.png){kind=icon}
返回
Deep Unsupervised Binary Descriptor Learning Through Locality Consistency and Self Distinctiveness
.png){kind=icon}
PRE
AI
DOI：10.1109/TMM.2020.3016122.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Deep learning has been successfully applied to learn local feature descriptors in recent years. However, most of existing methods are supervised methods relying on a large number of labeled training patches, which are also proposed for learning real valued descriptors. In this paper, we propose a novel unsupervised deep learning method for binary descriptor learning. The binary descriptors are much more compact and efficient than the real valued descriptors and unsupervised leaning is highly required in many applications due to its label-free characteristic as the annotations are sometimes expensive to obtain. The core idea of our method is to explore the locality consistency in the descriptor space as well as to distinguish different patches while maintaining the ability to match a patch with its geometric transformed ones. We also give a theorical analysis about the role of batch normalization in learning effective binary descriptors. Benefited from this analysis, there is no need to append two additional losses on minimizing the quantization error and maximizing the entropy to the final learning objective like previous works did, thus simplifying our network training. Experiments on four benchmarks demonstrate that the proposed method is able to learn binary descriptors significantly outperforming previous unsupervised binary descriptors, even superior to most supervised ones. Especially, it obtains 21.2% of improvement on the UBC Phototour dataset, and 19.8%, 26.7%, 26.0% of improvements for patch verification, matching, retrieval tasks respectively on the HPatches dataset compared to the previous best unsupervised method.
Keyword:
Machine learning
Robustness
Quantization (signal)
Binary codes
Task analysis
Feature extraction
Training
Unsupervised learning
deep learning
pattern matching
feature extraction
compact descriptor
mobile applications
image retrieval
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
9.7
论文数:
4.7K
被引数:
2.4W
机构
引用论文
Pumilio1 phosphorylation precedes translational activation of its target mRNA in zebrafish oocytes.png)
Zygote
OAAI
ZygoteIF0
OAAI分享收藏1H-MR spectroscopy differentiates mild cognitive impairment from normal brain agingNeuroreport
NeuroreportIF0
PREAI
分享收藏分享收藏分享收藏
查看更多内容