Triplet interactive attention network for cross-modality person re-identification

Abstract Cross-modality (RGB-Infrared) person re-identification (ReID) has extreme superiority on low illumination ReID over conventional RGB-RGB matching due to its excellent capability on bridging cross-modality discrepancy. Previous works often focus on extracting modality-invariant global features, whereas the interaction among pairwise samples provides the most important clues for identifying persons. To explore the interactive clues among cross-modality pedestrian images, we propose a Triplet Interactive Attention Network (TIAN) to imitate the pairwise interactions and generate the attention scores for triplet samples. It can discover the fine-grained difference between pedestrian images and is optimized by successive attention losses to strengthen the feature learning capability of the backbone network. Meanwhile, the triplet interactive attention loss further alleviates the cross-modality discrepancy, based on the maximum mean discrepancy constraint. To demonstrate the effectiveness of our proposed TIAN, experiments on SYSU-MM01 and RegDB datasets show obvious superiority over popular cross-modality ReID methods, and the evaluation of main modules also reveals the novelties of our TIAN method.

[1]  Jian-Huang Lai,et al.  RGB-Infrared Cross-Modality Person Re-identification , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[2]  Rongrong Ji,et al.  AD-Cluster: Augmented Discriminative Clustering for Domain Adaptive Person Re-Identification , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Yang Yang,et al.  RGB-Infrared Cross-Modality Person Re-Identification via Joint Pixel and Feature Alignment , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[4]  Bernard De Baets,et al.  Kernel Distance Metric Learning Using Pairwise Constraints for Person Re-Identification , 2019, IEEE Transactions on Image Processing.

[5]  Ling Shao,et al.  Visible-Infrared Person Re-Identification via Homogeneous Augmented Tri-Modal Learning , 2021, IEEE Transactions on Information Forensics and Security.

[6]  Bin Liu,et al.  Cross-Modality Person Re-Identification With Shared-Specific Feature Transfer , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Pong C. Yuen,et al.  Hierarchical Discriminative Learning for Visible Thermal Person Re-Identification , 2018, AAAI.

[8]  Haifeng Hu,et al.  Adversarial Disentanglement Spectrum Variations and Cross-Modality Attention Networks for NIR-VIS Face Recognition , 2021, IEEE Transactions on Multimedia.

[9]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[10]  Xiaopeng Hong,et al.  Infrared-Visible Cross-Modal Person Re-Identification with an X Modality , 2020, AAAI.

[11]  Kaiqi Huang,et al.  Beyond Triplet Loss: A Deep Quadruplet Network for Person Re-identification , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Jian Cheng,et al.  Cross-Modality Paired-Images Generation for RGB-Infrared Person Re-Identification , 2020, AAAI.

[13]  Xiangtao Zheng,et al.  Bidirectional Interaction Network for Person Re-Identification , 2021, IEEE Transactions on Image Processing.

[14]  Mang Ye,et al.  Cross-Modality Person Re-Identification via Modality-Aware Collaborative Ensemble Learning , 2020, IEEE Transactions on Image Processing.

[15]  Yi Yang,et al.  Person Re-identification: Past, Present and Future , 2016, ArXiv.

[16]  Shaozi Li,et al.  SFANet: A Spectrum-aware Feature Augmentation Network for Visible-Infrared Person Re-Identification , 2021, IEEE transactions on neural networks and learning systems.

[17]  Qinqin Zhou,et al.  Fine-Grained Spatial Alignment Model for Person Re-Identification With Focal Triplet Loss , 2020, IEEE Transactions on Image Processing.

[18]  Zheng Wang,et al.  Visible Thermal Person Re-Identification via Dual-Constrained Top-Ranking , 2018, IJCAI.

[19]  Hong Liu,et al.  Bi-Directional Exponential Angular Triplet Loss for RGB-Infrared Person Re-Identification , 2020, IEEE Transactions on Image Processing.

[20]  Yung-Yu Chuang,et al.  Learning to Reduce Dual-Level Discrepancy for Infrared-Visible Person Re-Identification , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  Arko Barman,et al.  A Graph-Based Approach for Making Consensus-Based Decisions in Image Search and Person Re-Identification , 2021, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[22]  Jian Cheng,et al.  Enhancing the Discriminative Feature Learning for Visible-Thermal Cross-Modality Person Re-Identification , 2019, Neurocomputing.

[23]  Fan Zhang,et al.  Distance learning by mining hard and easy negative samples for person re-identification , 2019, Pattern Recognit..

[24]  Jie Li,et al.  HSME: Hypersphere Manifold Embedding for Visible Thermal Person Re-Identification , 2019, AAAI.

[25]  Tien Dat Nguyen,et al.  Person Recognition System Based on a Combination of Body Images from Visible Light and Thermal Cameras , 2017, Sensors.

[26]  Lucas Beyer,et al.  In Defense of the Triplet Loss for Person Re-Identification , 2017, ArXiv.

[27]  Liang Wang,et al.  Adaptive super-resolution for person re-identification with low-resolution images , 2020, Pattern Recognit..

[28]  Shengcai Liao,et al.  Person re-identification by Local Maximal Occurrence representation and metric learning , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[29]  Ling Shao,et al.  Dynamic Dual-Attentive Aggregation Learning for Visible-Infrared Person Re-Identification , 2020, ECCV.