Dynamic Deep Neural Networks: Optimizing accuracy-efficiency trade-offs by selective execution. In AAAI.  Lanlan Liu and Jia Deng. 2018. Dynamic Deep Neural Networks: Optimizing accuracy-efficiency trade-offs by selective execution. In AAAI."},{"key":"e_1_3_2_1_53_1","unstructured":"Weijie Liu Peng Zhou Zhiruo Wang Zhe Zhao Haotang Deng and Qi Ju. 2020. FastBERT: a Self-distilling BERT with Adaptive Inference Time. In ACL.  Weijie Liu Peng Zhou Zhiruo Wang Zhe Zhao Haotang Deng and Qi Ju. 2020. FastBERT: a Self-distilling BERT with Adaptive Inference Time. In ACL."},{"key":"e_1_3_2_1_54_1","unstructured":"Yoshitomo Matsubara et al. 2021. Split computing and early exiting for deep learning applications: Survey and research challenges. arXiv:2103.04505  Yoshitomo Matsubara et al. 2021. Split computing and early exiting for deep learning applications: Survey and research challenges. arXiv:2103.04505"},{"key":"e_1_3_2_1_55_1","volume-title":"Hydranets: Specialized dynamic architectures for efficient inference. In CVPR.","author":"Mullapudi Ravi Teja","year":"2018","unstructured":"Ravi Teja Mullapudi 2018 . Hydranets: Specialized dynamic architectures for efficient inference. In CVPR. Ravi Teja Mullapudi et al. 2018. Hydranets: Specialized dynamic architectures for efficient inference. In CVPR."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.5555\/2971808.2971918"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"crossref","unstructured":"Debdeep Paul Jawar Singh and Jimson Mathew. 2019. Hardware-Software Co-design Approach for Deep Learning Inference. In ICSCC.  Debdeep Paul Jawar Singh and Jimson Mathew. 2019. Hardware-Software Co-design Approach for Deep Learning Inference. In ICSCC.","DOI":"10.1109\/ICSCC.2019.8843626"},{"key":"e_1_3_2_1_58_1","volume-title":"Lampert","author":"Phuong Mary","year":"2019","unstructured":"Mary Phuong and Christoph H . Lampert . 2019 . Distillation-Based Training for Multi-Exit Architectures. In ICCV. Mary Phuong and Christoph H. Lampert. 2019. Distillation-Based Training for Multi-Exit Architectures. In ICCV."},{"key":"e_1_3_2_1_59_1","volume-title":"Xnor-net: Imagenet classification using binary convolutional neural networks. In ECCV.","author":"Mohammad Rastegari","year":"2016","unstructured":"Mohammad Rastegari et al. 2016 . Xnor-net: Imagenet classification using binary convolutional neural networks. In ECCV. Mohammad Rastegari et al. 2016. Xnor-net: Imagenet classification using binary convolutional neural networks. In ECCV."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"crossref","unstructured":"Simone Scardapane et al. 2020. Differentiable branching in deep networks for fast inference. In ICASSP.  Simone Scardapane et al. 2020. Differentiable branching in deep networks for fast inference. In ICASSP.","DOI":"10.1109\/ICASSP40776.2020.9054209"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"crossref","unstructured":"Roy Schwartz et al.2020. The Right Tool for the Job: Matching Model and Instance Complexities. In ACL.  Roy Schwartz et al.2020. The Right Tool for the Job: Matching Model and Instance Complexities. In ACL.","DOI":"10.18653\/v1\/2020.acl-main.593"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052618"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"crossref","unstructured":"Jianghao Shen et al. 2020. Fractional skipping: Towards finer-grained dynamic CNN inference. In AAAI.  Jianghao Shen et al. 2020. Fractional skipping: Towards finer-grained dynamic CNN inference. In AAAI.","DOI":"10.1609\/aaai.v34i04.6025"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"crossref","unstructured":"Luca Soldaini et al. 2020. The Cascade Transformer: an Application for Efficient Answer Sentence Selection. In ACL. 5697--5708.  Luca Soldaini et al. 2020. The Cascade Transformer: an Application for Efficient Answer Sentence Selection. In ACL. 5697--5708.","DOI":"10.18653\/v1\/2020.acl-main.504"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"crossref","unstructured":"Christian Szegedy et al. 2015. Going deeper with convolutions. In CVPR.  Christian Szegedy et al. 2015. Going deeper with convolutions. In CVPR.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_3_2_1_66_1","unstructured":"Mingxing Tan and Quoc Le. 2019. EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. In ICML.  Mingxing Tan and Quoc Le. 2019. EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. In ICML."},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/3299710.3211336"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"crossref","unstructured":"Surat Teerapittayanon Bradley McDanel and HT Kung. 2016. BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks. In ICPR.  Surat Teerapittayanon Bradley McDanel and HT Kung. 2016. BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks. In ICPR.","DOI":"10.1109\/ICPR.2016.7900006"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"crossref","unstructured":"Andreas Veit and Serge Belongie. 2018. Convolutional networks with adaptive inference graphs. In ECCV.  Andreas Veit and Serge Belongie. 2018. Convolutional networks with adaptive inference graphs. In ECCV.","DOI":"10.1007\/978-3-030-01246-5_1"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1145\/3309551"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"crossref","unstructured":"Jindong Wang et al. 2019. Deep learning for sensor-based activity recognition: A survey. Pattern Recognition Letters 119 (2019).  Jindong Wang et al. 2019. Deep learning for sensor-based activity recognition: A survey. Pattern Recognition Letters 119 (2019).","DOI":"10.1016\/j.patrec.2018.02.010"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"crossref","unstructured":"Meiqi Wang Jianqiao Mo Jun Lin Zhongfeng Wang and Li Du. 2019. DynExit: A Dynamic Early-Exit Strategy for Deep Residual Networks. In SiPS.  Meiqi Wang Jianqiao Mo Jun Lin Zhongfeng Wang and Li Du. 2019. DynExit: A Dynamic Early-Exit Strategy for Deep Residual Networks. In SiPS.","DOI":"10.1109\/SiPS47522.2019.9020551"},{"key":"e_1_3_2_1_74_1","volume-title":"2017. Idk cascades: Fast deep learning by learning not to overthink. arXiv preprint arXiv:1706.00885","author":"Xin Wang","year":"2017","unstructured":"Xin Wang et al. 2017. Idk cascades: Fast deep learning by learning not to overthink. arXiv preprint arXiv:1706.00885 ( 2017 ). Xin Wang et al.2017. Idk cascades: Fast deep learning by learning not to overthink. arXiv preprint arXiv:1706.00885 (2017)."},{"key":"e_1_3_2_1_75_1","volume-title":"Skipnet: Learning dynamic routing in convolutional networks. In ECCV.","author":"Wang Xin","year":"2018","unstructured":"Xin Wang , Fisher Yu , Zi-Yi Dou , Trevor Darrell , and Joseph E Gonzalez . 2018 . Skipnet: Learning dynamic routing in convolutional networks. In ECCV. Xin Wang, Fisher Yu, Zi-Yi Dou, Trevor Darrell, and Joseph E Gonzalez. 2018. Skipnet: Learning dynamic routing in convolutional networks. In ECCV."},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"crossref","unstructured":"Yue Wang et al. 2020. Dual Dynamic Inference: Enabling more efficient adaptive and controllable deep inference. Selected Topics in Signal Processing 14 4 (2020).  Yue Wang et al. 2020. Dual Dynamic Inference: Enabling more efficient adaptive and controllable deep inference. Selected Topics in Signal Processing 14 4 (2020).","DOI":"10.1109\/JSTSP.2020.2979669"},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"crossref","unstructured":"Zhihua Wei et al. 2019. A self-adaptive cascade ConvNets model based on label relation mining. Neurocomputing 328 (2019).  Zhihua Wei et al. 2019. A self-adaptive cascade ConvNets model based on label relation mining. Neurocomputing 328 (2019).","DOI":"10.1016\/j.neucom.2018.03.082"},{"key":"e_1_3_2_1_78_1","unstructured":"Carole-Jean Wu etal 2019. Machine learning at facebook: Understanding inference at the edge. In HPCA.  Carole-Jean Wu et al. 2019. Machine learning at facebook: Understanding inference at the edge. In HPCA."},{"key":"e_1_3_2_1_79_1","volume-title":"Blockdrop: Dynamic inference paths in residual networks. In CVPR.","author":"Zuxuan Wu","year":"2018","unstructured":"Zuxuan Wu et al. 2018 . Blockdrop: Dynamic inference paths in residual networks. In CVPR. Zuxuan Wu et al. 2018. Blockdrop: Dynamic inference paths in residual networks. In CVPR."},{"key":"e_1_3_2_1_80_1","volume-title":"Proceedings of SustaiNLP. ACL. https:\/\/doi.org\/10.1865","author":"Ji","year":"2020","unstructured":"Ji Xin et al. 2020. Early Exiting BERT for Efficient Document Ranking . In Proceedings of SustaiNLP. ACL. https:\/\/doi.org\/10.1865 3\/v1\/ 2020 .sustainlp-1.11 10.18653\/v1 Ji Xin et al. 2020. Early Exiting BERT for Efficient Document Ranking. In Proceedings of SustaiNLP. ACL. https:\/\/doi.org\/10.18653\/v1\/2020.sustainlp-1.11"},{"key":"e_1_3_2_1_81_1","doi-asserted-by":"crossref","unstructured":"Ji Xin Raphael Tang Jaejun Lee Yaoliang Yu and Jimmy Lin. 2020. DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference. In ACL.  Ji Xin Raphael Tang Jaejun Lee Yaoliang Yu and Jimmy Lin. 2020. DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference. In ACL.","DOI":"10.18653\/v1\/2020.acl-main.204"},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"crossref","unstructured":"Qunliang Xing et al. 2020. Early exit or not: resource-efficient blind quality enhancement for compressed images. In ECCV.  Qunliang Xing et al. 2020. Early exit or not: resource-efficient blind quality enhancement for compressed images. In ECCV.","DOI":"10.1007\/978-3-030-58517-4_17"},{"key":"e_1_3_2_1_83_1","doi-asserted-by":"crossref","unstructured":"Le Yang Yizeng Han Xi Chen Shiji Song Jifeng Dai and Gao Huang. 2020. Resolution adaptive networks for efficient inference. In CVPR.  Le Yang Yizeng Han Xi Chen Shiji Song Jifeng Dai and Gao Huang. 2020. Resolution adaptive networks for efficient inference. In CVPR.","DOI":"10.1109\/CVPR42600.2020.00244"},{"key":"e_1_3_2_1_84_1","volume-title":"Netadapt: Platform-aware neural network adaptation for mobile applications. In ECCV.","author":"Yang Tien-Ju","year":"2018","unstructured":"Tien-Ju Yang 2018 . Netadapt: Platform-aware neural network adaptation for mobile applications. In ECCV. Tien-Ju Yang et al. 2018. Netadapt: Platform-aware neural network adaptation for mobile applications. In ECCV."},{"key":"e_1_3_2_1_85_1","unstructured":"Jiahui Yu et al. 2019. Slimmable Neural Networks. ICLR (2019).  Jiahui Yu et al. 2019. Slimmable Neural Networks. ICLR (2019)."},{"key":"e_1_3_2_1_86_1","unstructured":"Jiahui Yu and Thomas S Huang. 2019. Universally Slimmable Networks and improved training techniques. In ICCV.  Jiahui Yu and Thomas S Huang. 2019. Universally Slimmable Networks and improved training techniques. In ICCV."},{"key":"e_1_3_2_1_87_1","doi-asserted-by":"crossref","unstructured":"Amir R Zamir etal 2017. Feedback networks. In CVPR.  Amir R Zamir et al. 2017. Feedback networks. In CVPR.","DOI":"10.1109\/CVPR.2017.196"},{"key":"e_1_3_2_1_88_1","doi-asserted-by":"crossref","unstructured":"Linfeng Zhang et al. 2019. Be your own teacher: Improve the performance of convolutional neural networks via self distillation. In ICCV.  Linfeng Zhang et al. 2019. Be your own teacher: Improve the performance of convolutional neural networks via self distillation. In ICCV.","DOI":"10.1109\/ICCV.2019.00381"},{"key":"e_1_3_2_1_89_1","unstructured":"Wangchunshu Zhou et al. 2020. BERT Loses Patience: Fast and Robust Inference with Early Exit. In NeurIPS.  Wangchunshu Zhou et al. 2020. BERT Loses Patience: Fast and Robust Inference with Early Exit. In NeurIPS."}],"event":{"name":"MobiSys '21: The 19th Annual International Conference on Mobile Systems, Applications, and Services","location":"Virtual WI USA","acronym":"MobiSys '21","sponsor":["SIGMOBILE ACM Special Interest Group on Mobility of Systems, Users, Data and Computing","SIGOPS ACM Special Interest Group on Operating Systems"]},"container-title":["Proceedings of the 5th International Workshop on Embedded and Mobile Deep Learning"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3469116.3470012","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3469116.3470012","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:18:29Z","timestamp":1750191509000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3469116.3470012"}},"subtitle":["Design, Challenges and Directions"],"short-title":[],"issued":{"date-parts":[[2021,6,24]]},"references-count":89,"alternative-id":["10.1145\/3469116.3470012","10.1145\/3469116"],"URL":"https:\/\/doi.org\/10.1145\/3469116.3470012","relation":{},"subject":[],"published":{"date-parts":[[2021,6,24]]},"assertion":[{"value":"2021-06-24","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}