Fighting Fire with Fire: Contrastive Debiasing without Bias-free Data via Generative Bias-transformation

Yeonsung Jung, Hajin Shim, June Yong Yang, Eunho Yang

Keywords: debiasing, contrastive learning, image-to-image translation

TL;DR: In this paper, we propose Contrastive Debiasing via Generative Bias-transformation (CDvG) which is capable of operating without exploiting bias labels and bias-free samples explicitly.

Abstract: Despite their remarkable ability to generalize with over-capacity networks, deep neural networks often abuse bias instead of using the actual task-related information for discriminative tasks. Since such shortcuts are only effective within the collected dataset, the resulting biased model underperforms on real-world inputs. To counteract the influence of bias, existing methods either exploit auxiliary information which is rarely obtainable in practice, or sift bias-free samples to exploit them for debiasing. However, such presumptions about the availability of the auxiliary information or bias-free samples are not always guaranteed and the existing methods could break down due to the unmet presumptions. In this paper, we propose Contrastive Debiasing via Generative Bias-transformation (CDvG) which is capable of operating without exploiting bias labels and bias-free samples explicitly. Motivated by our observation that not only discriminative models but also image translation models tend to focus on the easy-to-learn bias, CDvG employs a image translation model to transform the bias to another mode of bias while preserving task-relevant information. Through contrastive learning, we set transformed biased views against another, learning bias-invariant representations. Especially, as the bias has a stronger correlation or is easier to perceive compared to the signal, the translation model is more likely to be a bias translation model, resulting in better debiasing effect. Experimental results demonstrate that CDvG outperforms the state-of-the-arts, especially when bias-free samples are extremely scarce.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning

Community Implementations: [ 3 code implementations](https://www.catalyzex.com/paper/fighting-fire-with-fire-contrastive-debiasing/code)