Larger Norm More Transferable: An Adaptive Feature Norm Approach for Unsupervised Domain Adaptation

Abstract

Domain adaptation enables the learner to safely generalize into novel environments by mitigating domain shifts across distributions. Previous works may not effectively uncover the underlying reasons that would lead to the drastic model degradation on the target task. In this paper, we empirically reveal that the erratic discrimination of the target domain mainly stems from its much smaller feature norms with respect to that of the source domain. To this end, we propose a novel parameter-free Adaptive Feature Norm approach. We demonstrate that progressively adapting the feature norms of the two domains to a large range of values can result in significant transfer gains, implying that those task-specific features with larger norms are more transferable. Our method successfully unifies the computation of both standard and partial domain adaptation with more robustness against the negative transfer issue. Without bells and whistles but a few lines of code, our method substantially lifts the performance on the target task and exceeds state-of-the-arts by a large margin (11.5% on Office-Home and 17.1% on VisDA2017). We hope our simple yet effective approach will shed some light on the future research of transfer learning. Code is available at https://github.com/jihanyang/AFN.

arXiv commentAccepted as an Oral presentation at ICCV2019

References in corpus (10)

• Learning Transferable Features with Deep Adaptation Networks
• Deep Domain Confusion: Maximizing for Domain Invariance
• Conditional Adversarial Domain Adaptation
• Unsupervised Domain Adaptation with Residual Transfer Networks
• Domain Separation Networks
• VisDA: The Visual Domain Adaptation Challenge
• Asymmetric Tri-training for Unsupervised Domain Adaptation
• A DIRT-T Approach to Unsupervised Domain Adaptation
• Rethinking the Smaller-Norm-Less-Informative Assumption in Channel Pruning of Convolution Layers
• Characterizing and Avoiding Negative Transfer

Cited by in corpus (4)

• Frustratingly Easy Person Re-Identification: Generalizing Person Re-ID in Practice
• Adversarial Bi-Regressor Network for Domain Adaptive Regression
• Domain-Adaptive Few-Shot Learning
• Domain Adaptation and Image Classification via Deep Conditional Adaptation Network