arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2106.15434cs.LG
收藏

Zoo-Tuning:从动物园模型的自适应转移

Zoo-Tuning: Adaptive Transfer from a Zoo of Models

Tsinghua University(清华大学)

Yang Shu, Zhi Kou, Zhangjie Cao, Jianmin Wang, Mingsheng Long

摘要:

随着深度网络在各种大规模数据集上的发展,可以使用大量的预训练模型。当从模型动物园迁移时,将经典的基于单模型的迁移学习方法应用于每个源模型遭受高计算负担,并且不能充分利用动物园中丰富的知识。我们提出了\emph{Zoo-Tuning}来解决这些挑战,它学习自适应地将预训练模型的参数转移到目标任务。通过可学习的通道对齐层和自适应聚合层,Zoo-Tuning \emph{adaptively aggregates channel aligned pretrained parameters}可以导出目标模型,从而通过同时使多个源模型适应下游任务来促进知识转移。自适应聚合大大降低了训练和推理的计算成本。我们进一步提出了精简的Zoo-Tuning与批量平均门控值的时间合奏,以减少在推理时间的存储成本。我们评估我们的方法在各种任务,包括强化学习,图像分类,和面部标志检测。实验结果表明,所提出的自适应迁移学习方法可以更有效地从一个动物园的模型转移知识。

英文摘要:

With the development of deep networks on various large-scale datasets, a large zoo of pretrained models are available. When transferring from a model zoo, applying classic single-model based transfer learning methods to each source model suffers from high computational burden and cannot fully utilize the rich knowledge in the zoo. We propose \emph{Zoo-Tuning} to address these challenges, which learns to adaptively transfer the parameters of pretrained models to the target task. With the learnable channel alignment layer and adaptive aggregation layer, Zoo-Tuning \emph{adaptively aggregates channel aligned pretrained parameters} to derive the target model, which promotes knowledge transfer by simultaneously adapting multiple source models to downstream tasks. The adaptive aggregation substantially reduces the computation cost at both training and inference. We further propose lite Zoo-Tuning with the temporal ensemble of batch average gating values to reduce the storage cost at the inference time. We evaluate our approach on a variety of tasks, including reinforcement learning, image classification, and facial landmark detection. Experiment results demonstrate that the proposed adaptive transfer learning approach can transfer knowledge from a zoo of models more effectively and efficiently.

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。

↑