Learning With Dual Noisy Labels for Text-to-Image Person Re-Identification

Text-to-image person re-identification (TIReID) aims to identify a target person from a given textual description. Although recent work has made significant progress, most of it implicitly assumes that the sample annotations are correct and that the cross-modal correspondence in each image-text pair is well aligned. However, such an assumption requires elaborately annotated datasets, which are expensive and even impossible to obtain in practice. To alleviate this issue, in this letter, we explore a new TIReID setting, termed learning with dual noisy labels, in which the model learns from data with both noisy identity labels and noisy correspondence. We propose a general framework called TDTD (Two stage framework for Dual noise of TIReID) to achieve this. In the first stage, a Noise-Aware Preliminary Learning (NAPL) strategy selects “easy” triplets to train a noise-tolerant initial model. In the second stage, the model leverages reliable representations from NAPL to automatically correct both identity and correspondence errors via soft-label estimation and is then fine-tuned on the entire dataset using a dual noise-robust triplet loss. Extensive experiments on three public benchmarks, CUHK-PEDES, ICFG-PEDES, and RSTPReID, demonstrate the performance and robustness of TDTD, achieving state-of-the-art results under dual noise conditions.