Dependability Feature Learning based on Sample Generation for Unsupervised Text-to-Image Person Re-identification

Text-to-image person re-identification (TIReID) aims to retrieve the target pedestrians according to specific textual descriptions. Benefiting from abundant annotated training data, current supervised TIReID methods have achieved impressive performance. However, annotating cross-modality data is extremely time-consuming, which limits their application in real-world scenarios. Several methods attempt to generate text descriptions or pseudo-labels but neglect the dependability of image-text matching relationships or identity information. To this end, we propose a Dependability Feature Learning based on Sample Generation (DFLSG) for unsupervised TIReID. First, we introduce a dependable text generation method that leverages multimodal large language models to generate diverse texts and further filtrate dependable texts for establishing image-text matching relationships. Second, we design an Error Sample Filtering Module (ESFM) to eliminate abnormal samples and obtain reliable identity labels. Furthermore, we develop a Multilevel Triplet Joint Learning (MTJL) process, which continuously optimizes the cross-modality dependable feature from center and instance views. Extensive experiments are implemented to assess the proposed DFLSG on four mainstream TIReID databases. Experimental results demonstrate that DFLSG achieves state-of-the-art performance compared with other unsupervised methods. Code will be available at: https://github.com/CLS-2001/DFLSG.