Cerberus: Attribute-based person re-identification using semantic IDs

TL;DR

Cerberus is a novel framework for attribute-based person re-identification that uses semantic IDs and a semantic guidance loss to improve representation learning, enabling better recognition, attribute recognition, and search.

Contribution

The paper introduces semantic IDs and a semantic guidance loss to enhance attribute-based person reID and generalization to unseen data.

Findings

Outperforms state-of-the-art on Market-1501 and DukeMTMC benchmarks.

Effectively recognizes person attributes and performs attribute-based search.

Improves generalization through SID prototype regularization.

Abstract

We introduce a new framework, dubbed Cerberus, for attribute-based person re-identification (reID). Our approach leverages person attribute labels to learn local and global person representations that encode specific traits, such as gender and clothing style. To achieve this, we define semantic IDs (SIDs) by combining attribute labels, and use a semantic guidance loss to align the person representations with the prototypical features of corresponding SIDs, encouraging the representations to encode the relevant semantics. Simultaneously, we enforce the representations of the same person to be embedded closely, enabling recognizing subtle differences in appearance to discriminate persons sharing the same attribute labels. To increase the generalization ability on unseen data, we also propose a regularization method that takes advantage of the relationships between SID prototypes. Our framework performs individual comparisons of local and global person representations between query and gallery images for attribute-based reID. By exploiting the SID prototypes aligned with the corresponding representations, it can also perform person attribute recognition (PAR) and attribute-based person search (APS) without bells and whistles. Experimental results on standard benchmarks on attribute-based person reID, Market-1501 and DukeMTMC, demonstrate the superiority of our model compared to the state of the art.