Counterfactual Generation Framework for Few-Shot Learning

Dang, Z; Luo, M; Jia, C; Yan, C; Chang, X; Zheng, Q

Counterfactual Generation Framework for Few-Shot Learning

Dang, Z Luo, M Jia, C Yan, C Chang, X

Zheng, Q

Permalink

Publisher:: Institute of Electrical and Electronics Engineers (IEEE)
Publication Type:: Journal Article
Citation:: IEEE Transactions on Circuits and Systems for Video Technology, 2023, PP, (99), pp. 1-1
Issue Date:: 2023-01-01

Closed Access

	Filename	Description	Size
	Counterfactual_Generation_Framework_for_Few-Shot_Learning.pdf	Published version	4.17 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	Dang, Z
dc.contributor.author	Luo, M
dc.contributor.author	Jia, C
dc.contributor.author	Yan, C
dc.contributor.author	Chang, X https://orcid.org/0000-0002-7778-8807
dc.contributor.author	Zheng, Q
dc.date.accessioned	2023-03-31T09:37:17Z
dc.date.available	2023-03-31T09:37:17Z
dc.date.issued	2023-01-01
dc.identifier.citation	IEEE Transactions on Circuits and Systems for Video Technology, 2023, PP, (99), pp. 1-1
dc.identifier.issn	1051-8215
dc.identifier.issn	1558-2205
dc.identifier.uri	http://hdl.handle.net/10453/168967
dc.description.abstract	Few-shot learning (FSL) that aims to recognize novel classes with few labeled samples is troubled by its data scarcity. Though recent works tackle FSL with data augmentation-based methods, these models fail to maintain the discrimination and diversity of the generated samples due to the distribution shift and intra-class bias caused by the data scarcity, therefore greatly undermining the performance. To this end, we use causal mechanisms, which are constant among independent variables across data distribution, to alleviate such effects. In this sense, we decompose the image information into two independent components: sample-specific and class-agnostic information, and further propose a novel Counterfactual Generation Framework (CGF) to learn the underlying causal mechanisms to synthesize faithful samples for FSL. Specifically, based on the counterfactual inference, we design a class-agnostic feature extractor to capture the sample-specific information, together with a counterfactual generation network to simulate the data generation process from a causal perspective. Moreover, to leverage the power of CGF in counterfactual inference, we further develop a novel classifier that classifies samples based on their distributions of counterfactual generations. Extensive experiments demonstrate the effectiveness of CGF on four FSL benchmarks, <italic>e.g</italic>., 80.12/86.13% accuracy on 5-way 1/5-shot miniImageNet FSL tasks, significantly improving the performance. Our codes and models are available at https://github.com/eric-hang/CGF.
dc.language	en
dc.publisher	Institute of Electrical and Electronics Engineers (IEEE)
dc.relation.ispartof	IEEE Transactions on Circuits and Systems for Video Technology
dc.relation.isbasedon	10.1109/TCSVT.2023.3241651
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	0801 Artificial Intelligence and Image Processing, 0906 Electrical and Electronic Engineering
dc.subject.classification	Artificial Intelligence & Image Processing
dc.title	Counterfactual Generation Framework for Few-Shot Learning
dc.type	Journal Article
utslib.citation.volume	PP
utslib.for	0801 Artificial Intelligence and Image Processing
utslib.for	0906 Electrical and Electronic Engineering
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Strength - AAII - Australian Artificial Intelligence Institute
utslib.copyright.status	closed_access	*
dc.date.updated	2023-03-31T09:37:14Z
pubs.issue	99
pubs.publication-status	Published
pubs.volume	PP
utslib.citation.issue	99

Abstract:

Few-shot learning (FSL) that aims to recognize novel classes with few labeled samples is troubled by its data scarcity. Though recent works tackle FSL with data augmentation-based methods, these models fail to maintain the discrimination and diversity of the generated samples due to the distribution shift and intra-class bias caused by the data scarcity, therefore greatly undermining the performance. To this end, we use causal mechanisms, which are constant among independent variables across data distribution, to alleviate such effects. In this sense, we decompose the image information into two independent components: sample-specific and class-agnostic information, and further propose a novel Counterfactual Generation Framework (CGF) to learn the underlying causal mechanisms to synthesize faithful samples for FSL. Specifically, based on the counterfactual inference, we design a class-agnostic feature extractor to capture the sample-specific information, together with a counterfactual generation network to simulate the data generation process from a causal perspective. Moreover, to leverage the power of CGF in counterfactual inference, we further develop a novel classifier that classifies samples based on their distributions of counterfactual generations. Extensive experiments demonstrate the effectiveness of CGF on four FSL benchmarks, e.g., 80.12/86.13% accuracy on 5-way 1/5-shot miniImageNet FSL tasks, significantly improving the performance. Our codes and models are available at https://github.com/eric-hang/CGF.

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

http://hdl.handle.net/10453/168967