swMATH ID: 43995
Software Authors: Maciej Zieba, Piotr Semberecki, Tarek El-Gaaly, Tomasz Trzcinski
Description: BinGAN: Learning Compact Binary Descriptors with a Regularized GAN. 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.
Homepage: https://arxiv.org/abs/1806.06778
Source Code:  https://github.com/maciejzieba/binGAN
Dependencies: Python
Keywords: Computer Vision; Pattern Recognition; arXiv_cs.CV; Regularized GAN; Generative Adversarial Network; GAN
Related Software: SIFT; YFCC100M; SOSNet; L2-Net; Theia; R2D2; MAGSAC++; USAC; D2-Net; GMS; ContextDesc; ASLFeat; SuperGlue; FusionGAN; Quicksilver; ApolloScape; PASCAL VOC; 3DMatch; PPFNet; ORB-SLAM2
Cited in: 3 Documents

Citations by Year