Modality Synergy Complement Learning with Cascaded Aggregation for Visible-Infrared Person Re-Identification

Visible-Infrared Re-Identification (VI-ReID) is challenging in image retrievals. The modality discrepancy will easily make huge intra-class variations. Most existing methods either bridge different modalities through modality-invariance or generate the intermediate modality for better performance. Differently, this paper proposes a novel framework, named Modality Synergy Complement Learning Network (MSCLNet) with Cascaded Aggregation. Its basic idea is to synergize two modalities to construct diverse representations of identity-discriminative semantics and less noise. Then, we complement synergistic representations under the advantages of the two modalities. Furthermore, we propose the Cascaded Aggregation strategy for fine-grained optimization of the feature distribution, which progressively aggregates feature embeddings from the subclass, intra-class, and inter-class. Extensive experiments on SYSU-MM01 and RegDB datasets show that MSCLNet outperforms the state-of-the-art by a large margin. On the large-scale SYSU-MM01 dataset, our model can achieve 76.99% and 71.64% in terms of Rank-1 accuracy and mAP value. Our code will be available at https://github.com/ bitreidgroup/VI- ReID- MSCLNet.

Automated summary

Visible-Infrared Re-Identification is a challenging task due to the modality discrepancy. This paper proposes a novel framework, MSCLNet, that synergizes two modalities to construct diverse representations and complements them to improve performance. The Cascaded Aggregation strategy is used to optimize the feature distribution. Experimental results demonstrate the superiority of MSCLNet over existing methods.