Self-Paced Hard Task-Example Mining for Few-Shot Classification

Xu, R; Yang, X; Yao, X; Tao, D; Cao, W; Lu, X; Liu, W

Self-Paced Hard Task-Example Mining for Few-Shot Classification

Xu, R Yang, X

Yao, X Tao, D Cao, W Lu, X Liu, W

Permalink

Publisher:: IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Publication Type:: Journal Article
Citation:: IEEE Transactions on Circuits and Systems for Video Technology, 2023, 33, (10), pp. 5631-5644
Issue Date:: 2023-10-01

Closed Access

	Filename	Description	Size
	Self-Paced_Hard_Task-Example_Mining_for_Few-Shot_Classification.pdf	Published version	1.6 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	Xu, R
dc.contributor.author	Yang, X https://orcid.org/0000-0001-6487-3183
dc.contributor.author	Yao, X
dc.contributor.author	Tao, D
dc.contributor.author	Cao, W
dc.contributor.author	Lu, X
dc.contributor.author	Liu, W
dc.date.accessioned	2024-03-21T01:59:58Z
dc.date.available	2024-03-21T01:59:58Z
dc.date.issued	2023-10-01
dc.identifier.citation	IEEE Transactions on Circuits and Systems for Video Technology, 2023, 33, (10), pp. 5631-5644
dc.identifier.issn	1051-8215
dc.identifier.issn	1558-2205
dc.identifier.uri	http://hdl.handle.net/10453/176962
dc.description.abstract	In recent years, researchers have commonly employed assistant tasks to enhance the training phase of the few-shot classification models. Several methods have been proposed to exploit and optimize the training tasks, such as Curriculum Learning (CL) and Hard Example Mining (HEM). However, most of the existing strategies can not elaborately leverage the training tasks and share some common drawbacks, including 1) the ignorance of the target tasks' properties, and 2) the neglect of sample relationships. In this work, we propose a Self-Paced Hard tAsk-Example Mining (SP-HAEM) method to solve these problems. Specifically, the SP-HAEM automatically chooses hard examples via the similarity between training and target tasks to optimize the support set. To represent the property of target tasks, SP-HAEM obtains a representation of the dataset, called 'meta-task'. No need to apply an additional model to measure difficulty and choose hard examples like other HEM methods, SP-HAEM selects the tasks with large optimal transport distance to the meta-task as hard tasks. Thus, training with such hard tasks can not only enhances the generalization ability of the model but also eliminate the negative effect of redundancy tasks. To evaluate the effectiveness of SP-HAEM, we conduct extensive experiments on a variety of datasets, including MiniImageNet, TieredImageNet, and FC100. The results of the experiments show that SP-HAEM can achieve higher accuracy compared with the typical few-shot classification models, e.g., Prototypical Network, MAML, FEAT, and MTL.
dc.language	English
dc.publisher	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
dc.relation.ispartof	IEEE Transactions on Circuits and Systems for Video Technology
dc.relation.isbasedon	10.1109/TCSVT.2023.3263593
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.subject.classification	4006 Communications engineering
dc.subject.classification	4009 Electronics, sensors and digital hardware
dc.subject.classification	4603 Computer vision and multimedia computation
dc.title	Self-Paced Hard Task-Example Mining for Few-Shot Classification
dc.type	Journal Article
utslib.citation.volume	33
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
utslib.copyright.status	closed_access	*
dc.date.updated	2024-03-21T01:59:56Z
pubs.issue	10
pubs.publication-status	Published
pubs.volume	33
utslib.citation.issue	10

Abstract:

In recent years, researchers have commonly employed assistant tasks to enhance the training phase of the few-shot classification models. Several methods have been proposed to exploit and optimize the training tasks, such as Curriculum Learning (CL) and Hard Example Mining (HEM). However, most of the existing strategies can not elaborately leverage the training tasks and share some common drawbacks, including 1) the ignorance of the target tasks' properties, and 2) the neglect of sample relationships. In this work, we propose a Self-Paced Hard tAsk-Example Mining (SP-HAEM) method to solve these problems. Specifically, the SP-HAEM automatically chooses hard examples via the similarity between training and target tasks to optimize the support set. To represent the property of target tasks, SP-HAEM obtains a representation of the dataset, called 'meta-task'. No need to apply an additional model to measure difficulty and choose hard examples like other HEM methods, SP-HAEM selects the tasks with large optimal transport distance to the meta-task as hard tasks. Thus, training with such hard tasks can not only enhances the generalization ability of the model but also eliminate the negative effect of redundancy tasks. To evaluate the effectiveness of SP-HAEM, we conduct extensive experiments on a variety of datasets, including MiniImageNet, TieredImageNet, and FC100. The results of the experiments show that SP-HAEM can achieve higher accuracy compared with the typical few-shot classification models, e.g., Prototypical Network, MAML, FEAT, and MTL.

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

http://hdl.handle.net/10453/176962