research-article

Meta-FDMixup: Cross-Domain Few-Shot Learning Guided by Labeled Target Data

Authors:

Yu-Gang JiangAuthors Info & Claims

MM '21: Proceedings of the 29th ACM International Conference on Multimedia

Pages 5326 - 5334

https://doi.org/10.1145/3474085.3475655

Published: 17 October 2021 Publication History

Abstract

A recent study [4] finds that existing few-shot learning methods, trained on the source domain, fail to generalize to the novel target domain when a domain gap is observed. This motivates the task of Cross-Domain Few-Shot Learning (CD-FSL). In this paper, we realize that the labeled target data in CD-FSL has not been leveraged in any way to help the learning process. Thus, we advocate utilizing few labeled target data to guide the model learning. Technically, a novel meta-FDMixup network is proposed. We tackle this problem mainly from two aspects. Firstly, to utilize the source and the newly introduced target data of two different class sets, a mixup module is re-proposed and integrated into the meta-learning mechanism. Secondly, a novel disentangle module together with a domain classifier is proposed to extract the disentangled domain-irrelevant and domain-specific features. These two modules together enable our model to narrow the domain gap thus generalizing well to the target datasets. Additionally, a detailed feasibility and pilot study is conducted to reflect the intuitive understanding of CD-FSL under our new setting. Experimental results show the effectiveness of our new setting and the proposed method. Codes and models are available at https://github.com/lovelyqian/Meta-FDMixup.

References

[1]

Konstantinos Bousmalis, Nathan Silberman, David Dohan, Dumitru Erhan, and Dilip Krishnan. 2017. Unsupervised pixel-level domain adaptation with generative adversarial networks. In CVPR.

[2]

Konstantinos Bousmalis, George Trigeorgis, Nathan Silberman, Dilip Krishnan, and Dumitru Erhan. 2016. Domain separation networks. arXiv preprint (2016).

Digital Library

[3]

John Cai, Bill Cai, and Sheng Mei Shen. 2020. SB-MTL: Score-based Meta Transfer-Learning for Cross-Domain Few-Shot Learning. arXiv preprint arXiv:2012.01784 (2020).

[4]

Wei-Yu Chen, Yen-Cheng Liu, Zsolt Kira, Yu-Chiang Frank Wang, and Jia-Bin Huang. 2019 b. A closer look at few-shot classification. arXiv preprint (2019).

[5]

Zitian Chen, Yanwei Fu, Kaiyu Chen, and Yu-Gang Jiang. 2019 a. Image block augmentation for one-shot learning. In AAAI.

[6]

Nanyi Fei, Zhiwu Lu, Tao Xiang, and Songfang Huang. [n.d.]. MELR: Meta-Learning via Modeling Episode-level Relationships for Few-shot Learning. ([n.,d.]).

[7]

Chelsea Finn, Pieter Abbeel, and Sergey Levine. 2017. Model-agnostic meta-learning for fast adaptation of deep networks. arXiv preprint (2017).

Digital Library

[8]

Yaroslav Ganin, Evgeniya Ustinova, Hana Ajakan, Pascal Germain, Hugo Larochelle, Francc ois Laviolette, Mario Marchand, and Victor Lempitsky. 2016 Domain-adversarial training of neural networks. JMLR (2016).

Digital Library

[9]

Victor Garcia and Joan Bruna. 2017. Few-shot learning with graph neural networks. arXiv preprint (2017).

[10]

Muhammad Ghifary, W Bastiaan Kleijn, Mengjie Zhang, David Balduzzi, and Wen Li. 2016. Deep reconstruction-classification networks for unsupervised domain adaptation. In ECCV.

[11]

Yunhui Guo, Noel C Codella, Leonid Karlinsky, James V Codella, John R Smith, Kate Saenko, Tajana Rosing, and Rogerio Feris. 2020. A broader study of cross-domain few-shot learning. In ECCV .

[12]

Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In CVPR.

[13]

Dan Hendrycks, Norman Mu, Ekin D Cubuk, Barret Zoph, Justin Gilmer, and Balaji Lakshminarayanan. 2019. Augmix: A simple data processing method to improve robustness and uncertainty. arXiv preprint arXiv:1912.02781 (2019).

[14]

Ruibing Hou, Hong Chang, Bingpeng Ma, Shiguang Shan, and Xilin Chen. 2019. Cross attention network for few-shot classification. arXiv preprint arXiv:1910.07677 (2019).

Digital Library

[15]

Guoliang Kang, Lu Jiang, Yi Yang, and Alexander G Hauptmann. 2019. Contrastive adaptation network for unsupervised domain adaptation. In CVPR.

[16]

Jang-Hyun Kim, Wonho Choo, and Hyun Oh Song. 2020. Puzzle mix: Exploiting saliency and local statistics for optimal mixup. In International Conference on Machine Learning. PMLR, 5275--5285.

[17]

Jonathan Krause, Michael Stark, Jia Deng, and Li Fei-Fei. 2013. 3d object representations for fine-grained categorization. In ICCVW.

Digital Library

[18]

Kai Li, Yulun Zhang, Kunpeng Li, and Yun Fu. 2020 b. Adversarial Feature Hallucination Networks for Few-Shot Learning. In CVPR.

[19]

Xingjian Li, Haoyi Xiong, Haozhe An, Chengzhong Xu, and Dejing Dou. 2020 a. XMixup: Efficient Transfer Learning with Auxiliary Samples by Cross-domain Mixup. arXiv preprint (2020).

[20]

Cheng Perng Phoo and Bharath Hariharan. 2020. Self-training for Few-shot Transfer Across Extreme Task Differences. arXiv preprint (2020).

[21]

Sachin Ravi and Hugo Larochelle. 2017. Optimization as a model for few-shot learning. In ICLR.

[22]

Artem Rozantsev, Mathieu Salzmann, and Pascal Fua. 2018. Beyond sharing weights for deep domain adaptation. TPAMI (2018).

Digital Library

[23]

Andrei A Rusu, Dushyant Rao, Jakub Sygnowski, Oriol Vinyals, Razvan Pascanu, Simon Osindero, and Raia Hadsell. 2018. Meta-learning with latent embedding optimization. arXiv preprint (2018).

[24]

Ramprasaath R Selvaraju, Michael Cogswell, Abhishek Das, Ramakrishna Vedantam, Devi Parikh, and Dhruv Batra. 2017. Grad-cam: Visual explanations from deep networks via gradient-based localization. In Proceedings of the IEEE international conference on computer vision. 618--626.

[25]

Jake Snell, Kevin Swersky, and Richard Zemel. 2017. Prototypical networks for few-shot learning. In NeurIPS.

Digital Library

[26]

Jiamei Sun, Sebastian Lapuschkin, Wojciech Samek, Yunqing Zhao, Ngai-Man Cheung, and Alexander Binder. 2020. Explanation-guided training for cross-domain few-shot classification. arXiv preprint (2020).

[27]

Flood Sung, Yongxin Yang, Li Zhang, Tao Xiang, Philip HS Torr, and Timothy M Hospedales. 2018. Learning to compare: Relation network for few-shot learning. In CVPR.

[28]

Hung-Yu Tseng, Hsin-Ying Lee, Jia-Bin Huang, and Ming-Hsuan Yang. 2020. Cross-domain few-shot classification via learned feature-wise transformation. In ICLR.

[29]

Eric Tzeng, Judy Hoffman, Trevor Darrell, and Kate Saenko. 2015. Simultaneous deep transfer across domains and tasks. In ICCV.

Digital Library

[30]

Eric Tzeng, Judy Hoffman, Ning Zhang, Kate Saenko, and Trevor Darrell. 2014. Deep domain confusion: Maximizing for domain invariance. arXiv preprint (2014).

[31]

Grant Van Horn, Oisin Mac Aodha, Yang Song, Yin Cui, Chen Sun, Alex Shepard, Hartwig Adam, Pietro Perona, and Serge Belongie. 2018. The inaturalist species classification and detection dataset. In CVPR.

[32]

Vikas Verma, Alex Lamb, Christopher Beckham, Amir Najafi, Ioannis Mitliagkas, David Lopez-Paz, and Yoshua Bengio. 2019. Manifold mixup: Better representations by interpolating hidden states. In ICML .

[33]

Oriol Vinyals, Charles Blundell, Timothy Lillicrap, Daan Wierstra, et al. 2016. Matching networks for one shot learning. In NeurIPS.

Digital Library

[34]

Catherine Wah, Steve Branson, Peter Welinder, Pietro Perona, and Serge Belongie. 2011. The caltech-ucsd birds-200--2011 dataset. (2011).

[35]

Han-Jia Ye, Hexiang Hu, De-Chuan Zhan, and Fei Sha. 2020. Few-shot learning via embedding adaptation with set-to-set functions. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 8808--8817.

[36]

Sangdoo Yun, Dongyoon Han, Seong Joon Oh, Sanghyuk Chun, Junsuk Choe, and Youngjoon Yoo. 2019. Cutmix: Regularization strategy to train strong classifiers with localizable features. In ICCV.

[37]

Hongyi Zhang, Moustapha Cisse, Yann N Dauphin, and David Lopez-Paz. 2017. mixup: Beyond empirical risk minimization. arXiv preprint (2017).

[38]

Bolei Zhou, Agata Lapedriza, Aditya Khosla, Aude Oliva, and Antonio Torralba. 2017. Places: A 10 million image database for scene recognition. TPAMI (2017).

Cited By

Luo CTang WWang QZheng D(2025)Few-Shot Website Fingerprinting With Distribution CalibrationIEEE Transactions on Dependable and Secure Computing10.1109/TDSC.2024.341101422:1(632-648)Online publication date: Jan-2025
https://doi.org/10.1109/TDSC.2024.3411014
Wu HXin L(2025)Cluster-HGNN: Deep Local Features Clustering for Few-Shot Image Classification With Hybrid Graph Neural NetworksIEEE Access10.1109/ACCESS.2025.353861013(30965-30975)Online publication date: 2025
https://doi.org/10.1109/ACCESS.2025.3538610
Li XHe ZZhang LGuo SHu BGuo K(2025)CDCNet: Cross-domain few-shot learning with adaptive representation enhancementPattern Recognition10.1016/j.patcog.2025.111382162(111382)Online publication date: Jun-2025
https://doi.org/10.1016/j.patcog.2025.111382
Show More Cited By

Index Terms

Meta-FDMixup: Cross-Domain Few-Shot Learning Guided by Labeled Target Data
1. Computing methodologies
  1. Artificial intelligence
    1. Computer vision
  2. Machine learning

Recommendations

Free-Lunch for Cross-Domain Few-Shot Learning: Style-Aware Episodic Training with Robust Contrastive Learning
MM '22: Proceedings of the 30th ACM International Conference on Multimedia

Cross-Domain Few-Shot Learning (CDFSL) aims for training an adaptable model that can learn out-of-domain classes with a handful of samples. Compared to the well-studied few-shot learning problem, the difficulty for CDFSL lies in that the available ...
TGDM: Target Guided Dynamic Mixup for Cross-Domain Few-Shot Learning
MM '22: Proceedings of the 30th ACM International Conference on Multimedia

Given sufficient training data on the source domain, cross-domain few-shot learning (CD-FSL) aims at recognizing new classes with a small number of labeled examples on the target domain. The key to addressing CD-FSL is to narrow the domain gap and ...
ME-D2N: Multi-Expert Domain Decompositional Network for Cross-Domain Few-Shot Learning
MM '22: Proceedings of the 30th ACM International Conference on Multimedia

Recently, Cross-Domain Few-Shot Learning (CD-FSL) which aims at addressing the Few-Shot Learning (FSL) problem across different domains has attracted rising attention. The core challenge of CD-FSL lies in the domain gap between the source and novel ...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

MM '21: Proceedings of the 29th ACM International Conference on Multimedia

October 2021

5796 pages

ISBN:9781450386517

DOI:10.1145/3474085

General Chairs:
Heng Tao Shen
University of Electronic Science&Technology of China, China
,
Yueting Zhuang
Zhejiang University, China
,
John R. Smith
IBM, USA
,
Program Chairs:
Yang Yang
University of Electronic Science and Technology of China, China
,
Pablo Cesar
CWI&TU Delft, The Netherlands
,
Florian Metze
FACEBOOK, Inc., USA
,
Balakrishnan Prabhakaran
University of Texas at Dallas, USA

Copyright © 2021 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

SIGMM: ACM Special Interest Group on Multimedia

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 17 October 2021

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Funding Sources

National Natural Science Foundation of China Project

Conference

MM '21

Sponsor:

SIGMM

MM '21: ACM Multimedia Conference

October 20 - 24, 2021

Virtual Event, China

Acceptance Rates

Overall Acceptance Rate 2,145 of 8,556 submissions, 25%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

52
Total Citations
View Citations
479
Total Downloads

Downloads (Last 12 months)87
Downloads (Last 6 weeks)9

Reflects downloads up to 27 Feb 2025

Other Metrics

View Author Metrics

Citations

Cited By

Luo CTang WWang QZheng D(2025)Few-Shot Website Fingerprinting With Distribution CalibrationIEEE Transactions on Dependable and Secure Computing10.1109/TDSC.2024.341101422:1(632-648)Online publication date: Jan-2025
https://doi.org/10.1109/TDSC.2024.3411014
Wu HXin L(2025)Cluster-HGNN: Deep Local Features Clustering for Few-Shot Image Classification With Hybrid Graph Neural NetworksIEEE Access10.1109/ACCESS.2025.353861013(30965-30975)Online publication date: 2025
https://doi.org/10.1109/ACCESS.2025.3538610
Li XHe ZZhang LGuo SHu BGuo K(2025)CDCNet: Cross-domain few-shot learning with adaptive representation enhancementPattern Recognition10.1016/j.patcog.2025.111382162(111382)Online publication date: Jun-2025
https://doi.org/10.1016/j.patcog.2025.111382
Guo FQi HZhang XZhu LSun J(2025)GSLTA-CDFSAR: Global Sequences and Local Tuples Alignment for Cross-Domain Few-Shot Action RecognitionKnowledge-Based Systems10.1016/j.knosys.2025.113041(113041)Online publication date: Jan-2025
https://doi.org/10.1016/j.knosys.2025.113041
Bi YZhu HShi JSong B(2025)TsCANet: Three-stream contrastive adaptive network for cross-domain few-shot learningThe Journal of Supercomputing10.1007/s11227-024-06482-281:1Online publication date: 1-Jan-2025
https://dl.acm.org/doi/10.1007/s11227-024-06482-2
Yue LFeng LShuai QLi ZXu L(2025)Multi-level adaptive feature representation based on task augmentation for Cross-Domain Few-Shot learningApplied Intelligence10.1007/s10489-024-06110-955:4Online publication date: 10-Jan-2025
https://doi.org/10.1007/s10489-024-06110-9
Ruan JHe JTong YWang YFang YQu L(2024)Knowledge Embedding Relation Network for Small Data Defect DetectionApplied Sciences10.3390/app1417792214:17(7922)Online publication date: 5-Sep-2024
https://doi.org/10.3390/app14177922
Zhang TCai QGao FQi LDong JLarson K(2024)Exploring cross-domain few-shot classification via frequency-aware promptingProceedings of the Thirty-Third International Joint Conference on Artificial Intelligence10.24963/ijcai.2024/607(5490-5498)Online publication date: 3-Aug-2024
https://dl.acm.org/doi/10.24963/ijcai.2024/607
Zhuo LFu YChen JCao YJiang Y(2024)Unified View Empirical Study for Large Pretrained Model on Cross-Domain Few-Shot LearningACM Transactions on Multimedia Computing, Communications, and Applications10.1145/367323120:9(1-18)Online publication date: 19-Jun-2024
https://dl.acm.org/doi/10.1145/3673231
Xu JLiu BXiao Y(2024)A Multitask Latent Feature Augmentation Method for Few-Shot LearningIEEE Transactions on Neural Networks and Learning Systems10.1109/TNNLS.2022.321357635:5(6976-6990)Online publication date: May-2024
https://doi.org/10.1109/TNNLS.2022.3213576
Show More Cited By

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Figures

Tables

Media

View Table of Conten