CVOct 19, 2020

Domain Generalized Person Re-Identification via Cross-Domain Episodic Learning

arXiv:2010.09561v116 citations
Originality Incremental advance
AI Analysis

It addresses a practical problem for computer vision applications where labeled target data is unavailable, representing an incremental advance over prior domain adaptation methods.

The paper tackles domain generalized person re-identification by learning domain-invariant features without access to target-domain training data, achieving state-of-the-art results on four benchmark datasets.

Aiming at recognizing images of the same person across distinct camera views, person re-identification (re-ID) has been among active research topics in computer vision. Most existing re-ID works require collection of a large amount of labeled image data from the scenes of interest. When the data to be recognized are different from the source-domain training ones, a number of domain adaptation approaches have been proposed. Nevertheless, one still needs to collect labeled or unlabelled target-domain data during training. In this paper, we tackle an even more challenging and practical setting, domain generalized (DG) person re-ID. That is, while a number of labeled source-domain datasets are available, we do not have access to any target-domain training data. In order to learn domain-invariant features without knowing the target domain of interest, we present an episodic learning scheme which advances meta learning strategies to exploit the observed source-domain labeled data. The learned features would exhibit sufficient domain-invariant properties while not overfitting the source-domain data or ID labels. Our experiments on four benchmark datasets confirm the superiority of our method over the state-of-the-arts.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes