{"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/dot-a-distillation-oriented-trainer","title":"DOT: A Distillation-Oriented Trainer","arxiv_id":"2307.08436","date":"2023-07-17","proceeding":"ICCV 2023 1","authors":["Borui Zhao","Quan Cui","RenJie Song","Jiajun Liang"],"abstract":"Knowledge distillation transfers knowledge from a large model to a small one via task and distillation losses. In this paper, we observe a trade-off between task and distillation losses, i.e., introducing distillation loss limits the convergence of task loss. We believe that the trade-off results from the insufficient optimization of distillation loss. The reason is: The teacher has a lower task loss than the student, and a lower distillation loss drives the student more similar to the teacher, then a better-converged task loss could be obtained. To break the trade-off, we propose the Distillation-Oriented Trainer (DOT). DOT separately considers gradients of task and distillation losses, then applies a larger momentum to distillation loss to accelerate its optimization. We empirically prove that DOT breaks the trade-off, i.e., both losses are sufficiently optimized. Extensive experiments validate the superiority of DOT. Notably, DOT achieves a +2.59% accuracy improvement on ImageNet-1k for the ResNet50-MobileNetV1 pair. Conclusively, DOT greatly benefits the student's optimization properties in terms of loss convergence and model generalization. Code will be made publicly available.","url_abs":"https://arxiv.org/abs/2307.08436v1","url_pdf":"https://arxiv.org/pdf/2307.08436v1.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":"dot-a-distillation-oriented-trainer","repo_url":"https://github.com/megvii-research/mdistiller","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2307.08436","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}