Diverse semantic information fusion for unsupervised person re-identification

Unsupervised Person Re-Identification (Re-ID) has achieved considerable success through leveraging various approaches that rely on hard pseudo-labels. Prior work mainly focused on improving the quality of pseudo-labels or enhancing the robustness of representation learning model. However, there has been little focus on exploring the contextual semantic information, which can reveal rich relations within samples and provide complementary knowledge to assist the hard pseudo-labels. To this end, we propose a novel method named FuseDSI to explore the potential to harness diverse contextual semantic information fusion. In addition to the hard pseudo labels, FuseDSI explores additional pair-wise semantic information and neighborhood semantic information within each mini-batch through online self-exploration. Furthermore, it leverages the explored semantic information as an additional supervisory signal to enhance robust representation learning. For these two types of contextual semantic information are dynamically estimated in an online manner based on the model’s status, they complement each other well with the hard pseudo-labels. One significant advantage of FuseDSI is its flexibility in combining various pseudo-labels-based methods. Moreover, since exploring the contextual semantic information requires no external elaborate module nor memory-consuming memory bank, it maintains the structure of baseline model with negligible impact on training time. Experimental studies on two widely used person ReID benchmark datasets (MSMT17, Market-1501) demonstrate that FuseDSI consistently improves the performance of baseline model and achieves the state-of-the-art results. Code is available at: FuseDSI.