Counterfactual Intervention Feature Transfer for Visible-Infrared Person Re-identification

@inproceedings{Li2022CounterfactualIF,
  title={Counterfactual Intervention Feature Transfer for Visible-Infrared Person Re-identification},
  author={Xulin Li and Yan Lu and B. Liu and Yating Liu and Guojun Yin and Qi Chu and Jinyang Huang and Feng Zhu and Rui Zhao and Nenghai Yu},
  booktitle={European Conference on Computer Vision},
  year={2022}
}
. Graph-based models have achieved great success in person re-identification tasks recently, which compute the graph topology structure (affinities) among different people first and then pass the information across them to achieve stronger features. But we find existing graph-based methods in the visible-infrared person re-identification task (VI-ReID) suffer from bad generalization because of two issues: 1) train-test modality balance gap , which is a property of VI-ReID task. The number of… 

Figures and Tables from this paper

References

SHOWING 1-10 OF 48 REFERENCES

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

An intra-modality weighted-part attention module to extract discriminative part-aggregated features, by imposing the domain knowledge on the part relationship mining, and a parameter-free dynamic dual aggregation learning strategy to adaptively integrate the two components in a progressive joint training manner.

Spectral Feature Transformation for Person Re-Identification

Inspired by spectral clustering, a novel module termed Spectral Feature Transformation is developed to facilitate the optimization of group-wise similarities and adds no burden to the inference and can be applied to various scenarios.

Person Re-identification with Deep Similarity-Guided Graph Neural Network

This paper proposes a novel deep learning framework, named Similarity-Guided Graph Neural Network (SGGNN), which learns the edge weights with rich labels of gallery instance pairs directly, which provides relation fusion more precise information.

Discover Cross-Modality Nuances for Visible-Infrared Person Re-Identification

A joint Modality and Pattern Alignment Network (MPANet) is proposed to discover cross-modality nuances in different patterns for visible-infrared person Re-ID, which introduces a modality alleviation module and a pattern alignment module to jointly extract discriminative features.

Visible Thermal Person Re-Identification via Dual-Constrained Top-Ranking

A dual-path network with a novel bi-directional dual-constrained top-ranking loss to learn discriminative feature representations and identity loss is further incorporated to model the identity-specific information to handle large intra-class variations.

A Multi-Constraint Similarity Learning with Adaptive Weighting for Visible-Thermal Person Re-Identification

A Multi-Constraint (MC) similarity learning method that jointly considers the crossmodality relationships from three different aspects, i.e., Instance-to-Instance (I2I), Center-to -Instance (C2I, and Center- to-Center (C1C), is proposed.

Syncretic Modality Collaborative Learning for Visible Infrared Person Re-Identification

This paper explores the correlation between two modalities and proposes a novel syncretic modality collaborative learning (SMCL) model to bridge the cross-modality gap and demonstrates the effectiveness and superiority of the proposed method.

Hierarchical Discriminative Learning for Visible Thermal Person Re-Identification

An improved two-stream CNN network is presented to learn the multi-modality sharable feature representations and identity loss and contrastive loss are integrated to enhance the discriminability and modality-invariance with partially shared layer parameters.

Deep Group-Shuffling Random Walk for Person Re-identification

A novel group-shuffling random walk network for fully utilizing the affinity information between gallery images in both the training and testing processes and which outperforms state-of-the-art methods on the Market-1501, CUHK03, and DukeMTMC datasets by large margins.

Bag of Tricks and a Strong Baseline for Deep Person Re-Identification

A simple and efficient baseline for person re-identification with deep neural networks by combining effective training tricks together, which achieves 94.5% rank-1 and 85.9% mAP on Market1501 with only using global features.