Attention-Aware Compositional Network for Person Re-identification

Abstract

Person re-identification (ReID) is to identify pedestrians observed from different camera views based on visual appearance. It is a challenging task due to large pose variations, complex background clutters and severe occlusions. Recently, human pose estimation by predicting joint locations was largely improved in accuracy. It is reasonable to use pose estimation results for handling pose variations and background clutters, and such attempts have obtained great improvement in ReID performance. However, we argue that the pose information was not well utilized and hasn't yet been fully exploited for person ReID. In this work, we introduce a novel framework called Attention-Aware Compositional Network (AACN) for person ReID. AACN consists of two main components: Pose-guided Part Attention (PPA) and Attention-aware Feature Composition (AFC). PPA is learned and applied to mask out undesirable background features in pedestrian feature maps. Furthermore, pose-guided visibility scores are estimated for body parts to deal with part occlusion in the proposed AFC module. Extensive experiments with ablation analysis show the effectiveness of our method, and state-of-the-art results are achieved on several public datasets, including Market-1501, CUHK03, CUHK01, SenseReID, CUHK03-NP and DukeMTMC-reID.

arXiv commentAccepted at CVPR2018

References in corpus (12)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Neural Machine Translation by Jointly Learning to Align and Translate
• Multiple Object Recognition with Visual Attention
• Pedestrian Alignment Network for Large-scale Person Re-identification
• Deep Transfer Learning for Person Re-identification
• PersonNet: Person Re-identification with Deep Convolutional Neural Networks
• Pose Invariant Embedding for Deep Person Re-identification
• SVDNet for Pedestrian Retrieval
• Multi-Context Attention for Human Pose Estimation
• Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Parts
• Look into Person: Self-supervised Structure-sensitive Learning and A New Benchmark for Human Parsing
• Constrained Deep Metric Learning for Person Re-identification

Cited by in corpus (14)

• Parameter-Free Spatial Attention Network for Person Re-Identification
• Discriminative Feature Learning with Foreground Attention for Person Re-Identification
• ABD-Net: Attentive but Diverse Person Re-Identification
• Auto-ReID: Searching for a Part-aware ConvNet for Person Re-Identification
• Hierarchical Clustering with Hard-batch Triplet Loss for Person Re-identification
• Towards Good Practices on Building Effective CNN Baseline Model for Person Re-identification
• Densely Semantically Aligned Person Re-Identification
• Beyond Human Parts: Dual Part-Aligned Representations for Person Re-Identification
• Re-Identification with Consistent Attentive Siamese Networks
• Semantics-Aligned Representation Learning for Person Re-identification
• Backbone Can Not be Trained at Once: Rolling Back to Pre-trained Network for Person Re-Identification
• Towards Discriminative Representation Learning for Unsupervised Person Re-identification
• TTPP: Temporal Transformer with Progressive Prediction for Efficient Action Anticipation
• Weakly Supervised Person Re-Identification