AmpliBias: Mitigating Dataset Bias through Bias Amplification in Few-shot Learning for Generative Models
Authors: 
Donggeun Ko, Dongjun Lee, Namjun Park, Kyoungrae Noh, Hyeonjin Park, Jaekwang KimAuthors Info & Claims
Pages 4028 - 4032
Abstract
Deep learning models exhibit a dependency on peripheral attributes of input data, such as shapes and colors, leading the models to become biased towards these certain attributes that result in subsequent degradation of performance. In this paper, we alleviate this problem by presenting~\sysname, a novel framework that tackles dataset bias by leveraging generative models to amplify bias and facilitate the learning of debiased representations of the classifier. Our method involves three major steps. We initially train a biased classifier, denoted as f_b, on a biased dataset and extract the top-K biased-conflict samples. Next, we train a generator solely on a bias-conflict dataset comprised of these top-K samples, aiming to learn the distribution of bias-conflict samples. Finally, we re-train the classifier on the newly constructed debiased dataset, which combines the original and amplified data. This allows the biased classifier to competently learn debiased representation. Extensive experiments validate that our proposed method effectively debiases the biased classifier.
References
[1]
Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. Generative adversarial networks. Communications of the ACM, 63(11):139--144, 2020.
[2]
Robert Geirhos, Patricia Rubisch, Claudio Michaelis, Matthias Bethge, Felix A Wichmann, and Wieland Brendel. Imagenet-trained cnns are biased towards texture; increasing shape bias improves accuracy and robustness. arXiv preprint arXiv:1811.12231, 2018.
[3]
Ziwei Liu, Ping Luo, Xiaogang Wang, and Xiaoou Tang. Deep learning face attributes in the wild. In Proceedings of the IEEE international conference on computer vision, pages 3730--3738, 2015.
[4]
Byungju Kim, Hyunwoo Kim, Kyungsu Kim, Sungjin Kim, and Junmo Kim. Learning not to learn: Training deep neural networks with biased data. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9012--9020, 2019.
[5]
Junhyun Nam, Hyuntak Cha, Sungsoo Ahn, Jaeho Lee, and Jinwoo Shin. Learning from failure: De-biasing classifier from biased classifier. Advances in Neural Information Processing Systems, 33:20673--20684, 2020.
[6]
Jungsoo Lee, Eungyeup Kim, Juyoung Lee, Jihyeon Lee, and Jaegul Choo. Learning debiased representation via disentangled feature augmentation. Advances in Neural Information Processing Systems, 34:25123--25133, 2021.
[7]
Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770--778, 2016.
[8]
Dan Hendrycks and Thomas Dietterich. Benchmarking neural network robustness to common corruptions and perturbations. arXiv preprint arXiv:1903.12261, 2019.
[9]
Jaeju An, Taejune Kim, Donggeun Ko, Sangyup Lee, and Simon S Woo. A? 2: Adaptive augmentation for effectively mitigating dataset bias. In Proceedings of the Asian Conference on Computer Vision, pages 4077--4092, 2022.
[10]
Zhilu Zhang and Mert Sabuncu. Generalized cross entropy loss for training deep neural networks with noisy labels. Advances in neural information processing systems, 31, 2018.
[11]
Vikram V Ramaswamy, Sunnie SY Kim, and Olga Russakovsky. Fair attribute classification through latent space de-biasing. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 9301--9310, 2021.
[12]
Tero Karras, Samuli Laine, Miika Aittala, Janne Hellsten, Jaakko Lehtinen, and Timo Aila. Analyzing and improving the image quality of stylegan. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 8110-- 8119, 2020.
[13]
Bingchen Liu, Yizhe Zhu, Kunpeng Song, and Ahmed Elgammal. Towards faster and stabilized gan training for high-fidelity few-shot image synthesis. In International Conference on Learning Representations, 2021.
[14]
Dustin Tran, Rajesh Ranganath, and David Blei. Hierarchical implicit models and likelihood-free variational inference. Advances in Neural Information Processing Systems, 30, 2017.
[15]
Jae Hyun Lim and Jong Chul Ye. Geometric gan. arXiv preprint arXiv:1705.02894, 2017.
[16]
Yi Li and Nuno Vasconcelos. Repair: Removing representation bias by dataset resampling. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 9572--9581, 2019.
[17]
Hyojin Bahng, Sanghyuk Chun, Sangdoo Yun, Jaegul Choo, and Seong Joon Oh. Learning de-biased representations with biased representations. In International Conference on Machine Learning, pages 528--539. PMLR, 2020.
Index Terms
- AmpliBias: Mitigating Dataset Bias through Bias Amplification in Few-shot Learning for Generative Models
Recommendations
A: Adaptive Augmentation for Effectively Mitigating Dataset Bias
Computer Vision – ACCV 2022AbstractRecently, deep neural networks (DNNs) have become the de facto standard to achieve outstanding performances and demonstrate significant impact on various computer vision tasks for real-world scenarios. However, the trained networks can often ...
Making generative classifiers robust to selection bias
KDD '07: Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data miningThis paper presents approaches to semi-supervised learning when the labeled training data and test data are differently distributed. Specifically, the samples selected for labeling are a biased subset of some general distribution and the test set ...
Undoing the damage of dataset bias
ECCV'12: Proceedings of the 12th European conference on Computer Vision - Volume Part IThe presence of bias in existing object recognition datasets is now well-known in the computer vision community. While it remains in question whether creating an unbiased dataset is possible given limited resources, in this work we propose a ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
October 2023
5508 pages
ISBN:9798400701245
DOI:10.1145/3583780
- General Chairs:
- Ingo Frommholz,
- Frank Hopfgartner,
- Mark Lee,
- Michael Oakes,
- Program Chairs:
- Mounia Lalmas,
- Min Zhang,
- Rodrygo Santos
Copyright © 2023 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 the author(s) 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
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 21 October 2023
Check for updates
Author Tags
Qualifiers
- Short-paper
Funding Sources
Conference
CIKM '23: The 32nd ACM International Conference on Information and Knowledge Management
October 21 - 25, 2023
Birmingham, United Kingdom
Acceptance Rates
Overall Acceptance Rate 1,861 of 8,427 submissions, 22%
Upcoming Conference
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 200Total Downloads
- Downloads (Last 12 months)165
- Downloads (Last 6 weeks)15
Reflects downloads up to 25 Nov 2024
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in