D3still : Decoupled differential distillation for asymmetric image retrieval

Existing methods for asymmetric image retrieval employ a rigid pairwise similarity constraint between the query network and the larger gallery network. However, these oneto-one constraint approaches often fail to maintain retrieval order consistency, especially when the query network has limited rep...

Full description

Saved in:
Bibliographic Details
Main Authors: XIE, Yi, LIN, Yihong, CAI, Wenjie, XU, Xuemiao, ZHANG, Huaidong, DU, Yong, HE, Shengfeng
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2024
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/9776
https://ink.library.smu.edu.sg/context/sis_research/article/10776/viewcontent/Xie_D3still_CVPR_2024_paper.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-10776
record_format dspace
spelling sg-smu-ink.sis_research-107762024-12-16T02:09:20Z D3still : Decoupled differential distillation for asymmetric image retrieval XIE, Yi LIN, Yihong CAI, Wenjie XU, Xuemiao ZHANG, Huaidong DU, Yong HE, Shengfeng Existing methods for asymmetric image retrieval employ a rigid pairwise similarity constraint between the query network and the larger gallery network. However, these oneto-one constraint approaches often fail to maintain retrieval order consistency, especially when the query network has limited representational capacity. To overcome this problem, we introduce the Decoupled Differential Distillation (D3still) framework. This framework shifts from absolute one-to-one supervision to optimizing the relational differences in pairwise similarities produced by the query and gallery networks, thereby preserving a consistent retrieval order across both networks. Our method involves computing a pairwise similarity differential matrix within the gallery domain, which is then decomposed into three components: feature representation knowledge, inconsistent pairwise similarity differential knowledge, and consistent pairwise similarity differential knowledge. This strategic decomposition aligns the retrieval ranking of the query network with the gallery network effectively. Extensive experiments on various benchmark datasets reveal that D3still surpasses state-of-the-art methods in asymmetric image retrieval. 2024-06-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/9776 info:doi/10.1109/CVPR52733.2024.01626 https://ink.library.smu.edu.sg/context/sis_research/article/10776/viewcontent/Xie_D3still_CVPR_2024_paper.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Asymmetric image retrieval Decoupled differential distillation framework Artificial Intelligence and Robotics Graphics and Human Computer Interfaces
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Asymmetric image retrieval
Decoupled differential distillation framework
Artificial Intelligence and Robotics
Graphics and Human Computer Interfaces
spellingShingle Asymmetric image retrieval
Decoupled differential distillation framework
Artificial Intelligence and Robotics
Graphics and Human Computer Interfaces
XIE, Yi
LIN, Yihong
CAI, Wenjie
XU, Xuemiao
ZHANG, Huaidong
DU, Yong
HE, Shengfeng
D3still : Decoupled differential distillation for asymmetric image retrieval
description Existing methods for asymmetric image retrieval employ a rigid pairwise similarity constraint between the query network and the larger gallery network. However, these oneto-one constraint approaches often fail to maintain retrieval order consistency, especially when the query network has limited representational capacity. To overcome this problem, we introduce the Decoupled Differential Distillation (D3still) framework. This framework shifts from absolute one-to-one supervision to optimizing the relational differences in pairwise similarities produced by the query and gallery networks, thereby preserving a consistent retrieval order across both networks. Our method involves computing a pairwise similarity differential matrix within the gallery domain, which is then decomposed into three components: feature representation knowledge, inconsistent pairwise similarity differential knowledge, and consistent pairwise similarity differential knowledge. This strategic decomposition aligns the retrieval ranking of the query network with the gallery network effectively. Extensive experiments on various benchmark datasets reveal that D3still surpasses state-of-the-art methods in asymmetric image retrieval.
format text
author XIE, Yi
LIN, Yihong
CAI, Wenjie
XU, Xuemiao
ZHANG, Huaidong
DU, Yong
HE, Shengfeng
author_facet XIE, Yi
LIN, Yihong
CAI, Wenjie
XU, Xuemiao
ZHANG, Huaidong
DU, Yong
HE, Shengfeng
author_sort XIE, Yi
title D3still : Decoupled differential distillation for asymmetric image retrieval
title_short D3still : Decoupled differential distillation for asymmetric image retrieval
title_full D3still : Decoupled differential distillation for asymmetric image retrieval
title_fullStr D3still : Decoupled differential distillation for asymmetric image retrieval
title_full_unstemmed D3still : Decoupled differential distillation for asymmetric image retrieval
title_sort d3still : decoupled differential distillation for asymmetric image retrieval
publisher Institutional Knowledge at Singapore Management University
publishDate 2024
url https://ink.library.smu.edu.sg/sis_research/9776
https://ink.library.smu.edu.sg/context/sis_research/article/10776/viewcontent/Xie_D3still_CVPR_2024_paper.pdf
_version_ 1819113135462678528