Self-Paced Collaborative and Adversarial Network for Unsupervised Domain Adaptation

TL;DR

This paper introduces a novel unsupervised domain adaptation method called CAN, combining collaborative and adversarial learning strategies to improve feature representation and achieve state-of-the-art results across multiple datasets.

Contribution

It proposes a unified framework that integrates domain-specific and domain-invariant feature learning with a self-paced pseudo-labeling strategy for enhanced adaptation.

Findings

Achieves state-of-the-art performance on benchmark datasets.

Effectively learns domain-specific and domain-invariant features.

Demonstrates robustness across image and video recognition tasks.

Abstract

This paper proposes a new unsupervised domain adaptation approach called Collaborative and Adversarial Network (CAN), which uses the domain-collaborative and domain-adversarial learning strategy for training the neural network. The domain-collaborative learning aims to learn domain-specific feature representation to preserve the discriminability for the target domain, while the domain adversarial learning aims to learn domain-invariant feature representation to reduce the domain distribution mismatch between the source and target domains. We show that these two learning strategies can be uniformly formulated as domain classifier learning with positive or negative weights on the losses. We then design a collaborative and adversarial training scheme, which automatically learns domain-specific representations from lower blocks in CNNs through collaborative learning and domain-invariant representations from higher blocks through adversarial learning. Moreover, to further enhance the discriminability in the target domain, we propose Self-Paced CAN (SPCAN), which progressively selects pseudo-labeled target samples for re-training the classifiers. We employ a self-paced learning strategy to select pseudo-labeled target samples in an easy-to-hard fashion. Comprehensive experiments on different benchmark datasets, Office-31, ImageCLEF-DA, and VISDA-2017 for the object recognition task, and UCF101-10 and HMDB51-10 for the video action recognition task, show our newly proposed approaches achieve the state-of-the-art performance, which clearly demonstrates the effectiveness of our proposed approaches for unsupervised domain adaptation.