Unsupervised Hashing with Contrastive Information Bottleneck
arXiv:2105.06138
Abstract
Many unsupervised hashing methods are implicitly established on the idea of reconstructing the input data, which basically encourages the hashing codes to retain as much information of original data as possible. However, this requirement may force the models spending lots of their effort on reconstructing the unuseful background information, while ignoring to preserve the discriminative semantic information that is more important for the hashing task. To tackle this problem, inspired by the recent success of contrastive learning in learning continuous representations, we propose to adapt this framework to learn binary hashing codes. Specifically, we first propose to modify the objective function to meet the specific requirement of hashing and then introduce a probabilistic binary representation layer into the model to facilitate end-to-end training of the entire model. We further prove the strong connection between the proposed contrastive-learning-based hashing method and the mutual information, and show that the proposed model can be considered under the broader framework of the information bottleneck (IB). Under this perspective, a more general hashing model is naturally obtained. Extensive experimental results on three benchmark image datasets demonstrate that the proposed hashing method significantly outperforms existing baselines.
IJCAI 2021
References in corpus (12)
- Distilling the Knowledge in a Neural Network
- A Simple Framework for Contrastive Learning of Visual Representations
- The information bottleneck method
- Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
- The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
- Learning Robust Representations via Multi-View Information Bottleneck
- BinGAN: Learning Compact Binary Descriptors with a Regularized GAN
- Learning to Hash with Binary Deep Neural Network
- Stochastic Generative Hashing
- Auto-Encoding Twin-Bottleneck Hashing
- Generative Semantic Hashing Enhanced via Boltzmann Machines
- Document Hashing with Mixture-Prior Generative Models