{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,17]],"date-time":"2026-10-17T02:47:03Z","timestamp":1792205223616,"version":"4.4.0"},"reference-count":72,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61772366"],"award-info":[{"award-number":["61772366"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172166"],"award-info":[{"award-number":["62172166"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003453","name":"Guangdong Provincial Natural Science Foundation","doi-asserted-by":"publisher","award":["2022A1515011380"],"award-info":[{"award-number":["2022A1515011380"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2024,2]]},"DOI":"10.1016\/j.neunet.2023.11.036","type":"journal-article","created":{"date-parts":[[2023,11,17]],"date-time":"2023-11-17T04:40:27Z","timestamp":1700196027000},"page":"176-189","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":15,"special_numbering":"C","title":["Teacher\u2013student complementary sample contrastive distillation"],"prefix":"10.1016","volume":"170","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9537-9604","authenticated-orcid":false,"given":"Zhiqiang","family":"Bao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenhua","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1413-0693","authenticated-orcid":false,"given":"Jianping","family":"Gou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lan","family":"Du","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingtao","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunwen","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2023.11.036_b1","series-title":"Learning multiple layers of features from tiny images","first-page":"1","author":"Alex","year":"2009"},{"key":"10.1016\/j.neunet.2023.11.036_b2","series-title":"Gated multimodal units for information fusion","author":"Arevalo","year":"2017"},{"key":"10.1016\/j.neunet.2023.11.036_b3","doi-asserted-by":"crossref","unstructured":"Bucilu\u01ce, Cristian, Caruana, Rich, & Niculescu-Mizil, Alexandru (2006). Model compression. In Proc. KDD (pp. 535\u2013541).","DOI":"10.1145\/1150402.1150464"},{"key":"10.1016\/j.neunet.2023.11.036_b4","doi-asserted-by":"crossref","unstructured":"Chen, Pengguang, Liu, Shu, Zhao, Hengshuang, & Jia, Jiaya (2021). Distilling Knowledge via Knowledge Review. In Proc. IEEE conf. comput. vis. pattern recognit. (pp. 5006\u20135015).","DOI":"10.1109\/CVPR46437.2021.00497"},{"key":"10.1016\/j.neunet.2023.11.036_b5","doi-asserted-by":"crossref","unstructured":"Chen, Defang, Mei, Jian-Ping, Wang, Can, Feng, Yan, & Chen, Chun (2020). Online knowledge distillation with diverse peers. In Proc. AAAI conf. artif. intell. (pp. 3430\u20133437).","DOI":"10.1609\/aaai.v34i04.5746"},{"key":"10.1016\/j.neunet.2023.11.036_b6","doi-asserted-by":"crossref","unstructured":"Chen, Defang, Mei, Jian-Ping, Zhang, Hailin, Wang, Can, Feng, Yan, & Chen, Chun (2022). Knowledge Distillation with the Reused Teacher Classifier. In Proc. IEEE conf. comput. vis. pattern recognit. (pp. 11933\u201311942).","DOI":"10.1109\/CVPR52688.2022.01163"},{"key":"10.1016\/j.neunet.2023.11.036_b7","doi-asserted-by":"crossref","first-page":"4919","DOI":"10.1109\/TIP.2021.3077136","article-title":"Learning from images: A distillation learning framework for event cameras","author":"Deng","year":"2021","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.neunet.2023.11.036_b8","article-title":"Multi-level attention-based sample correlations for knowledge distillation","author":"Gou","year":"2022","journal-title":"IEEE Transactions on Industrial Informatics"},{"key":"10.1016\/j.neunet.2023.11.036_b9","doi-asserted-by":"crossref","first-page":"1789","DOI":"10.1007\/s11263-021-01453-z","article-title":"Knowledge distillation: A survey","author":"Gou","year":"2021","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.neunet.2023.11.036_b10","series-title":"Proc. int. conf. mach. learn.","first-page":"1321","article-title":"On calibration of modern neural networks","author":"Guo","year":"2017"},{"key":"10.1016\/j.neunet.2023.11.036_b11","doi-asserted-by":"crossref","unstructured":"Guo, Qiushan, Wang, Xinjiang, Wu, Yichao, Yu, Zhipeng, Liang, Ding, Hu, Xiaolin, et al. (2020). Online knowledge distillation via collaborative learning. In Proc. IEEE conf. comput. vis. pattern recognit. (pp. 11020\u201311029).","DOI":"10.1109\/CVPR42600.2020.01103"},{"key":"10.1016\/j.neunet.2023.11.036_b12","doi-asserted-by":"crossref","unstructured":"He, Kaiming, Zhang, Xiangyu, Ren, Shaoqing, & Sun, Jian (2016). Deep residual learning for image recognition. In Proc. IEEE conf. comput. vis. pattern recognit. (pp. 770\u2013778).","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.1016\/j.neunet.2023.11.036_b13","doi-asserted-by":"crossref","unstructured":"He, Yihui, Zhang, Xiangyu, & Sun, Jian (2017). Channel pruning for accelerating very deep neural networks. In Proc. IEEE int. conf. comput. vis. (pp. 1389\u20131397).","DOI":"10.1109\/ICCV.2017.155"},{"key":"10.1016\/j.neunet.2023.11.036_b14","doi-asserted-by":"crossref","unstructured":"Heo, Byeongho, Kim, Jeesoo, Yun, Sangdoo, Park, Hyojin, Kwak, Nojun, & Choi, Jin Young (2019). A comprehensive overhaul of feature distillation. In Proc. IEEE int. conf. comput. vis..","DOI":"10.1109\/ICCV.2019.00201"},{"key":"10.1016\/j.neunet.2023.11.036_b15","series-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"10.1016\/j.neunet.2023.11.036_b16","doi-asserted-by":"crossref","unstructured":"Huang, Gao, Liu, Zhuang, Van Der Maaten, Laurens, & Weinberger, Kilian Q (2017). Densely connected convolutional networks. In Proc. IEEE conf. comput. vis. pattern recognit. (pp. 4700\u20134708).","DOI":"10.1109\/CVPR.2017.243"},{"key":"10.1016\/j.neunet.2023.11.036_b17","doi-asserted-by":"crossref","first-page":"1364","DOI":"10.1109\/TIP.2022.3141255","article-title":"Feature map distillation of thin nets for low-resolution object recognition","author":"Huang","year":"2022","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.neunet.2023.11.036_b18","doi-asserted-by":"crossref","unstructured":"Jafari, Aref, Rezagholizadeh, Mehdi, Sharma, Pranav, & Ghodsi, Ali (2021). Annealing Knowledge Distillation. In The Association for Computational Linguistics (pp. 2493\u20132504).","DOI":"10.18653\/v1\/2021.eacl-main.212"},{"key":"10.1016\/j.neunet.2023.11.036_b19","series-title":"Bag of tricks for efficient text classification","author":"Joulin","year":"2016"},{"key":"10.1016\/j.neunet.2023.11.036_b20","unstructured":"Kenton, Jacob Devlin Ming-Wei Chang, & Toutanova, Lee Kristina (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Association for Computational Linguistics (pp. 4171\u20134186)."},{"key":"10.1016\/j.neunet.2023.11.036_b21","series-title":"Supervised multimodal bitransformers for classifying images and text","author":"Kiela","year":"2019"},{"key":"10.1016\/j.neunet.2023.11.036_b22","first-page":"3","article-title":"Tiny imagenet visual recognition challenge","author":"Le","year":"2015","journal-title":"CS 231N"},{"issue":"Apr","key":"10.1016\/j.neunet.2023.11.036_b23","first-page":"361","article-title":"Rcv1: A new benchmark collection for text categorization research","volume":"5","author":"Lewis","year":"2004","journal-title":"Journal of Machine Learning Research"},{"key":"10.1016\/j.neunet.2023.11.036_b24","doi-asserted-by":"crossref","first-page":"4735","DOI":"10.1109\/TIP.2021.3066051","article-title":"ResKD: Residual-guided knowledge distillation","author":"Li","year":"2021","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.neunet.2023.11.036_b25","doi-asserted-by":"crossref","unstructured":"Liu, Yufan, Cao, Jiajiong, Li, Bing, Yuan, Chunfeng, Hu, Weiming, Li, Yangxi, et al. (2019). Knowledge distillation via instance relationship graph. In Proc. IEEE conf. comput. vis. pattern recognit. (pp. 7096\u20137104).","DOI":"10.1109\/CVPR.2019.00726"},{"key":"10.1016\/j.neunet.2023.11.036_b26","doi-asserted-by":"crossref","unstructured":"Liu, Yifan, Chen, Ke, Liu, Chris, Qin, Zengchang, Luo, Zhenbo, & Wang, Jingdong (2019). Structured knowledge distillation for semantic segmentation. In Proc. IEEE conf. comput. vis. pattern recognit. (pp. 2604\u20132613).","DOI":"10.1109\/CVPR.2019.00271"},{"key":"10.1016\/j.neunet.2023.11.036_b27","first-page":"20331","article-title":"Early-learning regularization prevents memorization of noisy labels","author":"Liu","year":"2020","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"10.1016\/j.neunet.2023.11.036_b28","series-title":"Learning to teach with student feedback","author":"Liu","year":"2021"},{"key":"10.1016\/j.neunet.2023.11.036_b29","doi-asserted-by":"crossref","unstructured":"Liu, Chang, Tao, Chongyang, Feng, Jiazhan, & Zhao, Dongyan (2022). Multi-Granularity Structural Knowledge Distillation for Language Model Compression. In Association for Computational Linguistics (pp. 1001\u20131011).","DOI":"10.18653\/v1\/2022.acl-long.71"},{"key":"10.1016\/j.neunet.2023.11.036_b30","doi-asserted-by":"crossref","first-page":"5573","DOI":"10.1109\/TIP.2021.3086590","article-title":"Semantics-aware adaptive knowledge distillation for sensor-to-vision action recognition","author":"Liu","year":"2021","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.neunet.2023.11.036_b31","doi-asserted-by":"crossref","unstructured":"Mackowiak, Radek, Ardizzone, Lynton, Kothe, Ullrich, & Rother, Carsten (2021). Generative classifiers as a basis for trustworthy image classification. In Proc. IEEE conf. comput. vis. pattern recognit. (pp. 2971\u20132981).","DOI":"10.1109\/CVPR46437.2021.00299"},{"key":"10.1016\/j.neunet.2023.11.036_b32","doi-asserted-by":"crossref","unstructured":"Mirzadeh, Seyed Iman, Farajtabar, Mehrdad, Li, Ang, Levine, Nir, Matsukawa, Akihiro, & Ghasemzadeh, Hassan (2020). Improved knowledge distillation via teacher assistant. In Proc. AAAI conf. artif. intell. (pp. 5191\u20135198).","DOI":"10.1609\/aaai.v34i04.5963"},{"key":"10.1016\/j.neunet.2023.11.036_b33","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2021.3112816","article-title":"Mining data impressions from deep models as substitute for the unavailable training data","author":"Nayak","year":"2021","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)"},{"key":"10.1016\/j.neunet.2023.11.036_b34","unstructured":"Nguyen, Tam, Mummadi, C., Ngo, T., Beggel, L., & Brox, Thomas (2020). SELF: learning to filter noisy labels with self-ensembling. In Proc. int. conf. learn. represent.."},{"key":"10.1016\/j.neunet.2023.11.036_b35","first-page":"13292","article-title":"Learning student-friendly teacher networks for knowledge distillation","volume":"34","author":"Park","year":"2021","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"10.1016\/j.neunet.2023.11.036_b36","doi-asserted-by":"crossref","unstructured":"Park, Wonpyo, Kim, Dongju, Lu, Yan, & Cho, Minsu (2019). Relational knowledge distillation. In Proc. IEEE conf. comput. vis. pattern recognit. (pp. 3967\u20133976).","DOI":"10.1109\/CVPR.2019.00409"},{"key":"10.1016\/j.neunet.2023.11.036_b37","doi-asserted-by":"crossref","unstructured":"Passalis, Nikolaos, & Tefas, Anastasios (2018). Learning deep representations with probabilistic knowledge transfer. In Proc. Eur. conf. comput. vis. (pp. 268\u2013284).","DOI":"10.1007\/978-3-030-01252-6_17"},{"key":"10.1016\/j.neunet.2023.11.036_b38","article-title":"Automatic differentiation in pytorch","author":"Paszke","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"10.1016\/j.neunet.2023.11.036_b39","doi-asserted-by":"crossref","unstructured":"Peng, Baoyun, Jin, Xiao, Liu, Jiaheng, Li, Dongsheng, Wu, Yichao, Liu, Yu, et al. (2019). Correlation congruence for knowledge distillation. In Proc. IEEE int. conf. comput. vis. (pp. 5007\u20135016).","DOI":"10.1109\/ICCV.2019.00511"},{"key":"10.1016\/j.neunet.2023.11.036_b40","series-title":"Better supervisory signals by observing learning paths","author":"Ren","year":"2022"},{"key":"10.1016\/j.neunet.2023.11.036_b41","series-title":"Fitnets: Hints for thin deep nets","author":"Romero","year":"2014"},{"key":"10.1016\/j.neunet.2023.11.036_b42","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"Imagenet large scale visual recognition challenge","author":"Russakovsky","year":"2015","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.neunet.2023.11.036_b43","series-title":"Deep model compression: Distilling knowledge from noisy teachers","author":"Sau","year":"2016"},{"key":"10.1016\/j.neunet.2023.11.036_b44","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1016\/j.neunet.2023.04.015","article-title":"Multi-teacher knowledge distillation based on joint guidance of probe and adaptive corrector","volume":"164","author":"Shang","year":"2023","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2023.11.036_b45","article-title":"Distilled siamese networks for visual tracking","author":"Shen","year":"2021","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)"},{"key":"10.1016\/j.neunet.2023.11.036_b46","unstructured":"Shen, Zhiqiang, Liu, Zechun, Xu, Dejia, Chen, Zitian, Cheng, Kwang-Ting, & Savvides, Marios (2020). Is Label Smoothing Truly Incompatible with Knowledge Distillation: An Empirical Study. In Proc. int. conf. learn. represent.."},{"key":"10.1016\/j.neunet.2023.11.036_b47","doi-asserted-by":"crossref","first-page":"617","DOI":"10.1016\/j.neunet.2023.05.006","article-title":"Multi-granularity knowledge distillation and prototype consistency regularization for class-incremental learning","volume":"164","author":"Shi","year":"2023","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2023.11.036_b48","doi-asserted-by":"crossref","unstructured":"Smith, Michael R., Martinez, Tony, & Giraud-Carrier, Christophe (2014). An instance level analysis of data complexity. In Proc. int. conf. mach. learn. (pp. 225\u2013256).","DOI":"10.1007\/s10994-013-5422-z"},{"key":"10.1016\/j.neunet.2023.11.036_b49","doi-asserted-by":"crossref","first-page":"3359","DOI":"10.1109\/TIP.2022.3170728","article-title":"Spot-adaptive knowledge distillation","author":"Song","year":"2022","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.neunet.2023.11.036_b50","doi-asserted-by":"crossref","unstructured":"Supancic, James S., & Ramanan, Deva (2013). Self-paced learning for long-term tracking. In Proc. IEEE conf. comput. vis. pattern recognit. (pp. 2379\u20132386).","DOI":"10.1109\/CVPR.2013.308"},{"key":"10.1016\/j.neunet.2023.11.036_b51","unstructured":"Tai, Cheng, Xiao, Tong, Zhang, Yi, Wang, Xiaogang, & Weinan, E (2016). Convolutional neural networks with low-rank regularization. In Proc. int. conf. learn. represent.."},{"key":"10.1016\/j.neunet.2023.11.036_b52","series-title":"Understanding and improving knowledge distillation","author":"Tang","year":"2020"},{"key":"10.1016\/j.neunet.2023.11.036_b53","article-title":"Adaptive perspective distillation for semantic segmentation","author":"Tian","year":"2022","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)"},{"key":"10.1016\/j.neunet.2023.11.036_b54","unstructured":"Tian, Yonglong, Krishnan, Dilip, & Isola, Phillip (2020). Contrastive Representation Distillation. In Proc. int. conf. learn. represent.."},{"key":"10.1016\/j.neunet.2023.11.036_b55","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1016\/j.neunet.2021.11.002","article-title":"Multi-view teacher\u2013student network","volume":"146","author":"Tian","year":"2022","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2023.11.036_b56","doi-asserted-by":"crossref","unstructured":"Tung, Frederick, & Mori, Greg (2019). Similarity-preserving knowledge distillation. In Proc. IEEE int. conf. comput. vis. (pp. 1365\u20131374).","DOI":"10.1109\/ICCV.2019.00145"},{"key":"10.1016\/j.neunet.2023.11.036_b57","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"10.1016\/j.neunet.2023.11.036_b58","series-title":"Mitigating neural network overconfidence with logit normalization","author":"Wei","year":"2022"},{"key":"10.1016\/j.neunet.2023.11.036_b59","doi-asserted-by":"crossref","unstructured":"Wu, Guile, & Gong, Shaogang (2021). Peer collaborative learning for online knowledge distillation. In Proc. AAAI conf. artif. intell. (pp. 10302\u201310310).","DOI":"10.1609\/aaai.v35i12.17234"},{"key":"10.1016\/j.neunet.2023.11.036_b60","doi-asserted-by":"crossref","first-page":"228","DOI":"10.1016\/j.neunet.2023.01.025","article-title":"Achieving efficient interpretability of reinforcement learning via policy distillation and selective input gradient regularization","volume":"161","author":"Xing","year":"2023","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2023.11.036_b61","first-page":"2313","article-title":"Auto-encoding and distilling scene graphs for image captioning","author":"Yang","year":"2022","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)"},{"key":"10.1016\/j.neunet.2023.11.036_b62","doi-asserted-by":"crossref","unstructured":"Yang, Chuanguang, Zhou, Helong, An, Zhulin, Jiang, Xue, Xu, Yongjun, & Zhang, Qian (2022). Cross-image relational knowledge distillation for semantic segmentation. In Proc. IEEE conf. comput. vis. pattern recognit. (pp. 12319\u201312328).","DOI":"10.1109\/CVPR52688.2022.01200"},{"key":"10.1016\/j.neunet.2023.11.036_b63","doi-asserted-by":"crossref","unstructured":"Yu, Lu, Yazici, Vacit Oguz, Liu, Xialei, Weijer, Joost van de, Cheng, Yongmei, & Ramisa, Arnau (2019). Learning metrics from teachers: Compact networks for image embedding. In Proc. IEEE conf. comput. vis. pattern recognit. (pp. 2907\u20132916).","DOI":"10.1109\/CVPR.2019.00302"},{"key":"10.1016\/j.neunet.2023.11.036_b64","doi-asserted-by":"crossref","unstructured":"Yuan, Fei, Shou, Linjun, Pei, Jian, Lin, Wutao, Gong, Ming, Fu, Yan, et al. (2021). Reinforced multi-teacher selection for knowledge distillation. In Proc. AAAI conf. artif. intell., vol. 35, no. 16 (pp. 14284\u201314291).","DOI":"10.1609\/aaai.v35i16.17680"},{"key":"10.1016\/j.neunet.2023.11.036_b65","doi-asserted-by":"crossref","unstructured":"Yuan, Li, Tay, Francis EH, Li, Guilin, Wang, Tao, & Feng, Jiashi (2020). Revisiting knowledge distillation via label smoothing regularization. In Proc. IEEE conf. comput. vis. pattern recognit. (pp. 3903\u20133911).","DOI":"10.1109\/CVPR42600.2020.00396"},{"key":"10.1016\/j.neunet.2023.11.036_b66","unstructured":"Zagoruyko, S., & Komodakis, N. (2016). Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer. In Proc. int. conf. learn. represent.."},{"key":"10.1016\/j.neunet.2023.11.036_b67","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1145\/3446776","article-title":"Understanding deep learning (still) requires rethinking generalization","author":"Zhang","year":"2021","journal-title":"Communications of the ACM"},{"key":"10.1016\/j.neunet.2023.11.036_b68","first-page":"1","article-title":"Quantifying the knowledge in a DNN to explain knowledge distillation for classification","author":"Zhang","year":"2022","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)"},{"key":"10.1016\/j.neunet.2023.11.036_b69","doi-asserted-by":"crossref","unstructured":"Zhang, Linfeng, Song, Jiebo, Gao, Anni, Chen, Jingwei, Bao, Chenglong, & Ma, Kaisheng (2019). Be your own teacher: Improve the performance of convolutional neural networks via self distillation. In Proc. IEEE int. conf. comput. vis. (pp. 3713\u20133722).","DOI":"10.1109\/ICCV.2019.00381"},{"key":"10.1016\/j.neunet.2023.11.036_b70","doi-asserted-by":"crossref","unstructured":"Zhang, Ying, Xiang, Tao, Hospedales, Timothy M., & Lu, Huchuan (2018). Deep mutual learning. In Proc. IEEE conf. comput. vis. pattern recognit. (pp. 4320\u20134328).","DOI":"10.1109\/CVPR.2018.00454"},{"key":"10.1016\/j.neunet.2023.11.036_b71","doi-asserted-by":"crossref","unstructured":"Zhao, Borui, Cui, Quan, Song, Renjie, Qiu, Yiyu, & Liang, Jiajun (2022). Decoupled Knowledge Distillation. In Proc. IEEE conf. comput. vis. pattern recognit. (pp. 11953\u201311962).","DOI":"10.1109\/CVPR52688.2022.01165"},{"key":"10.1016\/j.neunet.2023.11.036_b72","first-page":"8602","article-title":"Curriculum learning by dynamic instance hardness","author":"Zhou","year":"2020","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608023006597?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608023006597?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T02:35:32Z","timestamp":1760236532000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608023006597"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2]]},"references-count":72,"alternative-id":["S0893608023006597"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2023.11.036","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2024,2]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Teacher\u2013student complementary sample contrastive distillation","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2023.11.036","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2023 Elsevier Ltd. All rights reserved.","name":"copyright","label":"Copyright"}]}}