Hash Bit Selection With Reinforcement Learning for Image Retrieval
- 10 October 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 25 (15209210) , 6678-6687
Abstract
In recent years, binary hashing methods have been widely used in large-scale multimedia retrieval because of the low computational complexity and memory cost. Generally, better retrieval accuracy can be achieved with a longer hash code, which, however, may suffer redundancy. In this paper, we propose a novel hash bit selection method, called Hash Bit Selection with Reinforcement Learning (HBS-RL), which aims to adaptively select the most informative bits from the database binary codes. In our approach, the hash bit selection problem is firstly modeled as a Markov Decision Process (MDP), which is solved with reinforcement learning. HBS-RL learns a policy for bit selection, which effectively identifies the most informative bits by directly maximizing mean Average Precision (mAP) during training. Specially, given a generated bit pool, our HBS-RL can sequentially select bits with different code lengths with a very lightweight fully-connected policy network. The proposed method is evaluated on the MNIST, CIFAR-10, ImageNet and NUS-WIDE datasets, and the results show that it significantly improves the retrieval performance of the existing unsupervised and deep supervised hashing methods. It also outperforms the state-of-the-art bit selection methods. For convenience of repeating our results, we release our source code at: https://github.com/xyez/HBS-RL .Keywords
Funding Information
- National Natural Science Foundation of China (62102128, 61836011, 62021001)
- GPU cluster built
- MCC Laboratory of Information Science and Technology Institution
- University of Science and Technology of China
This publication has 30 references indexed in Scilit:
- Mastering the game of Go without human knowledgeNature, 2017
- Reinforcement Learning for Visual Object Detection2016
- Bit-Scalable Deep Hashing With Regularized Similarity Learning for Image Retrieval and Person Re-IdentificationIEEE Transactions on Image Processing, 2015
- Deep hashing for compact binary codes learning2015
- Weighted Component Hashing of Binary Aggregated Descriptors for Fast Visual SearchIEEE Transactions on Multimedia, 2015
- Supervised hashing with latent factor models2014
- Iterative Quantization: A Procrustean Approach to Learning Binary Codes for Large-Scale Image RetrievalIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- Multimedia semantics-aware query-adaptive hashing with bits reconfigurabilityInternational Journal of Multimedia Information Retrieval, 2012
- NUS-WIDE2009
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998