MSO: Multi-Feature Space Joint Optimization Network for RGB-Infrared Person Re-Identification

@article{Gao2021MSOMS,
  title={MSO: Multi-Feature Space Joint Optimization Network for RGB-Infrared Person Re-Identification},
  author={Yajun Gao and Tengfei Liang and Yi Jin and Xiaoyan Gu and Wu Liu and Yidong Li and Congyan Lang},
  journal={Proceedings of the 29th ACM International Conference on Multimedia},
  year={2021}
}
The RGB-infrared cross-modality person re-identification (ReID) task aims to recognize the images of the same identity between the visible modality and the infrared modality. Existing methods mainly use a two-stream architecture to eliminate the discrepancy between the two modalities in the final common feature space, which ignore the single space of each modality in the shallow layers. To solve it, in this paper, we present a novel multi-feature space joint optimization (MSO) network, which… 

Figures and Tables from this paper

References

SHOWING 1-10 OF 101 REFERENCES
HPILN: a feature learning framework for cross-modality person re-identification
TLDR
A novel feature learning framework, hard pentaplet and identity loss network (HPILN), is proposed, which outperforms all existing ones in terms of cumulative match characteristic curve and mean average precision.
Learning Modality-Specific Representations for Visible-Infrared Person Re-Identification
TLDR
This paper proposes a novel framework that employs modality-specific networks to tackle with the heterogeneous matching problem and demonstrates that the MSR effectively improves the performance of deep networks on VI-REID and remarkably outperforms the state-of-the-art methods.
Visible-Infrared Person Re-Identification via Homogeneous Augmented Tri-Modal Learning
TLDR
This paper proposes a Homogeneous Augmented Tri-Modal (HAT) learning method for VI-ReID, where an auxiliary grayscale modality is generated from their homogeneous visible images, without additional training process, and significantly outperforms the current state-of-the-art by a large margin.
HPILN: A feature learning framework for cross-modality person re-identification
TLDR
A novel feature learning framework, HPILN, is proposed, following which specifically designed hard pentaplet loss and identity loss are used to improve the performance of the modified cross-modality re-identification models.
RGB-Infrared Cross-Modality Person Re-Identification via Joint Pixel and Feature Alignment
TLDR
A novel and end-to-end Alignment Generative Adversarial Network (AlignGAN) for the RGB-IR RE-ID task, which consists of a pixel generator, a feature generator and a joint discriminator that is able to not only alleviate the cross-modality and intra- modality variations, but also learn identity-consistent features.
Hetero-Center Loss for Cross-Modality Person Re-Identification
TLDR
A novel loss function, called Hetero-Center loss (HC loss) is proposed to reduce the intra-class cross-modality variations and a simple and high-performance network architecture to learn local feature representations for cross- modality person re-identification is proposed, which can be a baseline for future research.
Cross-Modality Paired-Images Generation for RGB-Infrared Person Re-Identification
TLDR
This paper proposes to generate cross-modality paired-images and perform both global set-level and fine-grained instance-level alignments for RGB-IR Re-ID and demonstrates that the proposed model favourably against state-of-the-art methods.
Co-Attentive Lifting for Infrared-Visible Person Re-Identification
TLDR
A novel attention-based approach to handle the two difficulties in a unified framework of infrared-visible cross-modality person re-identification and proposes an attention lifting mechanism to learn discriminative features in each modality.
A Similarity Inference Metric for RGB-Infrared Cross-Modality Person Re-identification
TLDR
A novel similarity inference metric (SIM) that exploits the intra-modality sample similarities to circumvent the cross- modality discrepancy targeting optimal cross-modalities image matching and achieves significant accuracy improvement but with little extra training.
Modality-aware Collaborative Learning for Visible Thermal Person Re-Identification
TLDR
A novel modality-aware collaborative (MAC) learning method on top of a two-stream network for VT-ReID, which handles the modalities-discrepancy in both feature level and classifier level, and introduces a collaborative learning scheme, which regularizes themodality-sharable and modality -specific identity classifiers by utilizing the relationship between different classifiers.
...
1
2
3
4
5
...