We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Deep learning to ternary hash codes by continuation.
- Authors
Chen, Mingrui; Li, Weiyu; Lu, Weizhi
- Abstract
Recently, ithas been observed that {0,±1}‐ternary codes, which are simply generated from deep features by hard thresholding, tend to outperform {−1,1}‐binary codes in image retrieval. To obtain better ternary codes, the authors for the first time propose to jointly learn the features with the codes by appending a smoothed function to the networks. During training, the function could evolve into a non‐smoothed ternary function by a continuation method, and then generate ternary codes. The method circumvents the difficulty of directly training discrete functions and reduces the quantization errors of ternary codes. Experiments show that the proposed joint learning indeed could produce better ternary codes. For the first time, the authors propose to generate ternary hash codes by jointly learning the codes with deep features via a continuation method. Experiments show that the proposed method outperforms existing methods.
- Subjects
TERNARY codes; THRESHOLD concepts (Learning); IMAGE retrieval; BINARY codes; DEEP learning
- Publication
Electronics Letters (Wiley-Blackwell), 2021, Vol 57, Issue 24, p925
- ISSN
0013-5194
- Publication type
Article
- DOI
10.1049/ell2.12317