End-to-End Comparative Attention Networks for Person Re-identification

Abstract

Person re-identification across disjoint camera views has been widely applied in video surveillance yet it is still a challenging problem. One of the major challenges lies in the lack of spatial and temporal cues, which makes it difficult to deal with large variations of lighting conditions, viewing angles, body poses and occlusions. Recently, several deep learning based person re-identification approaches have been proposed and achieved remarkable performance. However, most of those approaches extract discriminative features from the whole frame at one glimpse without differentiating various parts of the persons to identify. It is essentially important to examine multiple highly discriminative local regions of the person images in details through multiple glimpses for dealing with the large appearance variance. In this paper, we propose a new soft attention based model, i.e., the end to-end Comparative Attention Network (CAN), specifically tailored for the task of person re-identification. The end-to-end CAN learns to selectively focus on parts of pairs of person images after taking a few glimpses of them and adaptively comparing their appearance. The CAN model is able to learn which parts of images are relevant for discerning persons and automatically integrates information from different parts to determine whether a pair of images belongs to the same person. In other words, our proposed CAN model simulates the human perception process to verify whether two images are from the same person. Extensive experiments on three benchmark person re-identification datasets, including CUHK01, CHUHK03 and Market-1501, clearly demonstrate that our proposed end-to-end CAN for person re-identification outperforms well established baselines significantly and offer new state-of-the-art performance.

Cited by in corpus (27)

• Attention Mechanisms in Computer Vision: A Survey
• Learning Discriminative Features with Multiple Granularities for Person Re-Identification
• Improving Person Re-identification by Attribute and Identity Learning
• A Strong Baseline and Batch Normalization Neck for Deep Person Re-identification
• Pedestrian Alignment Network for Large-scale Person Re-identification
• Deep Representation Learning with Part Loss for Person Re-Identification
• A Transformer-Based Feature Segmentation and Region Alignment Method For UAV-View Geo-Localization
• SphereReID: Deep Hypersphere Manifold Embedding for Person Re-Identification
• Unsupervised Person Re-identification by Deep Asymmetric Metric Embedding
• What-and-Where to Match: Deep Spatially Multiplicative Integration Networks for Person Re-identification
• Adaptive Exploration for Unsupervised Person Re-Identification
• Interpretable and Generalizable Person Re-Identification with Query-Adaptive Convolution and Temporal Lifting
• Person Re-identification via Attention Pyramid
• Deep Ordinal Hashing with Spatial Attention
• SCAN: Self-and-Collaborative Attention Network for Video Person Re-identification
• Learning View-Specific Deep Networks for Person Re-Identification
• Bi-directional Exponential Angular Triplet Loss for RGB-Infrared Person Re-Identification
• Let Features Decide for Themselves: Feature Mask Network for Person Re-identification
• Unsupervised Person Re-identification with Stochastic Training Strategy
• Joint Person Objectness and Repulsion for Person Search
• CDPM: Convolutional Deformable Part Models for Semantically Aligned Person Re-identification
• Leaning Compact and Representative Features for Cross-Modality Person Re-Identification
• Receptive Multi-granularity Representation for Person Re-Identification
• A Deep Four-Stream Siamese Convolutional Neural Network with Joint Verification and Identification Loss for Person Re-detection
• Multilinear subspace learning for person re-identification based fusion of high order tensor features
• Improving Person Re-identification with Iterative Impression Aggregation
• Adaptive Affinity for Associations in Multi-Target Multi-Camera Tracking