Unsupervised Deep Learning of Compact Binary Descriptors
Journal
IEEE Transactions on Pattern Analysis and Machine Intelligence
Journal Volume
41
Journal Issue
6
Pages
1501-1514
Date Issued
2019
Author(s)
Abstract
Binary descriptors have been widely used for efficient image matching and retrieval. However, most existing binary descriptors are designed with hand-craft sampling patterns or learned with label annotation provided by datasets. In this paper, we propose a new unsupervised deep learning approach, called DeepBit, to learn compact binary descriptor for efficient visual object matching. We enforce three criteria on binary descriptors which are learned at the top layer of the deep neural network: 1) minimal quantization loss, 2) evenly distributed codes and 3) transformation invariant bit. Then, we estimate the parameters of the network through the optimization of the proposed objectives with a back-propagation technique. Extensive experimental results on various visual recognition tasks demonstrate the effectiveness of the proposed approach. We further demonstrate our proposed approach can be realized on the simplified deep neural network, and enables efficient image matching and retrieval speed with very competitive accuracies. ? 1979-2012 IEEE.
Subjects
Backpropagation; Binary codes; Deep learning; Flow visualization; Image matching; Job analysis; Learning systems; Neural networks; Optimization; Quantization (signal); Unsupervised learning; Binary descriptor; Convolutional neural network; Descriptors; Learning approach; Quantization loss; Task analysis; Transformation invariants; Visual recognition; Deep neural networks
Type
journal article