SSKD: Self-Supervised Knowledge Distillation for Cross Domain Adaptive Person Re-Identification

TL;DR

This paper introduces SSKD, a self-supervised knowledge distillation approach that improves cross-domain person re-identification by leveraging multi-view features and soft labels to reduce label noise and enhance feature learning.

Contribution

The paper proposes a novel SSKD framework combining identity and soft label learning modules for better domain adaptation in person re-ID, outperforming existing methods.

Findings

Outperforms state-of-the-art methods on multiple adaptation tasks.

Effectively reduces label noise through dual-module learning.

Enhances feature representation by exploiting multi-view augmented images.

Abstract

Domain adaptive person re-identification (re-ID) is a challenging task due to the large discrepancy between the source domain and the target domain. To reduce the domain discrepancy, existing methods mainly attempt to generate pseudo labels for unlabeled target images by clustering algorithms. However, clustering methods tend to bring noisy labels and the rich fine-grained details in unlabeled images are not sufficiently exploited. In this paper, we seek to improve the quality of labels by capturing feature representation from multiple augmented views of unlabeled images. To this end, we propose a Self-Supervised Knowledge Distillation (SSKD) technique containing two modules, the identity learning and the soft label learning. Identity learning explores the relationship between unlabeled samples and predicts their one-hot labels by clustering to give exact information for confidently distinguished images. Soft label learning regards labels as a distribution and induces an image to be associated with several related classes for training peer network in a self-supervised manner, where the slowly evolving network is a core to obtain soft labels as a gentle constraint for reliable images. Finally, the two modules can resist label noise for re-ID by enhancing each other and systematically integrating label information from unlabeled images. Extensive experiments on several adaptation tasks demonstrate that the proposed method outperforms the current state-of-the-art approaches by large margins.