Robust Text‐Based Person Search via Noisy Pair Identification and Pseudo‐Text Augmentation

ABSTRACT Text‐based person search (TBPS) aims to retrieve pedestrian images from a database based on natural language descriptions. However, existing TBPS methods often assume that image‐text pairs in training datasets are perfectly aligned, neglecting noisy annotations characterized by coarse‐grained or mismatched descriptions. This letter presents a robust TBPS framework that addresses these challenges through two key innovations. First, we design a dual‐channel Gaussian mixture model (GMM) to identify noisy image‐text pairs by leveraging both global and local feature‐level alignment losses. Second, for the detected noisy samples, we generate pseudo‐texts using a multimodal large language model (MLLM) and filter them via a dynamic semantic consistency scoring mechanism to ensure high‐quality supervision. Extensive experiments on ICFG‐PEDES and RSTPReid demonstrate that our method consistently improves top‐k retrieval metrics.