Learning View-Specific Deep Networks for Person Re-Identification

Abstract

In recent years, a growing body of research has focused on the problem of person re-identification (re-id). The re-id techniques attempt to match the images of pedestrians from disjoint non-overlapping camera views. A major challenge of re-id is the serious intra-class variations caused by changing viewpoints. To overcome this challenge, we propose a deep neural network-based framework which utilizes the view information in the feature extraction stage. The proposed framework learns a view-specific network for each camera view with a cross-view Euclidean constraint (CV-EC) and a cross-view center loss (CV-CL). We utilize CV-EC to decrease the margin of the features between diverse views and extend the center loss metric to a view-specific version to better adapt the re-id problem. Moreover, we propose an iterative algorithm to optimize the parameters of the view-specific networks from coarse to fine. The experiments demonstrate that our approach significantly improves the performance of the existing deep networks and outperforms the state-of-the-art methods on the VIPeR, CUHK01, CUHK03, SYSU-mReId, and Market-1501 benchmarks.

12 pages, 8 figures, accepted by IEEE Transactions on image processing

References in corpus (5)

• Caffe: Convolutional Architecture for Fast Feature Embedding
• End-to-End Comparative Attention Networks for Person Re-identification
• Person Re-Identification by Camera Correlation Aware Feature Augmentation
• Learning Deep Embeddings with Histogram Loss
• An Enhanced Deep Feature Representation for Person Re-identification

Cited by in corpus (13)

• SCAN: Self-and-Collaborative Attention Network for Video Person Re-identification
• Incomplete Descriptor Mining with Elastic Loss for Person Re-Identification
• Bi-directional Exponential Angular Triplet Loss for RGB-Infrared Person Re-Identification
• CDPM: Convolutional Deformable Part Models for Semantically Aligned Person Re-identification
• Leaning Compact and Representative Features for Cross-Modality Person Re-Identification
• Receptive Multi-granularity Representation for Person Re-Identification
• Towards better Validity: Dispersion based Clustering for Unsupervised Person Re-identification
• Pedestrian Attribute Recognition in Video Surveillance Scenarios Based on View-attribute Attention Localization
• View Confusion Feature Learning for Person Re-identification
• Exploring Modality-shared Appearance Features and Modality-invariant Relation Features for Cross-modality Person Re-Identification
• Discovering Underlying Person Structure Pattern with Relative Local Distance for Person Re-identification
• Person Re-Identification using Deep Learning Networks: A Systematic Review
• Semi-Supervised Self-Growing Generative Adversarial Networks for Image Recognition