Bit-Scalable Deep Hashing with Regularized Similarity Learning for Image Retrieval and Person Re-identification

Abstract

Extracting informative image features and learning effective approximate hashing functions are two crucial steps in image retrieval . Conventional methods often study these two steps separately, e.g., learning hash functions from a predefined hand-crafted feature space. Meanwhile, the bit lengths of output hashing codes are preset in most previous methods, neglecting the significance level of different bits and restricting their practical flexibility. To address these issues, we propose a supervised learning framework to generate compact and bit-scalable hashing codes directly from raw images. We pose hashing learning as a problem of regularized similarity learning. Specifically, we organize the training images into a batch of triplet samples, each sample containing two images with the same label and one with a different label. With these triplet samples, we maximize the margin between matched pairs and mismatched pairs in the Hamming space. In addition, a regularization term is introduced to enforce the adjacency consistency, i.e., images of similar appearances should have similar codes. The deep convolutional neural network is utilized to train the model in an end-to-end fashion, where discriminative image features and hash functions are simultaneously optimized. Furthermore, each bit of our hashing codes is unequally weighted so that we can manipulate the code lengths by truncating the insignificant bits. Our framework outperforms state-of-the-arts on public benchmarks of similar image search and also achieves promising results in the application of person re-identification in surveillance. It is also shown that the generated bit-scalable hashing codes well preserve the discriminative powers with shorter code lengths.

14 pages, 5 figures. IEEE Transactions on Image Processing 2015

References in corpus (1)

• Discriminatively Trained And-Or Graph Models for Object Shape Detection

Cited by in corpus (23)

• A Decade Survey of Content Based Image Retrieval using Deep Learning
• SSDH: Semi-supervised Deep Hashing for Large Scale Image Retrieval
• DISC: Deep Image Saliency Computing via Progressive Representation Learning
• Cross-Domain Visual Matching via Generalized Similarity Measure and Feature Learning
• Deep Discrete Supervised Hashing
• Deep Ordinal Hashing with Spatial Attention
• SCAN: Self-and-Collaborative Attention Network for Video Person Re-identification
• Part-based Deep Hashing for Large-scale Person Re-identification
• Structured Deep Hashing with Convolutional Neural Networks for Fast Person Re-identification
• Deep Triplet Hashing Network for Case-based Medical Image Retrieval
• Learning Correspondence Structures for Person Re-identification
• Structure-Preserving Image Super-resolution via Contextualized Multi-task Learning
• Content-Adaptive Sketch Portrait Generation by Decompositional Representation Learning
• Learning Deep Similarity Models with Focus Ranking for Fabric Image Retrieval
• Unsupervised Deep Cross-modality Spectral Hashing
• Sampling Agnostic Feature Representation for Long-Term Person Re-identification
• Simultaneous Feature Aggregating and Hashing for Compact Binary Code Learning
• Deep Heterogeneous Hashing for Face Video Retrieval
• Transductive Zero-Shot Hashing for Multilabel Image Retrieval
• Rank-Consistency Deep Hashing for Scalable Multi-Label Image Search
• IEGAN: Multi-purpose Perceptual Quality Image Enhancement Using Generative Adversarial Network
• Texture Synthesis Guided Deep Hashing for Texture Image Retrieval
• Semantic Cluster Unary Loss for Efficient Deep Hashing