Timezone: »

Zoo-Tuning: Adaptive Transfer from A Zoo of Models
Yang Shu · Zhi Kou · Zhangjie Cao · Jianmin Wang · Mingsheng Long

Tue Jul 20 05:40 AM -- 05:45 AM (PDT) @

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 cost 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 simultaneously promotes knowledge transfer and adapts 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 more effectively and efficiently transfer knowledge from a zoo of models.

Author Information

Yang Shu (Tsinghua University)
Zhi Kou (Tsinghua University)
Zhangjie Cao (Tsinghua University)
Jianmin Wang (Tsinghua University)
Mingsheng Long (Tsinghua University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors