"ICG"

"    The representation of human parts plays a crucial role in person re-identification (re-ID) by offering discriminative cues, yet it presents challenges such as misalignment, occlusion, and extreme illumination. Previous methods have primarily focused on achieving strict part-level consistency. However, individual part features change inevitably under harsh conditions, hindering consistent representation.     In this paper, we propose an Instance-level Consistent Graph (ICG) framework to address this issue, which extracts structural information by introducing graph modeling atop unsupervised human parts. Firstly, we introduce an attention-based foreground separation to suppress non-instance noise. Subsequently, an unsupervised clustering method is designed to segment pixel-wise human parts within the foreground, enabling fine-grained part representations. We propose a Flexible Structure Graph that derives instance-level structure from part features, treating each part feature as a node in a graph convolutional network.     In essence, ICG mitigates incompleteness through feature flow among nodes, broadening the matching condition from strict part-level consistency to robust instance-level consistency. Extensive experiments on four popular person re-ID datasets demonstrate that ICG outperforms most state-of-the-art methods, exhibiting remarkable improvements over the baseline. "