Cross-Scale Context Extracted Hashing for Fine-Grained Image Binary Encoding

Xuetong Xue, Jiaying Shi, Xinxue He, Shenghui Xu, Zhaoming Pan
Proceedings of The 14th Asian Conference on Machine Learning, PMLR 189:1197-1212, 2023.

Abstract

Deep hashing has been widely applied to large-scale image retrieval tasks owing to efficient computation and low storage cost by encoding high-dimensional image data into binary codes. Since binary codes do not contain as much information as float features, the essence of binary encoding is preserving the main context to guarantee retrieval quality. However, the existing hashing methods have great limitations on suppressing redundant background information and accurately encoding from Euclidean space to Hamming space by a simple sign function. In order to solve these problems, a Cross-Scale Context Extracted Hashing Network (CSCE-Net) is proposed in this paper. Firstly, we design a two-branch framework to capture fine-grained local information while maintaining high-level global semantic information. Besides, Attention guided Information Extraction module (AIE) is introduced between two branches, which suppresses areas of low context information cooperated with global sliding windows. Unlike previous methods, our CSCE-Net learns a content-related Dynamic Sign Function (DSF) to replace the original simple sign function. Therefore, the proposed CSCE-Net is context-sensitive and able to perform well on accurate image binary encoding. We further demonstrate that our CSCE-Net is superior to the existing hashing methods, which improves retrieval performance on standard benchmarks.

Cite this Paper

BibTeX
@InProceedings{pmlr-v189-xue23a, title = {Cross-Scale Context Extracted Hashing for Fine-Grained Image Binary Encoding}, author = {Xue, Xuetong and Shi, Jiaying and He, Xinxue and Xu, Shenghui and Pan, Zhaoming}, booktitle = {Proceedings of The 14th Asian Conference on Machine Learning}, pages = {1197--1212}, year = {2023}, editor = {Khan, Emtiyaz and Gonen, Mehmet}, volume = {189}, series = {Proceedings of Machine Learning Research}, month = {12--14 Dec}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v189/xue23a/xue23a.pdf}, url = {https://proceedings.mlr.press/v189/xue23a.html}, abstract = {Deep hashing has been widely applied to large-scale image retrieval tasks owing to efficient computation and low storage cost by encoding high-dimensional image data into binary codes. Since binary codes do not contain as much information as float features, the essence of binary encoding is preserving the main context to guarantee retrieval quality. However, the existing hashing methods have great limitations on suppressing redundant background information and accurately encoding from Euclidean space to Hamming space by a simple sign function. In order to solve these problems, a Cross-Scale Context Extracted Hashing Network (CSCE-Net) is proposed in this paper. Firstly, we design a two-branch framework to capture fine-grained local information while maintaining high-level global semantic information. Besides, Attention guided Information Extraction module (AIE) is introduced between two branches, which suppresses areas of low context information cooperated with global sliding windows. Unlike previous methods, our CSCE-Net learns a content-related Dynamic Sign Function (DSF) to replace the original simple sign function. Therefore, the proposed CSCE-Net is context-sensitive and able to perform well on accurate image binary encoding. We further demonstrate that our CSCE-Net is superior to the existing hashing methods, which improves retrieval performance on standard benchmarks.} }
Endnote
%0 Conference Paper %T Cross-Scale Context Extracted Hashing for Fine-Grained Image Binary Encoding %A Xuetong Xue %A Jiaying Shi %A Xinxue He %A Shenghui Xu %A Zhaoming Pan %B Proceedings of The 14th Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2023 %E Emtiyaz Khan %E Mehmet Gonen %F pmlr-v189-xue23a %I PMLR %P 1197--1212 %U https://proceedings.mlr.press/v189/xue23a.html %V 189 %X Deep hashing has been widely applied to large-scale image retrieval tasks owing to efficient computation and low storage cost by encoding high-dimensional image data into binary codes. Since binary codes do not contain as much information as float features, the essence of binary encoding is preserving the main context to guarantee retrieval quality. However, the existing hashing methods have great limitations on suppressing redundant background information and accurately encoding from Euclidean space to Hamming space by a simple sign function. In order to solve these problems, a Cross-Scale Context Extracted Hashing Network (CSCE-Net) is proposed in this paper. Firstly, we design a two-branch framework to capture fine-grained local information while maintaining high-level global semantic information. Besides, Attention guided Information Extraction module (AIE) is introduced between two branches, which suppresses areas of low context information cooperated with global sliding windows. Unlike previous methods, our CSCE-Net learns a content-related Dynamic Sign Function (DSF) to replace the original simple sign function. Therefore, the proposed CSCE-Net is context-sensitive and able to perform well on accurate image binary encoding. We further demonstrate that our CSCE-Net is superior to the existing hashing methods, which improves retrieval performance on standard benchmarks.
APA
Xue, X., Shi, J., He, X., Xu, S. & Pan, Z.. (2023). Cross-Scale Context Extracted Hashing for Fine-Grained Image Binary Encoding. Proceedings of The 14th Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 189:1197-1212 Available from https://proceedings.mlr.press/v189/xue23a.html.

Related Material