Adversarial Decoupling and Modality-Invariant Representation Learning for Visible-Infrared Person Re-Identification

Visible-infrared person re-identification (RGB-IR ReID) has now attracted increasing attention due to its surveillance applications under low-light environments. However, the large intra-class variations between different domains are still a challenging issue in the field of computer vision. To address the above issue, we propose a novel adversarial Decoupling and Modality-invariant Representation learning (DMiR) method to explore potential spectrum-invariant yet identity-discriminative representations for cross-modality pedestrians. Our model consists of three key components, including Domain-related Representation Disentanglement (DrRD), Modality-invariant Discriminative Representation (MiDR) and Representation Orthogonal Decorrelation (ROD). First, two subnets named Identity-Net and Domain-Net are designed to extract identity-related features and domain-related features, respectively. Given this two-stream structure, the DrRD is introduced to achieve adversarial decoupling against domain-specific features via a min-max disentanglement process. Specifically, the classification objective function on Domain-Net is minimized to extract spectrum-specific information while maximizing it to reduce domain-specific information. Second, in Identity-Net, we introduce MiDR to enhance intra-class compactness and reduce domain variations by exploring positive and negative pair variations, semantic-wise differences, and pair-wise semantic variations. Finally, the correlation between the two decomposed features, i.e., identity-related features and domain-related features, may lead to the introduction of modal information in identity representations, and vice versa. Therefore, we present the ROD constraint to make the two decomposed features unrelated to each other, which can more effectively separate the two-component features and enhance feature representations. Practically, we construct ROD at the feature-level and parameter-level, and finally select feature-level ROD as the decorrelation strategy because of its superior decorrelation performance. The whole scheme leads to disentangling spectrum-dependent information, as well as purifying identity information. Extensive experiments are carried out on two mainstream RGB-IR ReID datasets, and the results demonstrate the effectiveness of our method.

Automated summary

In this paper, a novel adversarial decoupling and modality-invariant representation learning method is proposed for visible-infrared person re-identification (RGB-IR ReID). By decoupling domain-related features and identity-related features, and orthogonal decorrelation between them, the method effectively separates identity information and domain information for cross-modality pedestrians, improving the accuracy of re-identification.