Structured Deep Hashing with Convolutional Neural Networks for Fast Person Re-identification

Abstract

Given a pedestrian image as a query, the purpose of person re-identification is to identify the correct match from a large collection of gallery images depicting the same person captured by disjoint camera views. The critical challenge is how to construct a robust yet discriminative feature representation to capture the compounded variations in pedestrian appearance. To this end, deep learning methods have been proposed to extract hierarchical features against extreme variability of appearance. However, existing methods in this category generally neglect the efficiency in the matching stage whereas the searching speed of a re-identification system is crucial in real-world applications. In this paper, we present a novel deep hashing framework with Convolutional Neural Networks (CNNs) for fast person re-identification. Technically, we simultaneously learn both CNN features and hash functions/codes to get robust yet discriminative features and similarity-preserving hash codes. Thereby, person re-identification can be resolved by efficiently computing and ranking the Hamming distances between images. A structured loss function defined over positive pairs and hard negatives is proposed to formulate a novel optimization problem so that fast convergence and more stable optimized solution can be obtained. Extensive experiments on two benchmarks CUHK03 \cite{FPNN} and Market-1501 \cite{Market1501} show that the proposed deep architecture is efficacy over state-of-the-arts.

arXiv commentTo appear at Computer Vision and Image Understanding

References in corpus (10)

• Simultaneous Feature Learning and Hash Coding with Deep Neural Networks
• Bit-Scalable Deep Hashing with Regularized Similarity Learning for Image Retrieval and Person Re-identification
• PersonNet: Person Re-identification with Deep Convolutional Neural Networks
• Deep Adaptive Feature Embedding with Local Sample Distributions for Person Re-identification
• Deep Ranking for Person Re-identification via Joint Representation Learning
• What-and-Where to Match: Deep Spatially Multiplicative Integration Networks for Person Re-identification
• Deep Semantic Ranking Based Hashing for Multi-Label Image Retrieval
• Learning a Discriminative Null Space for Person Re-identification
• Gated Siamese Convolutional Neural Network Architecture for Human Re-Identification
• Learning to rank in person re-identification with metric ensembles

Cited by in corpus (19)

• Deep Adaptive Feature Embedding with Local Sample Distributions for Person Re-identification
• What-and-Where to Match: Deep Spatially Multiplicative Integration Networks for Person Re-identification
• Hierarchical Information Quadtree: Efficient Spatial Temporal Image Search for Multimedia Stream
• Distance-based Camera Network Topology Inference for Person Re-identification
• Where to Focus: Deep Attention-based Spatially Recurrent Bilinear Networks for Fine-Grained Visual Recognition
• Faster Person Re-Identification
• Hierarchical One Permutation Hashing: Efficient Multimedia Near Duplicate Detection
• Efficient Interactive Search for Geo-tagged Multimedia Data
• An Efficient Approach for Geo-Multimedia Cross-Modal Retrieval
• Efficient Region of Visual Interests Search for Geo-multimedia Data
• PAC-GAN: An Effective Pose Augmentation Scheme for Unsupervised Cross-View Person Re-identification
• A hybrid index model for efficient spatio-temporal search in HBase
• Efficient Top K Temporal Spatial Keyword Search
• Temporal Activity Path Based Character Correction in Social Networks
• CNN-VWII: An Efficient Approach for Large-Scale Video Retrieval by Image Queries
• Efficient Multimedia Similarity Measurement Using Similar Elements
• Efficient Continuous Top-$k$ Geo-Image Search on Road Network
• A Filter of Minhash for Image Similarity Measures
• HOC-Tree: A Novel Index for efficient Spatio-temporal Range Search