Deep Reinforcement Learning with Label Embedding Reward for Supervised Image Hashing

2020/08/10 by Zhenzhen Wang, Wang, Zhenzhen, Weixiang Hong +3
Computer Science · #Advanced Image and Video Retrieval Techniques #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Video Surveillance and Tracking Methods

paper · pdf · doi:10.48550/arxiv.2008.03973

openalex publication_date 2020/08/10 · openalex created_date 2020/08/13 · openalex updated_date 2026/07/28

Abstract

Deep hashing has shown promising results in image retrieval and recognition. Despite its success, most existing deep hashing approaches are rather similar: either multi-layer perceptron or CNN is applied to extract image feature, followed by different binarization activation functions such as sigmoid, tanh or autoencoder to generate binary code. In this work, we introduce a novel decision-making approach for deep supervised hashing. We formulate the hashing problem as travelling across the vertices in the binary code space, and learn a deep Q-network with a novel label embedding reward defined by Bose-Chaudhuri-Hocquenghem (BCH) codes to explore the best path. Extensive experiments and analysis on the CIFAR-10 and NUS-WIDE dataset show that our approach outperforms state-of-the-art supervised hashing methods under various code lengths.

Citations

• Tensorizing Neural Networks
• ImageNet classification with deep convolutional neural networks
• Deep Reinforcement Learning-based Image Captioning with Embedding Reward
• Learning Multiple Layers of Features from Tiny Images

Related

• Deep Reinforcement Learning for Image Hashing
• Discrete Hashing with Deep Neural Network
• Supervised Hashing with End-to-End Binary Deep Neural Network
• A Deep Hashing Learning Network
• Deep Supervised Hashing with Triplet Labels