Relation-Aware Global Attention for Person Re-identification
arXiv:1904.02998
Abstract
For person re-identification (re-id), attention mechanisms have become attractive as they aim at strengthening discriminative features and suppressing irrelevant ones, which matches well the key of re-id, i.e., discriminative feature learning. Previous approaches typically learn attention using local convolutions, ignoring the mining of knowledge from global structure patterns. Intuitively, the affinities among spatial positions/nodes in the feature map provide clustering-like information and are helpful for inferring semantics and thus attention, especially for person images where the feasible human poses are constrained. In this work, we propose an effective Relation-Aware Global Attention (RGA) module which captures the global structural information for better attention learning. Specifically, for each feature position, in order to compactly grasp the structural information of global scope and local appearance information, we propose to stack the relations, i.e., its pairwise correlations/affinities with all the feature positions (e.g., in raster scan order), and the feature itself together to learn the attention with a shallow convolutional model. Extensive ablation studies demonstrate that our RGA can significantly enhance the feature representation power and help achieve the state-of-the-art performance on several popular benchmarks. The source code is available at https://github.com/microsoft/Relation-Aware-Global-Attention-Networks.
arXiv commentAccepted by CVPR2020
References in corpus (23)
- Rethinking Atrous Convolution for Semantic Image Segmentation
- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
- In Defense of the Triplet Loss for Person Re-Identification
- Densely Connected Convolutional Networks
- Person Re-identification: Past, Present and Future
- The Cityscapes Dataset for Semantic Urban Scene Understanding
- Understanding the Effective Receptive Field in Deep Convolutional Neural Networks
- Random Erasing Data Augmentation
- Multiple Object Recognition with Visual Attention
- Pedestrian Alignment Network for Large-scale Person Re-identification
- OCNet: Object Context Network for Scene Parsing
- AlignedReID: Surpassing Human-Level Performance in Person Re-Identification
- Pyramid Scene Parsing Network
- GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond
- Dual Attention Network for Scene Segmentation
- Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro
- Residual Non-local Attention Networks for Image Restoration
- Re-ID done right: towards good practices for person re-identification
- Recognizing Partial Biometric Patterns
- Deep-Person: Learning Discriminative Deep Features for Person Re-Identification
- MaskReID: A Mask Based Deep Ranking Neural Network for Person Re-identification
- SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioning
- Survey on Deep Learning Techniques for Person Re-Identification Task