Dynamic Dual-Attentive Aggregation Learning for Visible-Infrared Person Re-Identification

TL;DR

This paper introduces a novel dynamic dual-attentive aggregation learning method for visible-infrared person re-identification, effectively capturing intra-modality and cross-modality cues to improve discriminability and robustness against noise.

Contribution

The paper proposes a dynamic dual-attentive aggregation approach that mines intra-modality and cross-modality contextual cues, enhancing feature discriminability and robustness in VI-ReID.

Findings

Outperforms state-of-the-art methods in various settings

Effective in handling noisy samples and large intra-class variations

Improves discriminative part feature extraction

Abstract

Visible-infrared person re-identification (VI-ReID) is a challenging cross-modality pedestrian retrieval problem. Due to the large intra-class variations and cross-modality discrepancy with large amount of sample noise, it is difficult to learn discriminative part features. Existing VI-ReID methods instead tend to learn global representations, which have limited discriminability and weak robustness to noisy images. In this paper, we propose a novel dynamic dual-attentive aggregation (DDAG) learning method by mining both intra-modality part-level and cross-modality graph-level contextual cues for VI-ReID. We propose an intra-modality weighted-part attention module to extract discriminative part-aggregated features, by imposing the domain knowledge on the part relationship mining. To enhance robustness against noisy samples, we introduce cross-modality graph structured attention to reinforce the representation with the contextual relations across the two modalities. We also develop a parameter-free dynamic dual aggregation learning strategy to adaptively integrate the two components in a progressive joint training manner. Extensive experiments demonstrate that DDAG outperforms the state-of-the-art methods under various settings.