Towards Fair Knowledge Transfer for Imbalanced Domain Adaptation

Abstract

Domain adaptation (DA) becomes an up-and-coming technique to address the insufficient or no annotation issue by exploiting external source knowledge. Existing DA algorithms mainly focus on practical knowledge transfer through domain alignment. Unfortunately, they ignore the fairness issue when the auxiliary source is extremely imbalanced across different categories, which results in severe under-presented knowledge adaptation of minority source set. To this end, we propose a Towards Fair Knowledge Transfer (TFKT) framework to handle the fairness challenge in imbalanced cross-domain learning. Specifically, a novel cross-domain mixup generation is exploited to augment the minority source set with target information to enhance fairness. Moreover, dual distinct classifiers and cross-domain prototype alignment are developed to seek a more robust classifier boundary and mitigate the domain shift. Such three strategies are formulated into a unified framework to address the fairness issue and domain shift challenge. Extensive experiments over two popular benchmarks have verified the effectiveness of our proposed model by comparing to existing state-of-the-art DA models, and especially our model significantly improves over 20% on two benchmarks in terms of the overall accuracy.

References in corpus (17)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Prototypical Networks for Few-shot Learning
• Learning Transferable Features with Deep Adaptation Networks
• Deep Domain Confusion: Maximizing for Domain Invariance
• Conditional Adversarial Domain Adaptation
• Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learning
• Data Decisions and Theoretical Implications when Adversarially Learning Fair Representations
• Wasserstein Distance Guided Representation Learning for Domain Adaptation
• Transfer Learning with Dynamic Distribution Adaptation
• Deep Transfer Network: Unsupervised Domain Adaptation
• A Reductions Approach to Fair Classification
• Multi-Adversarial Domain Adaptation
• Complementary Pseudo Labels For Unsupervised Domain Adaptation On Person Re-identification
• Transfer of Machine Learning Fairness across Domains
• Discriminatory Transfer
• Adversarial Domain Adaptation with Domain Mixup
• Discriminative Cross-Domain Feature Learning for Partial Domain Adaptation

Cited by in corpus (2)

• Inverse Image Frequency for Long-tailed Image Recognition
• Adversarial Bi-Regressor Network for Domain Adaptive Regression