Multi-cascaded attention and overlapping part features network for person re-identification

Zhang, Xin; Hou, Mingzheng; Deng, Xiaoyan; Feng, Ziliang

doi:10.1007/s11760-021-02106-x

Cited by 5 publications

(1 citation statement)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lin et al [24] introduce additional attribute information, such as gender, hair length, age, backpacks, and so on, to enforce model learning of local details. Attention mechanisms have been adopted in [25]- [27] to emphasize feature extraction on human body areas. [28], [29] fully exploit the knowledge from the source domain to address cross-domain re-ID.…”

Section: A Holistic Person Re-identificationmentioning

confidence: 99%

Patch Features Reconstruction Transformer for Occluded Person Re-Identification

Zhao

Zhu

Liang

2022

2022 41st Chinese Control Conference (CCC)

View full text Add to dashboard Cite

Person re-identification (re-ID) continues to pose a significant challenge, particularly in scenarios involving occlusions. Prior approaches aimed at tackling occlusions have predominantly focused on aligning physical body features through the utilization of external semantic cues. However, these methods tend to be intricate and susceptible to noise. To address the aforementioned challenges, we present an innovative end-toend solution known as the Dynamic Patch-aware Enrichment Transformer (DPEFormer). This model effectively distinguishes human body information from occlusions automatically and dynamically, eliminating the need for external detectors or precise image alignment. Specifically, we introduce a dynamic patch token selection module (DPSM). DPSM utilizes a label-guided proxy token as an intermediary to identify informative occlusionfree tokens. These tokens are then selected for deriving subsequent local part features. To facilitate the seamless integration of global classification features with the finely detailed local features selected by DPSM, we introduce a novel feature blending module (FBM). FBM enhances feature representation through the complementary nature of information and the exploitation of part diversity. Furthermore, to ensure that DPSM and the entire DPEFormer can effectively learn with only identity labels, we also propose a Realistic Occlusion Augmentation (ROA) strategy. This strategy leverages the recent advances in the Segment Anything Model (SAM) [1]. As a result, it generates occlusion images that closely resemble real-world occlusions, greatly enhancing the subsequent contrastive learning process. Experiments on occluded and holistic re-ID benchmarks signify a substantial advancement of DPEFormer over existing state-ofthe-art approaches. The code will be made publicly available.

show abstract