Diverse Embedding Expansion Network and Low-Light Cross-Modality Benchmark for Visible-Infrared Person Re-identification

CVPR 2023  ·  Yukang Zhang, Hanzi Wang ·

For the visible-infrared person re-identification (VIReID) task, one of the major challenges is the modality gaps between visible (VIS) and infrared (IR) images. However, the training samples are usually limited, while the modality gaps are too large, which leads that the existing methods cannot effectively mine diverse cross-modality clues. To handle this limitation, we propose a novel augmentation network in the embedding space, called diverse embedding expansion network (DEEN). The proposed DEEN can effectively generate diverse embeddings to learn the informative feature representations and reduce the modality discrepancy between the VIS and IR images. Moreover, the VIReID model may be seriously affected by drastic illumination changes, while all the existing VIReID datasets are captured under sufficient illumination without significant light changes. Thus, we provide a low-light cross-modality (LLCM) dataset, which contains 46,767 bounding boxes of 1,064 identities captured by 9 RGB/IR cameras. Extensive experiments on the SYSU-MM01, RegDB and LLCM datasets show the superiority of the proposed DEEN over several other state-of-the-art methods. The code and dataset are released at: https://github.com/ZYK100/LLCM

PDF Abstract CVPR 2023 PDF CVPR 2023 Abstract

Datasets


Introduced in the Paper:

LLCM

Used in the Paper:

SYSU-MM01
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Cross-Modal Person Re-Identification SYSU-MM01 DEEN mAP (All-search & Single-shot) 71.8 # 1
rank1 74.7 # 1

Methods


No methods listed for this paper. Add relevant methods here