Learning Transformation-Invariant Local Descriptors With Low-Coupling Binary Codes

Yunqi Miao, Zijia Lin, Xiao Ma, Guiguang Ding, Jungong Han

Research output: Contribution to journalArticlepeer-review

19 Citations (SciVal)
65 Downloads (Pure)


Despite the great success achieved by prevailing binary local descriptors, they are still suffering from two problems: 1) vulnerable to the geometric transformations; 2) lack of an effective treatment to the highly-correlated bits that are generated by directly applying the scheme of image hashing. To tackle both limitations, we propose an unsupervised Transformation-invariant Binary Local Descriptor learning method (TBLD). Specifically, the transformation invariance of binary local descriptors is ensured by projecting the original patches and their transformed counterparts into an identical high-dimensional feature space and an identical low-dimensional descriptor space simultaneously. Meanwhile, it enforces the dissimilar image patches to have distinctive binary local descriptors. Moreover, to reduce high correlations between bits, we propose a bottom-up learning strategy, termed Adversarial Constraint Module , where low-coupling binary codes are introduced externally to guide the learning of binary local descriptors. With the aid of the Wasserstein loss, the framework is optimized to encourage the distribution of the generated binary local descriptors to mimic that of the introduced low-coupling binary codes, eventually making the former more low-coupling. Experimental results on three benchmark datasets well demonstrate the superiority of the proposed method over the state-of-the-art methods.
Original languageEnglish
Pages (from-to)7554 - 7566
Number of pages13
JournalIEEE Transactions on Image Processing
Early online date27 Aug 2021
Publication statusPublished - 08 Sept 2021


  • Binary local descriptor
  • deep learning
  • patch matching


Dive into the research topics of 'Learning Transformation-Invariant Local Descriptors With Low-Coupling Binary Codes'. Together they form a unique fingerprint.

Cite this