Learning Compact Binary Descriptors with Unsupervised Deep Neural Networks
- 1 June 2016
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1183-1192
- https://doi.org/10.1109/cvpr.2016.133
Abstract
In this paper, we propose a new unsupervised deep learning approach called DeepBit to learn compact binary descriptor for efficient visual object matching. Unlike most existing binary descriptors which were designed with random projections or linear hash functions, we develop a deep neural network to learn binary descriptors in an unsupervised manner. We enforce three criterions on binary codes which are learned at the top layer of our network: 1) minimal loss quantization, 2) evenly distributed codes and 3) uncorrelated bits. Then, we learn the parameters of the networks with a back-propagation technique. Experimental results on three different visual analysis tasks including image matching, image retrieval, and object recognition clearly demonstrate the effectiveness of the proposed approach.Keywords
This publication has 41 references indexed in Scilit:
- USB: Ultrashort Binary Descriptor for Fast Visual Matching and RetrievalIEEE Transactions on Image Processing, 2014
- Coupled Binary Embedding for Large-Scale Image RetrievalIEEE Transactions on Image Processing, 2014
- OSRI: A Rotationally Invariant Binary DescriptorIEEE Transactions on Image Processing, 2014
- Receptive Fields Selection for Binary Feature DescriptionIEEE Transactions on Image Processing, 2014
- Local Difference Binary for Ultrafast and Distinctive Feature DescriptionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Semantic hashingInternational Journal of Approximate Reasoning, 2009
- Automatic Panoramic Image Stitching using Invariant FeaturesInternational Journal of Computer Vision, 2006
- Local Features and Kernels for Classification of Texture and Object Categories: A Comprehensive StudyInternational Journal of Computer Vision, 2006
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- Content-based image retrieval at the end of the early yearsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2000