{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T00:15:38Z","timestamp":1761005738921,"version":"build-2065373602"},"publisher-location":"Singapore","reference-count":86,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819513451","type":"print"},{"value":"9789819513468","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T00:00:00Z","timestamp":1761004800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T00:00:00Z","timestamp":1761004800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-981-95-1346-8_6","type":"book-chapter","created":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T06:21:33Z","timestamp":1760941293000},"page":"86-106","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Survey of\u00a0Deep Model Compression and\u00a0Acceleration"],"prefix":"10.1007","author":[{"given":"Chong","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocab":"crossref"}]},{"given":"Hongwei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocab":"crossref"}]},{"given":"Hongzhi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocab":"crossref"}]},{"given":"Jiaying","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocab":"crossref"}]},{"given":"Sijia","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocab":"crossref"}]},{"given":"Xiaoqian","family":"Meng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocab":"crossref"}]},{"given":"Siyan","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocab":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,10,21]]},"reference":[{"issue":"6","key":"6_CR1","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2017","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Commun. ACM 60(6), 84\u201390 (2017). https:\/\/doi.org\/10.1145\/3065386","journal-title":"Commun. ACM"},{"key":"6_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"W Liu","year":"2016","unstructured":"Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21\u201337. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2"},{"key":"6_CR3","unstructured":"Ren, S., He, K., Girshick, R., et al.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, vol. 28 (2015)"},{"key":"6_CR4","doi-asserted-by":"publisher","unstructured":"Kong, X., Zhao, H., Qiao, Y., et al.: Classsr: a general framework to accelerate super-resolution networks by data characteristic. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR, pp. 12016\u201312025 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.01184","DOI":"10.1109\/CVPR46437.2021.01184"},{"issue":"2","key":"6_CR5","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1109\/TPAMI.2015.2439281","volume":"38","author":"C Dong","year":"2016","unstructured":"Dong, C., Loy, C.C., He, K., et al.: Image super-resolution using deep convolutional networks. IEEE Trans. Pattern Anal. Mach. Intell. 38(2), 295\u2013307 (2016). https:\/\/doi.org\/10.1109\/TPAMI.2015.2439281","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"3","key":"6_CR6","doi-asserted-by":"publisher","first-page":"1139","DOI":"10.1109\/TETC.2019.2958946","volume":"9","author":"H Yin","year":"2021","unstructured":"Yin, H., Mukadam, B., Dai, X., et al.: Diabdeep: pervasive diabetes diagnosis based on wearable medical sensors and efficient neural networks. IEEE Trans. Emerg. Top. Comput. 9(3), 1139\u20131150 (2021). https:\/\/doi.org\/10.1109\/TETC.2019.2958946","journal-title":"IEEE Trans. Emerg. Top. Comput."},{"key":"6_CR7","doi-asserted-by":"publisher","unstructured":"Niyaz, U., Bathula, D.R.: Augmenting knowledge distillation with peer-topeer mutual learning for model compression. In: International Symposium on Biomedical Imaging (ISBI), pp. 1\u20134 (2022). https:\/\/doi.org\/10.1109\/ISBI52829.2022.9761511","DOI":"10.1109\/ISBI52829.2022.9761511"},{"key":"6_CR8","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Proceedings of the 28th International Conference on Neural Information Processing Systems, vol. 2, pp. 3104\u20133112 (2014)"},{"key":"6_CR9","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1016\/j.neucom.2022.11.0.84","volume":"521","author":"J Liu","year":"2023","unstructured":"Liu, J., Zhang, F., Zhou, Z., et al.: Bfmnet: bilateral feature fusion network with multi-scale context aggregation for real-time semantic segmentation. Neurocomputing 521, 27\u201340 (2023). https:\/\/doi.org\/10.1016\/j.neucom.2022.11.0.84","journal-title":"Neurocomputing"},{"key":"6_CR10","doi-asserted-by":"publisher","unstructured":"Zhang, B., Wang, Z., Ling, Y., et al.: Mx2m: masked cross-modality modeling in domain adaptation for 3D semantic segmentation. In: Conference on Artificial Intelligence, (AAAI), pp. 3401\u20133409 (2023). https:\/\/doi.org\/10.1609\/AAAI.V37I3.25448","DOI":"10.1609\/AAAI.V37I3.25448"},{"key":"6_CR11","doi-asserted-by":"publisher","unstructured":"Antol, S., Agrawal, A., Lu, J., et al.: VQA: visual question answering. In: IEEE International Conference on Computer Vision (ICCV), pp. 2425\u20132433 (2015). https:\/\/doi.org\/10.1109\/ICCV.2015.279","DOI":"10.1109\/ICCV.2015.279"},{"key":"6_CR12","doi-asserted-by":"publisher","unstructured":"Noh, H., Seo, P.H., Han, B.: Image question answering using convolutional neural network with dynamic parameter prediction. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 30\u201338 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.11","DOI":"10.1109\/CVPR.2016.11"},{"key":"6_CR13","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for largescale image recognition. In: International Conference on Learning Representations, ICLR (2015). http:\/\/arxiv.org\/abs\/1409.1556"},{"key":"6_CR14","unstructured":"Lecun, Y., Denker, J.S., Solla, S.A.: Optimal brain damage. In: Advances in Neural Information Processing Systems, pp. 598\u2013605 (1989)"},{"key":"6_CR15","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network (2015). arXiv:1503.02531"},{"key":"6_CR16","unstructured":"Romero, A., Ballas, N., Kahou, S.E., et al.: Fitnets: hints for thin deep nets. In: International Conference on Learning Representations (2015)"},{"issue":"5","key":"6_CR17","doi-asserted-by":"publisher","first-page":"2030","DOI":"10.1109\/TNNLS.2020.2995884","volume":"32","author":"N Passalis","year":"2021","unstructured":"Passalis, N., Tzelepi, M., Tefas, A.: Probabilistic knowledge transfer for lightweight deep representation learning. IEEE Trans. Neural Netw. Learn. Syst. 32(5), 2030\u20132039 (2021). https:\/\/doi.org\/10.1109\/TNNLS.2020.2995884","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"6_CR18","unstructured":"Tian, Y., Krishnan, D., Isola, P.: Contrastive representation distillation. In: International Conference on Learning Representations (2020)"},{"key":"6_CR19","unstructured":"Zagoruyko, S., Komodakis, N.: Paying more attention to attention: improving the performance of convolutional neural networks via attention transfer. In: International Conference on Learning Representations (2017)"},{"key":"6_CR20","doi-asserted-by":"crossref","unstructured":"Ahn, S., Hu, S.X., Damianou, A., et al.: Variational information distillation for knowledge transfer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00938"},{"key":"6_CR21","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Xiang, T., Hospedales, T.M., et al.: Deep mutual learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00454"},{"key":"6_CR22","doi-asserted-by":"publisher","unstructured":"Wang, Y., Xu, C., Xu, C., et al.: Adversarial learning of portable student networks. In: Proceedings of the Conference on Artificial Intelligence, (AAAI), pp. 4260\u20134267 (2018). https:\/\/doi.org\/10.1609\/AAAI.V32I1.11667","DOI":"10.1609\/AAAI.V32I1.11667"},{"key":"6_CR23","doi-asserted-by":"publisher","unstructured":"Chen, H., Wang, Y., Xu, C., et al.: Data-free learning of student networks. In: IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 3513\u20133521 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00361","DOI":"10.1109\/ICCV.2019.00361"},{"key":"6_CR24","doi-asserted-by":"crossref","unstructured":"Chen, P., Liu, S., Zhao, H., et al.: Distilling knowledge via knowledge review. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 5008\u20135017 (2021)","DOI":"10.1109\/CVPR46437.2021.00497"},{"key":"6_CR25","doi-asserted-by":"publisher","unstructured":"Tung, F., Mori, G.: Similarity-preserving knowledge distillation. In: IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 1365\u20131374 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00145","DOI":"10.1109\/ICCV.2019.00145"},{"key":"6_CR26","doi-asserted-by":"crossref","unstructured":"Park, W., Kim, D., Lu, Y., et al.: Relational knowledge distillation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00409"},{"key":"6_CR27","doi-asserted-by":"crossref","unstructured":"Yim, J., Joo, D., Bae, J.H., et al.: A gift from knowledge distillation: fast optimization, network minimization and transfer learning. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 7130\u20137138 (2017)","DOI":"10.1109\/CVPR.2017.754"},{"key":"6_CR28","unstructured":"Wen, W., Wu, C., Wang, Y., et al.: Learning structured sparsity in deep neural networks. In: Proceedings of the 30th International Conference on Neural Information Processing Systems, pp. 2082\u20132090 (2016)"},{"key":"6_CR29","doi-asserted-by":"publisher","unstructured":"Guo, J., Ouyang, W., Xu, D.: Multi-dimensional pruning: a unified framework for model compression. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1505\u20131514 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00158","DOI":"10.1109\/CVPR42600.2020.00158"},{"key":"6_CR30","unstructured":"Fan, A., Grave, E., Joulin, A.: Reducing transformer depth on demand with structured dropout. In: International Conference on Learning Representations (2020)"},{"key":"6_CR31","doi-asserted-by":"crossref","unstructured":"Lin, M., Ji, R., Wang, Y., et al.: Hrank: filter pruning using high-rank feature map. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1526\u20131535 (2020)","DOI":"10.1109\/CVPR42600.2020.00160"},{"key":"6_CR32","doi-asserted-by":"publisher","unstructured":"He, Y., Zhang, X., Sun, J.: Channel pruning for accelerating very deep neural networks. In: IEEE International Conference on Computer Vision (ICCV), pp. 1398\u20131406 (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.155","DOI":"10.1109\/ICCV.2017.155"},{"key":"6_CR33","doi-asserted-by":"crossref","unstructured":"Liu, Z., LI, J., Shen, Z., et al.: Learning efficient convolutional networks through network slimming. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 2736\u20132744 (2017)","DOI":"10.1109\/ICCV.2017.298"},{"key":"6_CR34","doi-asserted-by":"publisher","unstructured":"Chin, T.W., Ding, R., Zhang, C., et al.: Towards efficient model compression via learned global ranking. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1515\u20131525 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00159","DOI":"10.1109\/CVPR42600.2020.00159"},{"key":"6_CR35","doi-asserted-by":"publisher","unstructured":"Yang, H., Yin, H., Shen, M., et al.: Global vision transformer pruning with hessianaware saliency. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 18547\u201318557 (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.01779","DOI":"10.1109\/CVPR52729.2023.01779"},{"key":"6_CR36","unstructured":"Hu, H., Peng, R., Tai, Y.W., et al.: Network trimming: a data-driven neuron pruning approach towards efficient deep architectures (2016). arXiv:1607.03250"},{"key":"6_CR37","doi-asserted-by":"publisher","unstructured":"Luo, J., Wu, J., Lin, W.: Thinet: a filter level pruning method for deep neural network compression. In: IEEE International Conference on Computer Vision, ICCV, pp. 5068\u20135076 (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.541","DOI":"10.1109\/ICCV.2017.541"},{"key":"6_CR38","doi-asserted-by":"publisher","unstructured":"He, Y., Ding, Y., Liu, P., et al.: Learning filter pruning criteria for deep convolutional neural networks acceleration. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2006\u20132015 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00208","DOI":"10.1109\/CVPR42600.2020.00208"},{"key":"6_CR39","doi-asserted-by":"crossref","unstructured":"Gao, S., Huang, F., Pei, J., et al.: Discrete model compression with resource constraint for deep neural networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00197"},{"key":"6_CR40","doi-asserted-by":"publisher","unstructured":"Srinivas, S., Subramanya, A., Babu, R.V.: Training sparse neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 455\u2013462 (2017). https:\/\/doi.org\/10.1109\/CVPRW.2017.61","DOI":"10.1109\/CVPRW.2017.61"},{"issue":"6","key":"6_CR41","doi-asserted-by":"publisher","first-page":"1902","DOI":"10.1109\/TCAD.2021.3093835","volume":"41","author":"K Huang","year":"2022","unstructured":"Huang, K., Chen, S., Li, B., et al.: Acceleration-aware fine-grained channel pruning for deep neural networks via residual gating. IEEE Trans. Comput. Aided Des. Integr. Circuits Syst. 41(6), 1902\u20131915 (2022). https:\/\/doi.org\/10.1109\/TCAD.2021.3093835","journal-title":"IEEE Trans. Comput. Aided Des. Integr. Circuits Syst."},{"key":"6_CR42","doi-asserted-by":"crossref","unstructured":"He, Y., Lin, J., Liu, Z., et al.: AMC: AutoML for model compression and acceleration on mobile devices. In: European Conference on Computer Vision (ECCV), pp. 815\u2013832 (2018)","DOI":"10.1007\/978-3-030-01234-2_48"},{"key":"6_CR43","doi-asserted-by":"crossref","unstructured":"Lin, S., Ji, R., Yan, C., et al.: Towards optimal structured CNN pruning via generative adversarial learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00290"},{"key":"6_CR44","unstructured":"Wang, Y., Xu, C., You, S., et al.: CNNpack: packing convolutional neural networks in the frequency domain. In: Advances in Neural Information Processing Systems, vol. 29 (2016)"},{"key":"6_CR45","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/j.neucom.2021.12.002","volume":"477","author":"Y Ding","year":"2022","unstructured":"Ding, Y., Wu, Y., Huang, C., et al.: Nap: neural architecture search with pruning. Neurocomputing 477, 85\u201395 (2022). https:\/\/doi.org\/10.1016\/j.neucom.2021.12.002","journal-title":"Neurocomputing"},{"key":"6_CR46","doi-asserted-by":"crossref","unstructured":"Ma, N., Zhang, X., Zheng, H.T., et al.: Shufflenet v2: practical guidelines for efficient CNN architecture design. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 116\u2013131 (2018)","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"6_CR47","doi-asserted-by":"crossref","unstructured":"Han, K., Wang, Y., Tian, Q., et al.: Ghostnet: more features from cheap operations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00165"},{"key":"6_CR48","unstructured":"Iandola, F.N., Han, S., Moskewicz, M.W., et al.: Squeezenet: alexnet-level accuracy with 50x fewer parameters and $$<$$0.5 mb model size (2016). arXiv:1602.07360"},{"key":"6_CR49","unstructured":"Howard, A.G., Zhu, M., Chen, B., et al.: MobileNets: efficient convolutional neural networks for mobile vision applications (2017). arXiv:1704.04861"},{"key":"6_CR50","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A.G., Zhu, M., et al.: Mobilenetv2: inverted residuals and linear bottlenecks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510\u20134520 (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"6_CR51","doi-asserted-by":"publisher","unstructured":"Zhang, X., Zhou, X., Lin, M., et al.: Shufflenet: an extremely efficient convolutional neural network for mobile devices. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6848\u20136856 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00716","DOI":"10.1109\/CVPR.2018.00716"},{"key":"6_CR52","unstructured":"Tan, M., Le, Q.: Efficientnet: rethinking model scaling for convolutional neural networks. In: Proceedings of the 36th International Conference on Machine Learning, vol. 97, pp. 6105\u20136114 (2019)"},{"key":"6_CR53","doi-asserted-by":"crossref","unstructured":"Zoph, B., Vasudevan, V., Shlens, J., et al.: Learning transferable architectures for scalable image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00907"},{"key":"6_CR54","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108025","volume":"118","author":"Y Hu","year":"2021","unstructured":"Hu, Y., Wang, X., Li, L., et al.: Improving one-shot NAS with shrinking-and-expanding supernet. Pattern Recogn. 118, 108025 (2021). https:\/\/doi.org\/10.1016\/j.patcog.2021.108025","journal-title":"Pattern Recogn."},{"key":"6_CR55","unstructured":"Li, L., Talwalkar, A.: Random search and reproducibility for neural architecture search. In: Proceedings of Machine Learning Research, Proceedings of the Conference on Uncertainty in Artificial Intelligence, vol. 115, pp. 367\u2013377 (2019)"},{"key":"6_CR56","unstructured":"Liu, H., Simonyan, K., Yang, Y.: DARTS: differentiable architecture search. In: International Conference on Learning Representations (2019)"},{"key":"6_CR57","doi-asserted-by":"publisher","unstructured":"Cai, H., Zhang, Z., Feng, T., et al.: Darts-PD: differentiable architecture search with path-wise weight sharing derivation. In: IEEE International Conference on Image Processing (ICIP), pp. 1256\u20131260 (2022). https:\/\/doi.org\/10.1109\/ICIP46576.2022.9897275","DOI":"10.1109\/ICIP46576.2022.9897275"},{"key":"6_CR58","doi-asserted-by":"publisher","unstructured":"Chen, M., Peng, H., Fu, J., et al.: Autoformer: searching transformers for visual recognition. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 12250\u201312260 (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.01205","DOI":"10.1109\/ICCV48922.2021.01205"},{"issue":"1","key":"6_CR59","doi-asserted-by":"publisher","first-page":"1346","DOI":"10.1109\/TIV.2023.3332594","volume":"9","author":"D Ziwen","year":"2024","unstructured":"Ziwen, D., Dong, Y.: Multi-objective neural architecture search for efficient and fast semantic segmentation on edge. IEEE Trans. Intell. Veh. 9(1), 1346\u20131357 (2024). https:\/\/doi.org\/10.1109\/TIV.2023.3332594","journal-title":"IEEE Trans. Intell. Veh."},{"key":"6_CR60","doi-asserted-by":"crossref","unstructured":"Tan, M., Chen, B., Pang, R., et al.: Mnasnet: platform-aware neural architecture search for mobile. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00293"},{"key":"6_CR61","unstructured":"Dong, P., Niu, X., Li, L., et al.: Prior-guided one-shot neural architecture search (2022). arXiv:2206.13329"},{"key":"6_CR62","unstructured":"Pham, H., Guan, M.Y., Zoph, B., et al.: Efficient neural architecture search via parameter sharing. In: Proceedings of Machine Learning Research, Proceedings of the Conference on Machine Learning, ICML, vol. 80, pp. 4092\u20134101 (2018)"},{"key":"6_CR63","unstructured":"Mellor, J., Turnera, J., Storkey, A.J., et al.: Neural architecture search without training. In: International Conference on Machine Learning, pp. 7588\u20137598 (2021)"},{"key":"6_CR64","doi-asserted-by":"crossref","unstructured":"Dong, P., Li, L., Wei, Z.: Diswot: student architecture search for distillation without training. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 11898\u201311908 (2023)","DOI":"10.1109\/CVPR52729.2023.01145"},{"key":"6_CR65","doi-asserted-by":"crossref","unstructured":"Li, C., Peng, J., Yuan, L., et al.: Blockwisely supervised neural architecture search with knowledge distillation (2020). arXiv:1911.13053","DOI":"10.1109\/CVPR42600.2020.00206"},{"key":"6_CR66","unstructured":"Han, S., Mao, H., Dally, W.J.: Deep compression: compressing deep neural networks with pruning, trained quantization and Huffman coding. In: ICLR (2016)"},{"key":"6_CR67","unstructured":"Zhou, A., Yao, A., Guo, Y., Xu, L., Chen, Y.: Incremental network quantization: towards lossless CNNs with low-precision weights. In: ICLR (2017)"},{"key":"6_CR68","unstructured":"Courbariaux, M., Bengio, Y.: Binarynet: training deep neural net works with weights and activations constrained to +1 or $$-1$$. CoRR, vol. abs\/1602.02830 (2016)"},{"key":"6_CR69","doi-asserted-by":"crossref","unstructured":"Rastegari, M., Ordonez, V., Redmon, J., Farhadi, A.: XNOR-net: imagenet classification using binary convolutional neural networks. In: ECCV (4), pp. 525\u2013542 (2016)","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"6_CR70","doi-asserted-by":"crossref","unstructured":"Nagel, M., van Baalen, M., Blankevoort, T., Welling, M.: Data-free quantization through weight equalization and bias correction. In: ICCV 2019, pp. 1325\u20131334 (2019)","DOI":"10.1109\/ICCV.2019.00141"},{"key":"6_CR71","unstructured":"Banner, R., Nahshan, Y., Hoffer, E., Soudry, D.: ACIQ: analytical clipping for integer quantization of neural networks. CoRR abs\/1810.05723 (2018)"},{"key":"6_CR72","doi-asserted-by":"crossref","unstructured":"Fang, J., Shafiee, A., Abdel-Aziz, H., Thorsley, D., Georgiadis, G., Hassoun, J.: Post-training piecewise linear quantization for deep neural networks. In: ECCV (2), pp. 69\u201386 (2020)","DOI":"10.1007\/978-3-030-58536-5_5"},{"key":"6_CR73","unstructured":"Yang, Y., Yu, J., Jojic, N., Huan, J., Huang, T.S.: FSNet: compression of deep convolutional neural networks by filter summary. In: ICLR 2020 (2020)"},{"issue":"5","key":"6_CR74","doi-asserted-by":"publisher","first-page":"2295","DOI":"10.1137\/090752286","volume":"33","author":"IV Oseledets","year":"2011","unstructured":"Oseledets, I.V.: Tensor-train decomposition. SIAM J. Sci. Comput. 33(5), 2295\u20132317 (2011)","journal-title":"SIAM J. Sci. Comput."},{"key":"6_CR75","doi-asserted-by":"crossref","unstructured":"Ye, J., et al.: Learning compact recurrent neural networks with block-term tensor decomposition. In: CVPR, pp. 9378\u20139387 (2018)","DOI":"10.1109\/CVPR.2018.00977"},{"key":"6_CR76","unstructured":"Li, Y., et al.: MicroNet: towards image recognition with extremely low FLOPs. CoRR abs\/2011.12289 (2020)"},{"key":"6_CR77","doi-asserted-by":"crossref","unstructured":"Yu, H., Wu, J.: Compressing transformers: features are low-rank, but weights are not! In: AAAI 2023, pp. 11007\u201311015 (2023)","DOI":"10.1609\/aaai.v37i9.26304"},{"key":"6_CR78","unstructured":"Lin, J., Rao, Y., Lu, J., et al.: Runtime neural pruning. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, pp. 2178\u2013 2188 (2017)"},{"key":"6_CR79","doi-asserted-by":"crossref","unstructured":"Liu, C., Wang, Y., Han, K., et al.: Learning instance-wise sparsity for accelerating deep models. In: Proceedings of the 28th International Joint Conference on Artificial Intelligence, pp. 3001\u20133007 (2019)","DOI":"10.24963\/ijcai.2019\/416"},{"key":"6_CR80","doi-asserted-by":"publisher","unstructured":"Tang, Y., Wang, Y., Xu, Y., et al.: Manifold regularized dynamic network pruning. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5016\u20135026 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.00498","DOI":"10.1109\/CVPR46437.2021.00498"},{"key":"6_CR81","doi-asserted-by":"publisher","first-page":"38448","DOI":"10.1109\/ACCESS.2023.3267469","volume":"11","author":"J Hu","year":"2023","unstructured":"Hu, J., Lin, P., Zhang, H., et al.: A dynamic pruning method on multiple sparse structures in deep neural networks. IEEE Access 11, 38448\u201338457 (2023). https:\/\/doi.org\/10.1109\/ACCESS.2023.3267469","journal-title":"IEEE Access"},{"key":"6_CR82","doi-asserted-by":"publisher","unstructured":"Wang, Y., Zhang, X., Hu, X., et al.: Dynamic network pruning with interpretable layerwise channel selection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. 04, pp. 6299\u20136306 (2020). https:\/\/doi.org\/10.1609\/aaai.v34.i04.6098","DOI":"10.1609\/aaai.v34.i04.6098"},{"key":"6_CR83","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"420","DOI":"10.1007\/978-3-030-01261-8_25","volume-title":"Computer Vision \u2013 ECCV 2018","author":"X Wang","year":"2018","unstructured":"Wang, X., Yu, F., Dou, Z.-Y., Darrell, T., Gonzalez, J.E.: SkipNet: learning dynamic routing in convolutional networks. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11217, pp. 420\u2013436. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01261-8_25"},{"key":"6_CR84","doi-asserted-by":"publisher","unstructured":"Teerapittayanon, S., Mcdanel, B., Kung, H.T.: Branchynet: fast inference via early exiting from deep neural networks. In: International Conference on Pattern Recognition (ICPR), pp. 2464\u20132469 (2016). https:\/\/doi.org\/10.1109\/icpr.2016.7900006","DOI":"10.1109\/icpr.2016.7900006"},{"key":"6_CR85","unstructured":"Alex, G.: Adaptive computation time for recurrent neural networks (2016)"},{"key":"6_CR86","doi-asserted-by":"publisher","unstructured":"Figurnov, M., Collins, M.D., Zhu, Y., et al.: Spatially adaptive computation time for residual networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.194","DOI":"10.1109\/CVPR.2017.194"}],"container-title":["Lecture Notes in Computer Science","Green, Pervasive, and Cloud Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-1346-8_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T06:21:55Z","timestamp":1760941315000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-1346-8_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,21]]},"ISBN":["9789819513451","9789819513468"],"references-count":86,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-1346-8_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,21]]},"assertion":[{"value":"21 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"GPC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Green, Pervasive, and Cloud Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Macao","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"gpc2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2024.gpc-conf.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}