Complementary Incremental Hashing With Query-Adaptive Re-Ranking for Image Retrieval

被引:12
作者
Tian, Xing [1 ,2 ]
Ng, Wing W. Y. [1 ]
Wang, Hui [2 ]
Kwong, Sam [3 ]
机构
[1] South China Univ Technol, Sch Comp Sci & Engn, Guangdong Prov Key Lab Computat Intelligence & Cy, Guangzhou 510006, Peoples R China
[2] City Univ Hong Kong, Dept Comp Sci, Hong Kong, Peoples R China
[3] Ulster Univ, Sch Comp, Belfast BT15 1ED, Antrim, North Ireland
基金
欧盟地平线“2020”; 中国国家自然科学基金;
关键词
Image retrieval; Training; Semantics; Hamming distance; Computer science; Laplace equations; Image Retrieval; Hashing; Non-stationary Environment; Concept Drift; Re-ranking; SEARCH; GRAPH;
D O I
10.1109/TMM.2020.2994509
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Concept drift is prevalent in non-stationary data environments but is rarely researched in image retrieval. Therefore, more research is needed on image retrieval in non-stationary data environments so that highly relevant images can still be retrieved when concept drifts happen. Hashing is a key technique to allow efficient image retrieval, so incremental hashing technique emerges in recent years for image retrieval in non-stationary environments. A state-of-the-art method is Incremental Hashing (ICH). ICH trains new hash tables on new data without considering the performance of previous hash tables, so the dependency of successive hash tables is ignored. To make use of this dependency in order to improve the performance of image retrieval in non-stationary environments, Complementary Incremental Hashing with query-adaptive Re-ranking (CIHR) is proposed in this paper. CIHR trains multiple hash tables incrementally, one for each data chunk of images. A new hash table is trained on a new data chunk of images as well as those images badly hashed by previous hash tables, thus the new hash table is complementary to the previous hash tables. To use the hash tables more effectively, a query-adaptive re-ranking method is used to weight all hash functions in each hash table according to their retrieval performance with respect to a given query. Weighted Hamming distance is finally used to evaluate the similarity between the query and the images in the database, as the basis of image retrieval. Experimental results on simulated non-stationary scenarios show that the proposed CIHR method achieves higher retrieval accuracy than all methods being compared, thus setting a new state of the art in image retrieval in non-stationary data environments.
引用
收藏
页码:1210 / 1224
页数:15
相关论文
共 47 条
[1]   MIHash: Online Hashing with Mutual Information [J].
Cakir, Fatih ;
He, Kun ;
Bargal, Sarah Adel ;
Sclaroff, Stan .
2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2017, :437-445
[2]   Adaptive Hashing for Fast Similarity Search [J].
Cakir, Fatih ;
Sclaroff, Stan .
2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2015, :1044-1052
[3]  
Cakir F, 2015, IEEE IMAGE PROC, P2606, DOI 10.1109/ICIP.2015.7351274
[4]   Face Recognition and Retrieval Using Cross-Age Reference Coding With Cross-Age Celebrity Dataset [J].
Chen, Bor-Chun ;
Chen, Chu-Song ;
Hsu, Winston H. .
IEEE TRANSACTIONS ON MULTIMEDIA, 2015, 17 (06) :804-815
[5]   Nonlinear Discrete Hashing [J].
Chen, Zhixiang ;
Lu, Jiwen ;
Feng, Jianjiang ;
Zhou, Jie .
IEEE TRANSACTIONS ON MULTIMEDIA, 2017, 19 (01) :123-135
[6]   Histograms of oriented gradients for human detection [J].
Dalal, N ;
Triggs, B .
2005 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOL 1, PROCEEDINGS, 2005, :886-893
[7]   Triplet-Based Deep Hashing Network for Cross-Modal Retrieval [J].
Deng, Cheng ;
Chen, Zhaojia ;
Liu, Xianglong ;
Gao, Xinbo ;
Tao, Dacheng .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2018, 27 (08) :3893-3903
[8]   Incremental Learning of Concept Drift in Nonstationary Environments [J].
Elwell, Ryan ;
Polikar, Robi .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2011, 22 (10) :1517-1531
[9]   Locality-Sensitive Hashing for Chi2 Distance [J].
Gorisse, David ;
Cord, Matthieu ;
Precioso, Frederic .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2012, 34 (02) :402-409
[10]   Learning to Hash With Optimized Anchor Embedding for Scalable Retrieval [J].
Guo, Yuchen ;
Ding, Guiguang ;
Liu, Li ;
Han, Jungong ;
Shao, Ling .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2017, 26 (03) :1344-1354