Deep supervised hashing hash has been widely utilized in large-scale image retrieval due to its lightweight storage and fast search speed. The distribution of features from the existing hashing methods has been inevitably distorted from the original feature distribution, which resulted in the performance decline on image retrieval. With the constraints of the Euclidian metric, the distortion can be mitigated to certain extent. However, the Euclidian distance is sensitive to the norm of the features. On the point, we propose a novel deep hashing method, called cosine metric supervised deep hashing (CMDH), to perform hash learning by incorporating cosine metric and category loss. CMDH uses the cosine metric to effectively mitigate the impact caused by the diverse sample vector norms on retrieval performance. In addition, joint deep hash learning constructs binary coding over cosine loss and category loss, which further alleviates distortion in binary feature learning for efficient retrieval.
Cosine Metric Supervised Deep Hashing
Lect. Notes Electrical Eng.
International Conference on Autonomous Unmanned Systems ; 2021 ; Changsha, China September 24, 2021 - September 26, 2021
Proceedings of 2021 International Conference on Autonomous Unmanned Systems (ICAUS 2021) ; Chapter : 56 ; 560-570
2022-03-18
11 pages
Article/Chapter (Book)
Electronic Resource
English
Deep and fast: Deep learning hashing with semi-supervised graph construction
British Library Online Contents | 2016
|Deep and fast: Deep learning hashing with semi-supervised graph construction
British Library Online Contents | 2016
|Deep and fast: Deep learning hashing with semi-supervised graph construction
British Library Online Contents | 2016
|Semi-supervised multi-graph hashing for scalable similarity search
British Library Online Contents | 2014
|Temporary Vehicle ID With Deep Hashing
IEEE | 2019
|