Feature Learning based Deep Supervised Hashing with Pairwise Labels

Abstract

Recent years have witnessed wide application of hashing for large-scale image retrieval. However, most existing hashing methods are based on hand-crafted features which might not be optimally compatible with the hashing procedure. Recently, deep hashing methods have been proposed to perform simultaneous feature learning and hash-code learning with deep neural networks, which have shown better performance than traditional hashing methods with hand-crafted features. Most of these deep hashing methods are supervised whose supervised information is given with triplet labels. For another common application scenario with pairwise labels, there have not existed methods for simultaneous feature learning and hash-code learning. In this paper, we propose a novel deep hashing method, called deep pairwise-supervised hashing(DPSH), to perform simultaneous feature learning and hash-code learning for applications with pairwise labels. Experiments on real datasets show that our DPSH method can outperform other methods to achieve the state-of-the-art performance in image retrieval applications.

IJCAI 2016

References in corpus (2)

• Simultaneous Feature Learning and Hash Coding with Deep Neural Networks
• Learning Hash Functions Using Column Generation

Cited by in corpus (28)

• Self-Supervised Video Hashing with Hierarchical Binary Auto-encoder
• Visual Search at eBay
• Metric-Learning based Deep Hashing Network for Content Based Retrieval of Remote Sensing Images
• HashNet: Deep Learning to Hash by Continuation
• Deep Triplet Hashing Network for Case-based Medical Image Retrieval
• A Revisit on Deep Hashings for Large-scale Content Based Image Retrieval
• End-to-End Supervised Product Quantization for Image Search and Retrieval
• Mean Local Group Average Precision (mLGAP): A New Performance Metric for Hashing-based Retrieval
• Learning A Deep ${\ell }_{\infty }$ Encoder for Hashing
• Adversarially Trained Deep Neural Semantic Hashing Scheme for Subjective Search in Fashion Inventory
• Dual Asymmetric Deep Hashing Learning
• Weakly Supervised Deep Image Hashing through Tag Embeddings
• Transductive Zero-Shot Hashing via Coarse-to-Fine Similarity Mining
• Instance-weighted Central Similarity for Multi-label Image Retrieval
• Combating Ambiguity for Hash-code Learning in Medical Instance Retrieval
• Fast Supervised Discrete Hashing
• DeepHashing using TripletLoss
• Rescuing Deep Hashing from Dead Bits Problem
• Deep Supervised Hashing with Triplet Labels
• Deep Hashing for Signed Social Network Embedding
• A Scalable Optimization Mechanism for Pairwise based Discrete Hashing
• Object Detection based Deep Unsupervised Hashing
• Place recognition survey: An update on deep learning approaches
• Regularizing Deep Hashing Networks Using GAN Generated Fake Images
• Deep Collaborative Discrete Hashing with Semantic-Invariant Structure
• Bilinear Supervised Hashing Based on 2D Image Features
• Deep Policy Hashing Network with Listwise Supervision
• Supervised Discrete Hashing with Relaxation