Translator Disclaimer
Paper
12 June 2020 Robust deep supervised hashing for image retrieval
Author Affiliations +
Proceedings Volume 11519, Twelfth International Conference on Digital Image Processing (ICDIP 2020); 115191T (2020) https://doi.org/10.1117/12.2573083
Event: Twelfth International Conference on Digital Image Processing, 2020, Osaka, Japan
Abstract
Hashing is an important technique branch of image retrieval due to its satisfactory retrieval performance with high retrieval speed and low storage cost. Deep supervised hashing methods, which take advantage of the convolutional neural network and the supervised information, have shown better performance than other kinds of hashing methods. However, previous deep hashing methods do not consider the noisy data, which generally exist in large-scale labeled datasets and mislead the learning algorithm. In this paper, we propose a novel robust deep supervised hashing (RDSH) method, in which a robust pairwise loss and a quantitation loss are used to supervise the learning procedure. The quantitation loss guides the CNN to output binary codes. The robust pairwise loss for similarity-preserving learning is designed based on generalizations of the exponential and logarithmic functions. By adjusting its parameters, the robust pairwise loss can exhibit special properties, including tail-heaviness and boundedness, which results in the robustness of the learning procedure to noisy training data. To verify the robustness of the RDSH, we conduct experiments on CIFAR10 with different noisy levels, in which RDSH shows better robustness than other deep supervised hashing methods. Experiments on standard CIFAR-10 and NUS-WIDE datasets show that RDSH outperforms other baselines.
© (2020) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Zhaoguo Mo, Yuesheng Zhu, and Jiawei Zhan "Robust deep supervised hashing for image retrieval", Proc. SPIE 11519, Twelfth International Conference on Digital Image Processing (ICDIP 2020), 115191T (12 June 2020); https://doi.org/10.1117/12.2573083
PROCEEDINGS
13 PAGES


SHARE
Advertisement
Advertisement
Back to Top