{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/exploring-inter-channel-correlation-for","title":"Exploring Inter-Channel Correlation for Diversity-Preserved Knowledge Distillation","arxiv_id":null,"date":"2021-01-01","proceeding":"ICCV 2021 10","authors":["Li Liu","Qingle Huang","Sihao Lin","Hongwei Xie","Bing Wang","Xiaojun Chang","Xiaodan Liang"],"abstract":"    Knowledge Distillation has shown very promising ability in transferring learned representation from the larger model (teacher) to the smaller one (student). Despite many efforts, prior methods ignore the important role of retaining inter-channel correlation of features, leading to the lack of capturing intrinsic distribution of the feature space and sufficient diversity properties of features in the teacher network. To solve the issue, we propose the novel Inter-Channel Correlation for Knowledge Distillation (ICKD), with which the diversity and homology of the feature space of the student network can align with that of the teacher network. The correlation between these two channels is interpreted as diversity if they are irrelevant to each other, otherwise homology. Then the student is required to mimic the correlation within its own embedding space. In addition, we introduce the grid-level inter-channel correlation, making it capable of dense prediction tasks. Extensive experiments on two vision tasks, including ImageNet classification and Pascal VOC segmentation, demonstrate the superiority of our ICKD, which consistently outperforms many existing methods, advancing the state-of-the-art in the fields of Knowledge Distillation. To our knowledge, we are the first method based on knowledge distillation boosts ResNet18 beyond 72% Top-1 accuracy on ImageNet classification. Code is available at: https://github.com/ADLab-AutoDrive/ICKD.    ","url_abs":"http://openaccess.thecvf.com//content/ICCV2021/html/Liu_Exploring_Inter-Channel_Correlation_for_Diversity-Preserved_Knowledge_Distillation_ICCV_2021_paper.html","url_pdf":"http://openaccess.thecvf.com//content/ICCV2021/papers/Liu_Exploring_Inter-Channel_Correlation_for_Diversity-Preserved_Knowledge_Distillation_ICCV_2021_paper.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"exploring-inter-channel-correlation-for","repo_url":"https://github.com/adlab-autodrive/ickd","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"exploring-inter-channel-correlation-for","repo_url":"https://github.com/yoshitomo-matsubara/torchdistill","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/knowledge-distillation-on-imagenet","task":"Knowledge Distillation","dataset":"ImageNet","model":"ICKD (T: ResNet-34  S:ResNet-18)","rank_in_archive_order":32,"of":52,"metrics":{"CRD training setting":"✘","Top-1 accuracy %":"72.19"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}