CVMay 5, 2024

Fast One-Stage Unsupervised Domain Adaptive Person Search

arXiv:2405.02832v19 citationsh-index: 18Has CodeIJCAI
Originality Incremental advance
AI Analysis

This addresses the challenge of domain variations in unlabeled person search for computer vision applications, but it is incremental as it builds on existing multi-stage models.

The paper tackles the problem of unsupervised person search by proposing a fast one-stage method that integrates domain adaptation and label adaptation without iterative clustering, achieving state-of-the-art performance on CUHK-SYSU and PRW datasets.

Unsupervised person search aims to localize a particular target person from a gallery set of scene images without annotations, which is extremely challenging due to the unexpected variations of the unlabeled domains. However, most existing methods dedicate to developing multi-stage models to adapt domain variations while using clustering for iterative model training, which inevitably increases model complexity. To address this issue, we propose a Fast One-stage Unsupervised person Search (FOUS) which complementary integrates domain adaptaion with label adaptaion within an end-to-end manner without iterative clustering. To minimize the domain discrepancy, FOUS introduced an Attention-based Domain Alignment Module (ADAM) which can not only align various domains for both detection and ReID tasks but also construct an attention mechanism to reduce the adverse impacts of low-quality candidates resulting from unsupervised detection. Moreover, to avoid the redundant iterative clustering mode, FOUS adopts a prototype-guided labeling method which minimizes redundant correlation computations for partial samples and assigns noisy coarse label groups efficiently. The coarse label groups will be continuously refined via label-flexible training network with an adaptive selection strategy. With the adapted domains and labels, FOUS can achieve the state-of-the-art (SOTA) performance on two benchmark datasets, CUHK-SYSU and PRW. The code is available at https://github.com/whbdmu/FOUS.

Code Implementations1 repo
Foundations

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

Your Notes