Yang H.-FTu C.-HCHU-SONG CHEN2021-09-022021-09-02201918650929https://www.scopus.com/inward/record.uri?eid=2-s2.0-85069706246&doi=10.1007%2f978-981-13-9190-3_13&partnerID=40&md5=542e031f749a7fb787ac44e1b4e55487https://scholars.lib.ntu.edu.tw/handle/123456789/581341Learning-based hashing has been widely employed for large-scale similarity retrieval due to its efficient computation and compressed storage. In this paper, we propose ResHash, a deep representation hash code learning approach to learning compact and discriminative binary codes. In ResHash, we assume that each semantic label has its own representation codeword and these codewords guide hash coding. The codewords are attractors that attract semantically similar images and are also repulsors that repel semantically dissimilar ones. Furthermore, ResHash jointly learns compact binary codes and discover representation codewords from data by a simple margin ranking loss, making it easily realizable and avoiding the need to hand-craft the codewords beforehand. Experimental results on standard benchmark datasets show the effectiveness of ResHash. ? Springer Nature Singapore Pte Ltd. 2019.Binary codes; Digital storage; Hash functions; Image retrieval; Semantics; Benchmark datasets; Code-words; Codeword; Efficient computation; Learning approach; Scale similarity; Semantic labels; Similar image; Deep learningconference paper10.1007/978-981-13-9190-3_132-s2.0-85069706246