Deep Saliency Hashing for Fine-grained Retrieval

In recent years, hashing methods have been proved to be effective and efficient for large-scale Web media search. However, the existing general hashing methods have limited discriminative power for describing fine-grained objects that share similar overall appearance but have a subtle difference. To...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - (2020) vom: 16. März
1. Verfasser: Jin, Sheng (VerfasserIn)
Weitere Verfasser: Yao, Hongxun, Sun, Xiaoshuai, Zhou, Shangchen, Zhang, Lei, Hua, Xiansheng
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2020
Zugriff auf das übergeordnete Werk:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Schlagworte:Journal Article
LEADER 01000caa a22002652 4500
001 NLM30778309X
003 DE-627
005 20240229162657.0
007 cr uuu---uuuuu
008 231225s2020 xx |||||o 00| ||eng c
024 7 |a 10.1109/TIP.2020.2971105  |2 doi 
028 5 2 |a pubmed24n1308.xml 
035 |a (DE-627)NLM30778309X 
035 |a (NLM)32191885 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Jin, Sheng  |e verfasserin  |4 aut 
245 1 0 |a Deep Saliency Hashing for Fine-grained Retrieval 
264 1 |c 2020 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Revised 27.02.2024 
500 |a published: Print-Electronic 
500 |a Citation Status Publisher 
520 |a In recent years, hashing methods have been proved to be effective and efficient for large-scale Web media search. However, the existing general hashing methods have limited discriminative power for describing fine-grained objects that share similar overall appearance but have a subtle difference. To solve this problem, we for the first time introduce the attention mechanism to the learning of fine-grained hashing codes. Specifically, we propose a novel deep hashing model, named deep saliency hashing (DSaH), which automatically mines salient regions and learns semantic-preserving hashing codes simultaneously. DSaH is a two-step end-to-end model consisting of an attention network and a hashing network. Our loss function contains three basic components, including the semantic loss, the saliency loss, and the quantization loss. As the core of DSaH, the saliency loss guides the attention network to mine discriminative regions from pairs of images.We conduct extensive experiments on both fine-grained and general retrieval datasets for performance evaluation. Experimental results on fine-grained datasets, including Oxford Flowers, Stanford Dogs, and CUB Birds demonstrate that our DSaH performs the best for the fine-grained retrieval task and beats the strongest competitor (DTQ) by approximately 10% on both Stanford Dogs and CUB Birds. DSaH is also comparable to several state-of-the-art hashing methods on CIFAR-10 and NUS-WIDE 
650 4 |a Journal Article 
700 1 |a Yao, Hongxun  |e verfasserin  |4 aut 
700 1 |a Sun, Xiaoshuai  |e verfasserin  |4 aut 
700 1 |a Zhou, Shangchen  |e verfasserin  |4 aut 
700 1 |a Zhang, Lei  |e verfasserin  |4 aut 
700 1 |a Hua, Xiansheng  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on image processing : a publication of the IEEE Signal Processing Society  |d 1992  |g (2020) vom: 16. März  |w (DE-627)NLM09821456X  |x 1941-0042  |7 nnns 
773 1 8 |g year:2020  |g day:16  |g month:03 
856 4 0 |u http://dx.doi.org/10.1109/TIP.2020.2971105  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |j 2020  |b 16  |c 03