Person Re-Identification by Camera Correlation Aware Feature Augmentation

Abstract

The challenge of person re-identification (re-id) is to match individual images of the same person captured by different non-overlapping camera views against significant and unknown cross-view feature distortion. While a large number of distance metric/subspace learning models have been developed for re-id, the cross-view transformations they learned are view-generic and thus potentially less effective in quantifying the feature distortion inherent to each camera view. Learning view-specific feature transformations for re-id (i.e., view-specific re-id), an under-studied approach, becomes an alternative resort for this problem. In this work, we formulate a novel view-specific person re-identification framework from the feature augmentation point of view, called Camera coRrelation Aware Feature augmenTation (CRAFT). Specifically, CRAFT performs cross-view adaptation by automatically measuring camera correlation from cross-view visual data distribution and adaptively conducting feature augmentation to transform the original features into a new adaptive space. Through our augmentation framework, view-generic learning algorithms can be readily generalized to learn and optimize view-specific sub-models whilst simultaneously modelling view-generic discrimination information. Therefore, our framework not only inherits the strength of view-generic model learning but also provides an effective way to take into account view specific characteristics. Our CRAFT framework can be extended to jointly learn view-specific feature transformations for person re-id across a large network with more than two cameras, a largely under-investigated but realistic re-id setting. Additionally, we present a domain-generic deep person appearance representation which is designed particularly to be towards view invariant for facilitating cross-view adaptation by CRAFT.

To Appear in IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017

References in corpus (6)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
• Frustratingly Easy Domain Adaptation
• An Enhanced Deep Feature Representation for Person Re-identification
• Deep Ranking for Person Re-identification via Joint Representation Learning
• Deep Metric Learning for Practical Person Re-Identification

Cited by in corpus (35)

• Person Re-identification by Contour Sketch under Moderate Clothing Change
• Unsupervised Person Re-identification by Deep Asymmetric Metric Embedding
• What-and-Where to Match: Deep Spatially Multiplicative Integration Networks for Person Re-identification
• Robust Depth-based Person Re-identification
• Video Person Re-identification by Temporal Residual Learning
• Multi-task Learning with Coarse Priors for Robust Part-aware Person Re-identification
• A Self-Supervised Gait Encoding Approach with Locality-Awareness for 3D Skeleton Based Person Re-Identification
• SCAN: Self-and-Collaborative Attention Network for Video Person Re-identification
• Learning View-Specific Deep Networks for Person Re-Identification
• Learning Multi-Attention Context Graph for Group-Based Re-Identification
• Bi-directional Exponential Angular Triplet Loss for RGB-Infrared Person Re-Identification
• Deep-Person: Learning Discriminative Deep Features for Person Re-Identification
• Let Features Decide for Themselves: Feature Mask Network for Person Re-identification
• VStore: A Data Store for Analytics on Large Videos
• Person Re-Identification by Deep Joint Learning of Multi-Loss Classification
• Cross-Camera Feature Prediction for Intra-Camera Supervised Person Re-identification across Distant Scenes
• Hierarchical Skeleton Meta-Prototype Contrastive Learning with Hard Skeleton Mining for Unsupervised Person Re-Identification
• Multilinear subspace learning for person re-identification based fusion of high order tensor features
• CA3Net: Contextual-Attentional Attribute-Appearance Network for Person Re-Identification
• Probabilistic Semantic Retrieval for Surveillance Videos with Activity Graphs
• View Confusion Feature Learning for Person Re-identification
• Enhancing the Discriminative Feature Learning for Visible-Thermal Cross-Modality Person Re-Identification
• Multi-Scale Cascading Network with Compact Feature Learning for RGB-Infrared Person Re-Identification
• An Evaluation of Deep CNN Baselines for Scene-Independent Person Re-Identification
• TAL: Two-stream Adaptive Learning for Generalizable Person Re-identification
• Symbiotic Adversarial Learning for Attribute-based Person Search
• Anchor-Free Person Search
• Universal Person Re-Identification
• HPILN: A feature learning framework for cross-modality person re-identification
• Attribute-Aware Attention Model for Fine-grained Representation Learning
• Weakly supervised discriminative feature learning with state information for person identification
• Efficient Person Search: An Anchor-Free Approach
• Unsupervised Noisy Tracklet Person Re-identification
• Person Re-Identification using Deep Learning Networks: A Systematic Review
• Weakly Supervised Person Re-Identification