BinGAN: Learning Compact Binary Descriptors with a Regularized GAN

Abstract

In this paper, we propose a novel regularization method for Generative Adversarial Networks, which allows the model to learn discriminative yet compact binary representations of image patches (image descriptors). We employ the dimensionality reduction that takes place in the intermediate layers of the discriminator network and train binarized low-dimensional representation of the penultimate layer to mimic the distribution of the higher-dimensional preceding layers. To achieve this, we introduce two loss terms that aim at: (i) reducing the correlation between the dimensions of the binarized low-dimensional representation of the penultimate layer i. e. maximizing joint entropy) and (ii) propagating the relations between the dimensions in the high-dimensional space to the low-dimensional space. We evaluate the resulting binary image descriptors on two challenging applications, image matching and retrieval, and achieve state-of-the-art results.

arXiv commentPaper accepted to NIPS 2018

Cited by in corpus (7)

• A Decade Survey of Content Based Image Retrieval using Deep Learning
• R2D2: Repeatable and Reliable Detector and Descriptor
• Unsupervised Hashing with Contrastive Information Bottleneck
• Auto-Encoding Twin-Bottleneck Hashing
• Embarrassingly Simple Binary Representation Learning
• Shuffle and Learn: Minimizing Mutual Information for Unsupervised Hashing
• Leveraging Local and Global Descriptors in Parallel to Search Correspondences for Visual Localization