Quality Aware Network for Set to Set Recognition

Abstract

This paper targets on the problem of set to set recognition, which learns the metric between two image sets. Images in each set belong to the same identity. Since images in a set can be complementary, they hopefully lead to higher accuracy in practical applications. However, the quality of each sample cannot be guaranteed, and samples with poor quality will hurt the metric. In this paper, the quality aware network (QAN) is proposed to confront this problem, where the quality of each sample can be automatically learned although such information is not explicitly provided in the training stage. The network has two branches, where the first branch extracts appearance feature embedding for each sample and the other branch predicts quality score for each sample. Features and quality scores of all samples in a set are then aggregated to generate the final feature embedding. We show that the two branches can be trained in an end-to-end manner given only the set-level identity annotation. Analysis on gradient spread of this mechanism indicates that the quality learned by the network is beneficial to set-to-set recognition and simplifies the distribution that the network needs to fit. Experiments on both face verification and person re-identification show advantages of the proposed QAN. The source code and network structure can be downloaded at https://github.com/sciencefans/Quality-Aware-Network.

Accepted at CVPR 2017

References in corpus (1)

• Deeply learned face representations are sparse, selective, and robust

Cited by in corpus (32)

• AlignedReID: Surpassing Human-Level Performance in Person Re-Identification
• Margin Sample Mining Loss: A Deep Learning Based Method for Person Re-identification
• SCAN: Self-and-Collaborative Attention Network for Video Person Re-identification
• Automated interpretation of congenital heart disease from multi-view echocardiograms
• Dual Attention Matching Network for Context-Aware Feature Sequence based Person Re-Identification
• IMAE for Noise-Robust Learning: Mean Absolute Error Does Not Treat Examples Equally and Gradient Magnitude's Variance Matters
• Hallucinated-IQA: No-Reference Image Quality Assessment via Adversarial Learning
• Impression Network for Video Object Detection
• Multi-scale 3D Convolution Network for Video Based Person Re-Identification
• Pose-Robust Face Recognition via Deep Residual Equivariant Mapping
• Person Re-identification with Deep Similarity-Guided Graph Neural Network
• Spatial and Temporal Mutual Promotion for Video-based Person Re-identification
• Distributional Adversarial Networks
• Video Face Recognition: Component-wise Feature Aggregation Network (C-FAN)
• Learning Non-Uniform Hypergraph for Multi-Object Tracking
• Attention Control with Metric Learning Alignment for Image Set-based Recognition
• Derivative Manipulation for General Example Weighting
• Attribute-aware Identity-hard Triplet Loss for Video-based Person Re-identification
• Recurrent Scale Approximation for Object Detection in CNN
• You Only Recognize Once: Towards Fast Video Text Spotting
• GridFace: Face Rectification via Learning Local Homography Transformations
• GhostVLAD for set-based face recognition
• Beyond Trade-off: Accelerate FCN-based Face Detector with Higher Accuracy
• Multi-shot Pedestrian Re-identification via Sequential Decision Making
• A Flow-Guided Mutual Attention Network for Video-Based Person Re-Identification
• Unsupervised Person Re-identification by Deep Learning Tracklet Association
• Set Augmented Triplet Loss for Video Person Re-Identification
• Video-Based Convolutional Attention for Person Re-Identification
• Learning adaptively from the unknown for few-example video person re-ID
• In Defense of LSTMs for Addressing Multiple Instance Learning Problems
• Local-Global Associative Frame Assemble in Video Re-ID
• CAN: Composite Appearance Network for Person Tracking and How to Model Errors in a Tracking System