Harmonious Attention Network for Person Re-Identification
arXiv:1802.08122
Abstract
Existing person re-identification (re-id) methods either assume the availability of well-aligned person bounding box images as model input or rely on constrained attention selection mechanisms to calibrate misaligned images. They are therefore sub-optimal for re-id matching in arbitrarily aligned person images potentially with large human pose variations and unconstrained auto-detection errors. In this work, we show the advantages of jointly learning attention selection and feature representation in a Convolutional Neural Network (CNN) by maximising the complementary information of different levels of visual attention subject to re-id discriminative learning constraints. Specifically, we formulate a novel Harmonious Attention CNN (HA-CNN) model for joint learning of soft pixel attention and hard regional attention along with simultaneous optimisation of feature representations, dedicated to optimise person re-id in uncontrolled (misaligned) images. Extensive comparative evaluations validate the superiority of this new HA-CNN model for person re-id over a wide variety of state-of-the-art methods on three large-scale benchmarks including CUHK03, Market-1501, and DukeMTMC-ReID.
Accepted in CVPR 2018
References in corpus (3)
Cited by in corpus (27)
- SphereReID: Deep Hypersphere Manifold Embedding for Person Re-Identification
- Horizontal Pyramid Matching for Person Re-identification
- Improved Person Re-Identification Based on Saliency and Semantic Parsing with Deep Neural Network Models
- Let Features Decide for Themselves: Feature Mask Network for Person Re-identification
- Auto-ReID: Searching for a Part-aware ConvNet for Person Re-Identification
- Learning Shape Representations for Clothing Variations in Person Re-Identification
- Pose-guided Visible Part Matching for Occluded Person ReID
- Person Search via A Mask-Guided Two-Stream CNN Model
- Batch DropBlock Network for Person Re-identification and Beyond
- CA3Net: Contextual-Attentional Attribute-Appearance Network for Person Re-Identification
- Unsupervised Person Re-Identification: A Systematic Survey of Challenges and Solutions
- Beyond Human Parts: Dual Part-Aligned Representations for Person Re-Identification
- Person Re-identification with Deep Similarity-Guided Graph Neural Network
- Re-Identification with Consistent Attentive Siamese Networks
- Recover and Identify: A Generative Dual Model for Cross-Resolution Person Re-Identification
- A Person Re-identification Data Augmentation Method with Adversarial Defense Effect
- Uncertainty-Aware Multi-Shot Knowledge Distillation for Image-Based Object Re-Identification
- Towards Visually Explaining Similarity Models
- Towards Discriminative Representation Learning for Unsupervised Person Re-identification
- Vehicle Re-ID for Surround-view Camera System
- Wide-Baseline Multi-Camera Calibration using Person Re-Identification
- What I See Is What You See: Joint Attention Learning for First and Third Person Video Co-analysis
- SCPNet: Spatial-Channel Parallelism Network for Joint Holistic and Partial Person Re-Identification
- Sparse Label Smoothing Regularization for Person Re-Identification
- Learning adaptively from the unknown for few-example video person re-ID
- Local-Global Associative Frame Assemble in Video Re-ID
- Person Re-identification with Bias-controlled Adversarial Training