{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T16:41:25Z","timestamp":1777567285952,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":60,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"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":[[2023,10,26]]},"DOI":"10.1145\/3581783.3611788","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:30Z","timestamp":1698391650000},"page":"5272-5280","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Avatar Knowledge Distillation: Self-ensemble Teacher Paradigm with Uncertainty"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1268-3131","authenticated-orcid":false,"given":"Yuan","family":"Zhang","sequence":"first","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4141-7833","authenticated-orcid":false,"given":"Weihua","family":"Chen","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0296-3540","authenticated-orcid":false,"given":"Yichen","family":"Lu","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4463-4078","authenticated-orcid":false,"given":"Tao","family":"Huang","sequence":"additional","affiliation":[{"name":"The University of Sydney, Sydney, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7208-8078","authenticated-orcid":false,"given":"Xiuyu","family":"Sun","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4724-7065","authenticated-orcid":false,"given":"Jian","family":"Cao","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Andreas Damianou, Neil D Lawrence, and Zhenwen Dai.","author":"Ahn Sungsoo","year":"2019","unstructured":"Sungsoo Ahn, Shell Xu Hu, Andreas Damianou, Neil D Lawrence, and Zhenwen Dai. 2019. Variational information distillation for knowledge transfer. In CVPR. 9163--9171."},{"key":"e_1_3_2_1_2_1","unstructured":"Charles Blundell Julien Cornebise Koray Kavukcuoglu and Daan Wierstra. 2015. Weight uncertainty in neural network. In ICML. PMLR 1613--1622."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Zhaowei Cai and Nuno Vasconcelos. 2018. Cascade r-cnn: Delving into high quality object detection. In CVPR. 6154--6162.","DOI":"10.1109\/CVPR.2018.00644"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Yevgen Chebotar and Austin Waters. 2016. Distilling knowledge from ensembles of neural networks for speech recognition.. In Interspeech. 3439--3443.","DOI":"10.21437\/Interspeech.2016-1190"},{"key":"e_1_3_2_1_5_1","volume-title":"NeurIPS","volume":"30","author":"Chen Guobin","year":"2017","unstructured":"Guobin Chen, Wongun Choi, Xiang Yu, Tony Han, and Manmohan Chandraker. 2017. Learning efficient object detection models with knowledge distillation. NeurIPS, Vol. 30 (2017)."},{"key":"e_1_3_2_1_6_1","unstructured":"Kai Chen Jiaqi Wang Jiangmiao Pang Yuhang Cao Yu Xiong Xiaoxiao Li Shuyang Sun Wansen Feng Ziwei Liu Jiarui Xu et al. 2019. MMDetection: Open mmlab detection toolbox and benchmark. arXiv preprint arXiv:1906.07155 (2019)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Liang-Chieh Chen Yukun Zhu George Papandreou Florian Schroff and Hartwig Adam. 2018. Encoder-decoder with atrous separable convolution for semantic image segmentation. In ECCV. 801--818.","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"e_1_3_2_1_8_1","unstructured":"MMSegmentation Contributors. 2020. MMSegmentation: OpenMMLab Semantic Segmentation Toolbox and Benchmark. https:\/\/github.com\/open-mmlab\/mmsegmentation."},{"key":"e_1_3_2_1_9_1","unstructured":"MMRazor Contributors. 2021. OpenMMLab Model Compression Toolbox and Benchmark. https:\/\/github.com\/open-mmlab\/mmrazor."},{"key":"e_1_3_2_1_10_1","unstructured":"MMPreTrain Contributors. 2023. OpenMMLab's Pre-training Toolbox and Benchmark. https:\/\/github.com\/open-mmlab\/mmpretrain."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Marius Cordts Mohamed Omran Sebastian Ramos Timo Rehfeld Markus Enzweiler Rodrigo Benenson Uwe Franke Stefan Roth and Bernt Schiele. 2016. The Cityscapes Dataset for Semantic Urban Scene Understanding. In CVPR.","DOI":"10.1109\/CVPR.2016.350"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Xing Dai Zeren Jiang Zhao Wu Yiping Bao Zhicheng Wang Si Liu and Erjin Zhou. 2021. General instance distillation for object detection. In CVPR. 7842--7851.","DOI":"10.1109\/CVPR46437.2021.00775"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","unstructured":"Jia Deng Wei Dong Richard Socher Li-Jia Li Kai Li and Li Fei-Fei. 2009. ImageNet: A large-scale hierarchical image database. In CVPR. 248--255. https:\/\/doi.org\/10.1109\/CVPR.2009.5206848","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_14_1","first-page":"12345","article-title":"Agree to disagree: Adaptive ensemble knowledge distillation in gradient space","volume":"33","author":"Du Shangchen","year":"2020","unstructured":"Shangchen Du, Shan You, Xiaojie Li, Jianlong Wu, Fei Wang, Chen Qian, and Changshui Zhang. 2020. Agree to disagree: Adaptive ensemble knowledge distillation in gradient space. NeurIPS, Vol. 33 (2020), 12345--12355.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_15_1","unstructured":"Zhixing Du Rui Zhang Ming-Fang Chang Xishan Zhang Shaoli Liu Tianshi Chen and Yunji Chen. 2021. Distilling Object Detectors with Feature Richness. In NeurIPS."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"Takashi Fukuda Masayuki Suzuki Gakuto Kurata Samuel Thomas Jia Cui and Bhuvana Ramabhadran. 2017. Efficient Knowledge Distillation from an Ensemble of Teachers.. In Interspeech. 3697--3701.","DOI":"10.21437\/Interspeech.2017-614"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep residual learning for image recognition. In CVPR. 770--778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_18_1","volume-title":"NeurIPS Workshop","author":"Hinton Geoffrey","year":"2014","unstructured":"Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2014. Distilling the knowledge in a neural network. NeurIPS Workshop (2014)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Jie Hu Li Shen and Gang Sun. 2018. Squeeze-and-excitation networks. In CVPR. 7132--7141.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"e_1_3_2_1_20_1","unstructured":"Tao Huang Shan You Fei Wang Chen Qian and Chang Xu. 2022a. Knowledge Distillation from A Stronger Teacher. In NeurIPS Alice H. Oh Alekh Agarwal Danielle Belgrave and Kyunghyun Cho (Eds.). https:\/\/openreview.net\/forum?id=157Usp_kbi"},{"key":"e_1_3_2_1_21_1","volume-title":"Masked Distillation with Receptive Tokens. arXiv preprint arXiv:2205.14589","author":"Huang Tao","year":"2022","unstructured":"Tao Huang, Yuan Zhang, Shan You, Fei Wang, Chen Qian, Jian Cao, and Chang Xu. 2022b. Masked Distillation with Receptive Tokens. arXiv preprint arXiv:2205.14589 (2022)."},{"key":"e_1_3_2_1_22_1","volume-title":"Knowledge Diffusion for Distillation. arXiv preprint arXiv:2305.15712","author":"Huang Tao","year":"2023","unstructured":"Tao Huang, Yuan Zhang, Mingkai Zheng, Shan You, Fei Wang, Chen Qian, and Chang Xu. 2023. Knowledge Diffusion for Distillation. arXiv preprint arXiv:2305.15712 (2023)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00244"},{"key":"e_1_3_2_1_24_1","volume-title":"NeurIPS","volume":"30","author":"Kendall Alex","year":"2017","unstructured":"Alex Kendall and Yarin Gal. 2017. What uncertainties do we need in bayesian deep learning for computer vision? NeurIPS, Vol. 30 (2017)."},{"key":"e_1_3_2_1_25_1","volume-title":"NeurIPS","volume":"28","author":"Kingma Durk P","year":"2015","unstructured":"Durk P Kingma, Tim Salimans, and Max Welling. 2015. Variational dropout and the local reparameterization trick. NeurIPS, Vol. 28 (2015)."},{"key":"e_1_3_2_1_26_1","volume-title":"Adaptive knowledge distillation based on entropy","author":"Kwon Kisoo","unstructured":"Kisoo Kwon, Hwidong Na, Hoshik Lee, and Nam Soo Kim. 2020. Adaptive knowledge distillation based on entropy. In ICASSP. IEEE, 7409--7413."},{"key":"e_1_3_2_1_27_1","unstructured":"Quanquan Li Shengying Jin and Junjie Yan. 2017. Mimicking very efficient network for object detection. In CVPR. 6356--6364."},{"key":"e_1_3_2_1_28_1","unstructured":"Xiang Li Wenhai Wang Xiaolin Hu and Jian Yang. 2019. Selective kernel networks. In CVPR. 510--519."},{"key":"e_1_3_2_1_29_1","unstructured":"Tsung-Yi Lin Piotr Doll\u00e1r Ross Girshick Kaiming He Bharath Hariharan and Serge Belongie. 2017a. Feature pyramid networks for object detection. In CVPR. 2117--2125."},{"key":"e_1_3_2_1_30_1","unstructured":"Tsung-Yi Lin Priya Goyal Ross Girshick Kaiming He and Piotr Doll\u00e1r. 2017b. Focal loss for dense object detection. In ICCV. 2980--2988."},{"key":"e_1_3_2_1_31_1","volume-title":"Microsoft coco: Common objects in context","author":"Lin Tsung-Yi","unstructured":"Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r, and C Lawrence Zitnick. 2014. Microsoft coco: Common objects in context. In ECCV. Springer, 740--755."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.07.048"},{"key":"e_1_3_2_1_33_1","volume-title":"A simple baseline for bayesian uncertainty in deep learning. Advances in neural information processing systems","author":"Maddox Wesley J","year":"2019","unstructured":"Wesley J Maddox, Pavel Izmailov, Timur Garipov, Dmitry P Vetrov, and Andrew Gordon Wilson. 2019. A simple baseline for bayesian uncertainty in deep learning. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_34_1","volume-title":"Ablation-cam: Visual explanations for deep convolutional network via gradient-free localization. In WACV. 983--991.","author":"Ramaswamy Harish Guruprasad","year":"2020","unstructured":"Harish Guruprasad Ramaswamy et al. 2020. Ablation-cam: Visual explanations for deep convolutional network via gradient-free localization. In WACV. 983--991."},{"key":"e_1_3_2_1_35_1","volume-title":"NeurIPS","volume":"28","author":"Ren Shaoqing","year":"2015","unstructured":"Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. NeurIPS, Vol. 28 (2015)."},{"key":"e_1_3_2_1_36_1","volume-title":"Antoine Chassang, Carlo Gatta, and Yoshua Bengio.","author":"Romero Adriana","year":"2015","unstructured":"Adriana Romero, Nicolas Ballas, Samira Ebrahimi Kahou, Antoine Chassang, Carlo Gatta, and Yoshua Bengio. 2015. Fitnets: Hints for thin deep nets. In ICLR."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"crossref","unstructured":"Mark Sandler Andrew Howard Menglong Zhu Andrey Zhmoginov and Liang-Chieh Chen. 2018. Mobilenetv2: Inverted residuals and linear bottlenecks. In CVPR. 4510--4520.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_3_2_1_38_1","unstructured":"Yichun Shi and Anil K Jain. 2019. Probabilistic face embeddings. In ICCV. 6902--6911."},{"key":"e_1_3_2_1_39_1","unstructured":"Changyong Shu Yifan Liu Jianfei Gao Zheng Yan and Chunhua Shen. 2021. Channel-Wise Knowledge Distillation for Dense Prediction. In ICCV. 5311--5320."},{"key":"e_1_3_2_1_40_1","volume-title":"Weighted boxes fusion: Ensembling boxes from different object detection models. Image and Vision Computing","author":"Solovyev Roman","year":"2021","unstructured":"Roman Solovyev, Weimin Wang, and Tatiana Gabruseva. 2021. Weighted boxes fusion: Ensembling boxes from different object detection models. Image and Vision Computing (2021), 1--6."},{"key":"e_1_3_2_1_41_1","volume-title":"Fcos: Fully convolutional one-stage object detection. In ICCV. 9627--9636.","author":"Tian Zhi","year":"2019","unstructured":"Zhi Tian, Chunhua Shen, Hao Chen, and Tong He. 2019. Fcos: Fully convolutional one-stage object detection. In ICCV. 9627--9636."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"crossref","unstructured":"Tao Wang Li Yuan Xiaopeng Zhang and Jiashi Feng. 2019. Distilling object detectors with fine-grained feature imitation. In CVPR. 4933--4942.","DOI":"10.1109\/CVPR.2019.00507"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"crossref","unstructured":"Zhenyu Wang Yali Li Ye Guo Lu Fang and Shengjin Wang. 2021. Data-uncertainty guided multi-phase learning for semi-supervised object detection. In CVPR. 4568--4577.","DOI":"10.1109\/CVPR46437.2021.00454"},{"key":"e_1_3_2_1_44_1","volume-title":"Cbam: Convolutional block attention module. In ECCV. 3--19.","author":"Woo Sanghyun","year":"2018","unstructured":"Sanghyun Woo, Jongchan Park, Joon-Young Lee, and In So Kweon. 2018. Cbam: Convolutional block attention module. In ECCV. 3--19."},{"key":"e_1_3_2_1_45_1","volume-title":"Multi-teacher knowledge distillation for compressed video action recognition on deep neural networks","author":"Wu Meng-Chieh","unstructured":"Meng-Chieh Wu, Ching-Te Chiu, and Kun-Hsuan Wu. 2019. Multi-teacher knowledge distillation for compressed video action recognition on deep neural networks. In ICASSP. IEEE, 2202--2206."},{"key":"e_1_3_2_1_46_1","unstructured":"Saining Xie Ross Girshick Piotr Doll\u00e1r Zhuowen Tu and Kaiming He. 2017. Aggregated residual transformations for deep neural networks. In CVPR. 1492--1500."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"crossref","unstructured":"Zhendong Yang Zhe Li Xiaohu Jiang Yuan Gong Zehuan Yuan Danpei Zhao and Chun Yuan. 2022a. Focal and global knowledge distillation for detectors. In CVPR. 4643--4652.","DOI":"10.1109\/CVPR52688.2022.00460"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_4"},{"key":"e_1_3_2_1_49_1","volume-title":"Reppoints: Point set representation for object detection. In ICCV. 9657--9666.","author":"Yang Ze","year":"2019","unstructured":"Ze Yang, Shaohui Liu, Han Hu, Liwei Wang, and Stephen Lin. 2019. Reppoints: Point set representation for object detection. In ICCV. 9657--9666."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"crossref","unstructured":"Shan You Chang Xu Chao Xu and Dacheng Tao. 2017. Learning from multiple teacher networks. In SIGKDD. 1285--1294.","DOI":"10.1145\/3097983.3098135"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17680"},{"key":"e_1_3_2_1_52_1","volume-title":"Confidence-aware multi-teacher knowledge distillation","author":"Zhang Hailin","unstructured":"Hailin Zhang, Defang Chen, and Can Wang. 2022. Confidence-aware multi-teacher knowledge distillation. In ICASSP. IEEE, 4498--4502."},{"key":"e_1_3_2_1_53_1","volume-title":"Distilling neuron spike with high temperature in reinforcement learning agents. arXiv preprint arXiv:2108.10078","author":"Zhang Ling","year":"2021","unstructured":"Ling Zhang, Jian Cao, Yuan Zhang, Bohan Zhou, and Shuo Feng. 2021a. Distilling neuron spike with high temperature in reinforcement learning agents. arXiv preprint arXiv:2108.10078 (2021)."},{"key":"e_1_3_2_1_54_1","unstructured":"Linfeng Zhang and Kaisheng Ma. 2020. Improve object detection with feature-based knowledge distillation: Towards accurate and efficient detectors. In ICLR."},{"key":"e_1_3_2_1_55_1","volume-title":"Prime-aware adaptive distillation","author":"Zhang Youcai","unstructured":"Youcai Zhang, Zhonghao Lan, Yuchen Dai, Fangao Zeng, Yan Bai, Jie Chang, and Yichen Wei. 2020. Prime-aware adaptive distillation. In ECCV. Springer, 658--674."},{"key":"e_1_3_2_1_56_1","first-page":"17616","article-title":"Relative Uncertainty Learning for Facial Expression Recognition","volume":"34","author":"Zhang Yuhang","year":"2021","unstructured":"Yuhang Zhang, Chengrui Wang, and Weihong Deng. 2021b. Relative Uncertainty Learning for Facial Expression Recognition. NeurIPS, Vol. 34 (2021), 17616--17627.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_57_1","unstructured":"Hengshuang Zhao Jianping Shi Xiaojuan Qi Xiaogang Wang and Jiaya Jia. 2017. Pyramid scene parsing network. In CVPR. 2881--2890."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16468"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01395-y"},{"key":"e_1_3_2_1_60_1","unstructured":"Xizhou Zhu Dazhi Cheng Zheng Zhang Stephen Lin and Jifeng Dai. 2019. An empirical study of spatial attention mechanisms in deep networks. In ICCV. 6688--6697."}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611788","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3611788","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:00:46Z","timestamp":1755820846000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611788"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":60,"alternative-id":["10.1145\/3581783.3611788","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3611788","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}