Supervised Learning of Semantics-Preserving Hash via Deep Convolutional Neural Networks

Abstract

This paper presents a simple yet effective supervised deep hash approach that constructs binary hash codes from labeled data for large-scale image search. We assume that the semantic labels are governed by several latent attributes with each attribute on or off, and classification relies on these attributes. Based on this assumption, our approach, dubbed supervised semantics-preserving deep hashing (SSDH), constructs hash functions as a latent layer in a deep network and the binary codes are learned by minimizing an objective function defined over classification error and other desirable hash codes properties. With this design, SSDH has a nice characteristic that classification and retrieval are unified in a single learning model. Moreover, SSDH performs joint learning of image representations, hash codes, and classification in a point-wised manner, and thus is scalable to large-scale datasets. SSDH is simple and can be realized by a slight enhancement of an existing deep architecture for classification; yet it is effective and outperforms other hashing approaches on several benchmarks and large datasets. Compared with state-of-the-art approaches, SSDH achieves higher retrieval accuracy, while the classification performance is not sacrificed.

To appear in IEEE Trans. Pattern Analysis and Machine Intelligence

References in corpus (8)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Practical Bayesian Optimization of Machine Learning Algorithms
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Fully Convolutional Networks for Semantic Segmentation
• Simultaneous Feature Learning and Hash Coding with Deep Neural Networks
• Stochastic Pooling for Regularization of Deep Convolutional Neural Networks
• Aggregating Deep Convolutional Features for Image Retrieval
• Group Invariant Deep Representations for Image Instance Retrieval

Cited by in corpus (30)

• A Decade Survey of Content Based Image Retrieval using Deep Learning
• Deep Supervised Discrete Hashing
• Deep Semantic Multimodal Hashing Network for Scalable Image-Text and Video-Text Retrievals
• Deep Ordinal Hashing with Spatial Attention
• Deep Hashing for Secure Multimodal Biometrics
• Metric-Learning based Deep Hashing Network for Content Based Retrieval of Remote Sensing Images
• Unsupervised Deep Cross-modality Spectral Hashing
• Yottixel -- An Image Search Engine for Large Archives of Histopathology Whole Slide Images
• A Revisit on Deep Hashings for Large-scale Content Based Image Retrieval
• One Loss for All: Deep Hashing with a Single Cosine Similarity based Learning Objective
• Semantic Cluster Unary Loss for Efficient Deep Hashing
• Query Attack via Opposite-Direction Feature:Towards Robust Image Retrieval
• Barista - a Graphical Tool for Designing and Training Deep Neural Networks
• Simultaneous Region Localization and Hash Coding for Fine-grained Image Retrieval
• Unifying and Merging Well-trained Deep Neural Networks for Inference Stage
• Semantic Hierarchy Preserving Deep Hashing for Large-scale Image Retrieval
• AudioNet: Supervised Deep Hashing for Retrieval of Similar Audio Events
• Deep Discrete Hashing with Self-supervised Pairwise Labels
• A Novel Framework to Jointly Compress and Index Remote Sensing Images for Efficient Content-Based Retrieval
• Random VLAD based Deep Hashing for Efficient Image Retrieval
• Deep Class-Wise Hashing: Semantics-Preserving Hashing via Class-wise Loss
• Learning to Index for Nearest Neighbor Search
• Deep Policy Hashing Network with Listwise Supervision
• PDH : Probabilistic deep hashing based on MAP estimation of Hamming distance
• Self-supervised asymmetric deep hashing with margin-scalable constraint
• Improving Deep Binary Embedding Networks by Order-aware Reweighting of Triplets
• Deep Reinforcement Learning with Label Embedding Reward for Supervised Image Hashing
• Dual-level Semantic Transfer Deep Hashing for Efficient Social Image Retrieval
• Convolutional Hashing for Automated Scene Matching
• Tattoo Image Search at Scale: Joint Detection and Compact Representation Learning