MHSA-Net: Multi-Head Self-Attention Network for Occluded Person Re-Identification
arXiv:2008.04015 · doi:10.1109/TNNLS.2022.3144163
Abstract
This paper presents a novel person re-identification model, named Multi-Head Self-Attention Network (MHSA-Net), to prune unimportant information and capture key local information from person images. MHSA-Net contains two main novel components: Multi-Head Self-Attention Branch (MHSAB) and Attention Competition Mechanism (ACM). The MHSAB adaptively captures key local person information, and then produces effective diversity embeddings of an image for the person matching. The ACM further helps filter out attention noise and non-key information. Through extensive ablation studies, we verified that the Multi-Head Self-Attention Branch (MHSAB) and Attention Competition Mechanism (ACM) both contribute to the performance improvement of the MHSA-Net. Our MHSA-Net achieves competitive performance in the standard and occluded person Re-ID tasks.
arXiv commentAccepted by TNNLS
References in corpus (19)
- Adam: A Method for Stochastic Optimization
- Neural Machine Translation by Jointly Learning to Align and Translate
- In Defense of the Triplet Loss for Person Re-Identification
- Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
- A Structured Self-attentive Sentence Embedding
- Learning Discriminative Features with Multiple Granularities for Person Re-Identification
- Random Erasing Data Augmentation
- Pedestrian Alignment Network for Large-scale Person Re-identification
- FD-GAN: Pose-guided Feature Distilling GAN for Robust Person Re-identification
- Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)
- Reconstructive Sequence-Graph Network for Video Summarization
- Deep Learning for Person Re-identification: A Survey and Outlook
- A Self-Supervised Gait Encoding Approach with Locality-Awareness for 3D Skeleton Based Person Re-Identification
- On the Relationship between Self-Attention and Convolutional Layers
- Recognizing Partial Biometric Patterns
- Foreground-aware Pyramid Reconstruction for Alignment-free Occluded Person Re-identification
- Deep Spatial Feature Reconstruction for Partial Person Re-identification: Alignment-Free Approach
- High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification
- All You Need is Beyond a Good Init: Exploring Better Solution for Training Extremely Deep Convolutional Neural Networks with Orthonormality and Modulation