Research map / Label-efficient and robust learning / Recognition and long-tail
Learning Not to Learn: Training Deep Neural Networks With Biased Data
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Apply mutual-information regularization to remove color bias | Colored MNIST classifier · Colored MNIST Test-σ² | accuracy | Helped |
| Apply mutual-information regularization to remove color bias | Dogs and Cats classifier trained on TB1 · Dogs and Cats Test | accuracy: .9254 -> .9638 | Helped |
| Apply mutual-information regularization to remove color bias | Dogs and Cats classifier trained on TB2 · Dogs and Cats Test | accuracy: .8524 -> .9376 | Helped |
| Add gradient reversal to mutual-information regularization (ablation) | Dogs and Cats classifier trained on TB1 · Dogs and Cats Test | accuracy: .9594 -> .9638 | Helped |
| Add gradient reversal to mutual-information regularization (ablation) | Dogs and Cats classifier trained on TB2 · Dogs and Cats Test | accuracy: .9298 -> .9376 | Helped |
| Remove mutual-information regularization while retaining gradient reversal (ablation) | Dogs and Cats classifier trained on TB1 · Dogs and Cats Test | accuracy: .9582 -> .9638 | Hurt |
| Remove mutual-information regularization while retaining gradient reversal (ablation) | Dogs and Cats classifier trained on TB2 · Dogs and Cats Test | accuracy: .9291 -> .9376 | Hurt |
| Apply mutual-information regularization to remove age bias while learning gender | IMDB Face classifier trained on EB1 · IMDB Face Test | accuracy: .8442 -> .8666 | Helped |
| Apply mutual-information regularization to remove age bias while learning gender | IMDB Face classifier trained on EB2 · IMDB Face Test | accuracy: .6975 -> .7450 | Helped |
| Apply mutual-information regularization to remove gender bias while learning age | IMDB Face classifier trained on EB1 · IMDB Face Test | accuracy: .7717 -> .7743 | Helped |
| Apply mutual-information regularization to remove gender bias while learning age | IMDB Face classifier trained on EB2 · IMDB Face Test | accuracy: .6197 -> .6304 | Helped |
| Apply mutual-information regularization to remove gender bias while learning age | IMDB Face classifier trained on EB1 · IMDB Face EB2 | accuracy: .6680 -> .6527 | Hurt |
Closest papers by meaning
- Self-supervised Debiasing Using Low Rank Regularization (CVPR 2024 · similarity 0.86)
- Feature Averaging: An Implicit Bias of Gradient Descent Leading to Non-Robustness in Neural Networks (ICLR 2025 · similarity 0.86)
- Estimating Implicit Regularization in Deep Learning (NeurIPS 2026 · similarity 0.85)
- Initial Guessing Bias: How Untrained Networks Favor Some Classes (ICML 2024 · similarity 0.85)
- Enhancing Intrinsic Features for Debiasing via Investigating Class-Discerning Common Attributes in Bias-Contrastive Pair (CVPR 2024 · similarity 0.85)
- Simplicity Bias in Overparameterized Machine Learning (AAAI 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.