Towards Robustness of Person Search against Corruptions
Keywords: Corruption, Person Search, Robustness
Abstract: Person search aims to simultaneously detect and re-identify a query person within an entire scene, involving detection and re-identification as a multi-task problem.
While existing studies have made significant progress in achieving superior performance on clean datasets, the challenge of robustness under various corruptions remains largely unexplored.
To address this gap, we propose two benchmarks, CUHK-SYSU-C and PRW-C, designed to assess the robustness of person search models across diverse corruption scenarios.
Previous researches on corruption have been conducted independently for single tasks such as re-identification and detection.
However, recent advancements in person search adopt an end-to-end multi-task learning framework that processes the entire scene as input, unlike the combination of single tasks.
This raises the question of whether independent achievements can ensure corruption robustness for person search.
Our findings reveal that merely combining independent, robust detection and re-identification models is not sufficient for achieving robust person search.
We further investigate the vulnerability of the detection and representation stages to corruption and explore its impact on both foreground and background areas.
Based on these insights, we propose a foreground-aware augmentation and regularization method to enhance the robustness of person search models.
Supported by our comprehensive robustness analysis and evaluation framework our benchmarks provide, our proposed technique substantially improves the robustness of existing person search models.
Code will be made publicly available.
Primary Area: applications to computer vision, audio, language, and other modalities
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 7041
Loading