arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.08528cs.CVcs.LG
收藏

采用共享分类器的自适应教学知识蒸馏

Adaptive Teaching with Shared Classifier for Knowledge Distillation

The Catholic University of Korea(韩国天主教大学);DenComm;AI Lab(AI实验室)

Jaeyeon Jang, Young-Ik Kim, Jisu Lim, Hyeonseong Lee

AI总结:

本文提出ATSC知识蒸馏方法,通过共享分类器并让预训练教师依据学生能力自适应调整,在单教师和多教师场景的CIFAR-100与ImageNet上达到最先进性能。

摘要:

知识蒸馏(KD)是一种将知识从参数过参数化的教师网络迁移到参数较少的学生网络、从而尽量降低所产生性能损失的技术。KD方法可分为离线方法和在线方法。离线KD利用强大的预训练教师网络,而在线KD允许动态调整教师网络,以提升学生网络的学习效果。最近研究发现,共享教师网络的分类器能够显著提升学生网络的性能,同时仅带来极少的网络参数增加。基于这些认识,我们提出采用共享分类器的自适应教学(ATSC)。在ATSC中,预训练教师网络会根据学生网络的能力进行自我调整,以更好地契合学生网络的学习需求,并且学生网络受益于共享分类器,从而提升其性能。此外,我们将ATSC扩展到具有多个教师的环境。我们开展了大量实验,证明了所提出KD方法的有效性。在单教师和多教师场景下,我们的方法均在CIFAR-100和ImageNet数据集上取得了最先进结果,而所需模型参数仅适度增加。源代码已公开发布于https://github.com/random2314235/ATSC。

英文摘要:

Knowledge distillation (KD) is a technique used to transfer knowledge from an overparameterized teacher network to a less-parameterized student network, thereby minimizing the incurred performance loss. KD methods can be categorized into offline and online approaches. Offline KD leverages a powerful pretrained teacher network, while online KD allows the teacher network to be adjusted dynamically to enhance the learning effectiveness of the student network. Recently, it has been discovered that sharing the classifier of the teacher network can significantly boost the performance of the student network with only a minimal increase in the number of network parameters. Building on these insights, we propose adaptive teaching with a shared classifier (ATSC). In ATSC, the pretrained teacher network self-adjusts to better align with the learning needs of the student network based on its capabilities, and the student network benefits from the shared classifier, enhancing its performance. Additionally, we extend ATSC to environments with multiple teachers. We conduct extensive experiments, demonstrating the effectiveness of the proposed KD method. Our approach achieves state-of-the-art results on the CIFAR-100 and ImageNet datasets in both single-teacher and multiteacher scenarios, with only a modest increase in the number of required model parameters. The source code is publicly available at https://github.com/random2314235/ATSC.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑