Progressive Local Filter Pruning for Image Retrieval Acceleration

Wang, X; Zheng, Z; He, Y; Yan, F; Zeng, Z; Yang, Y

Progressive Local Filter Pruning for Image Retrieval Acceleration

Wang, X Zheng, Z He, Y Yan, F Zeng, Z Yang, Y

Permalink

Publisher:: IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Publication Type:: Journal Article
Citation:: IEEE Transactions on Multimedia, 2023, 25, pp. 9597-9607
Issue Date:: 2023-01-01

Closed Access

	Filename	Description	Size
	Progressive Local Filter Pruning for Image Retrieval Acceleration_Published.pdf	Published version	1.9 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Wang, X
dc.contributor.author	Zheng, Z
dc.contributor.author	He, Y
dc.contributor.author	Yan, F
dc.contributor.author	Zeng, Z
dc.contributor.author	Yang, Y https://orcid.org/0000-0002-0512-880X
dc.date.accessioned	2024-03-08T05:31:40Z
dc.date.available	2024-03-08T05:31:40Z
dc.date.issued	2023-01-01
dc.identifier.citation	IEEE Transactions on Multimedia, 2023, 25, pp. 9597-9607
dc.identifier.issn	1520-9210
dc.identifier.issn	1941-0077
dc.identifier.uri	http://hdl.handle.net/10453/176363
dc.description.abstract	Most image retrieval works aim at learning discriminative visual features, while little attention is paid to the retrieval efficiency. The speed of feature extraction is key to the real-world system. Therefore, in this article, we focus on network pruning for image retrieval acceleration. Different from the classification models predicting discrete categories, image retrieval models usually extract continuous features for retrieval, which are more sensitive to network pruning. Such different characteristics of the retrieval and classification models make the traditional pruning method sub-optimal for image retrieval acceleration. Two points are critical for pruning image retrieval models: preserving the local geometry structure of filters and maintaining the model capacity during pruning. In view of the above considerations, we propose a Progressive Local Filter Pruning (PLFP) method. Specifically, we analyze the local geometry of filter distribution in every layer and select redundant filters according to one new criterion that the filter can be replaced locally by other similar filters. Furthermore, to preserve the model capacity of the original model, the proposed method progressively prune the filter by decreasing the scale of filter weights gradually. We evaluate our method on four scene retrieval datasets, i.e., Oxford5K, Oxford105K, Paris6K, and Paris106K, and one person re-identification dataset, i.e., Market-1501. Extensive experiments show that the proposed method (1) preserves the original model capacity while pruning (2) and achieves superior performance to other widely-used pruning methods.
dc.language	English
dc.publisher	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
dc.relation.ispartof	IEEE Transactions on Multimedia
dc.relation.isbasedon	10.1109/TMM.2023.3256092
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	08 Information and Computing Sciences, 09 Engineering
dc.subject.classification	Artificial Intelligence & Image Processing
dc.subject.classification	40 Engineering
dc.subject.classification	46 Information and computing sciences
dc.title	Progressive Local Filter Pruning for Image Retrieval Acceleration
dc.type	Journal Article
utslib.citation.volume	25
utslib.for	08 Information and Computing Sciences
utslib.for	09 Engineering
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology
utslib.copyright.status	closed_access	*
dc.date.updated	2024-03-08T05:31:39Z
pubs.publication-status	Published
pubs.volume	25

Abstract:

Most image retrieval works aim at learning discriminative visual features, while little attention is paid to the retrieval efficiency. The speed of feature extraction is key to the real-world system. Therefore, in this article, we focus on network pruning for image retrieval acceleration. Different from the classification models predicting discrete categories, image retrieval models usually extract continuous features for retrieval, which are more sensitive to network pruning. Such different characteristics of the retrieval and classification models make the traditional pruning method sub-optimal for image retrieval acceleration. Two points are critical for pruning image retrieval models: preserving the local geometry structure of filters and maintaining the model capacity during pruning. In view of the above considerations, we propose a Progressive Local Filter Pruning (PLFP) method. Specifically, we analyze the local geometry of filter distribution in every layer and select redundant filters according to one new criterion that the filter can be replaced locally by other similar filters. Furthermore, to preserve the model capacity of the original model, the proposed method progressively prune the filter by decreasing the scale of filter weights gradually. We evaluate our method on four scene retrieval datasets, i.e., Oxford5K, Oxford105K, Paris6K, and Paris106K, and one person re-identification dataset, i.e., Market-1501. Extensive experiments show that the proposed method (1) preserves the original model capacity while pruning (2) and achieves superior performance to other widely-used pruning methods.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/176363