# Common-Sense Bias Modeling for Classification Tasks

arXiv: https://arxiv.org/abs/2401.13213 · HTML: https://mlsanity.com/paper/2401.13213/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 52 references that are in the map.
- First posted on arXiv 24 Jan 2024.

## Builds on (most cited first, 30 of 39)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [Microsoft COCO Captions: Data Collection and Evaluation Server](https://mlsanity.com/paper/1504.00325/) (2015)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [SPICE: Semantic Propositional Image Caption Evaluation](https://mlsanity.com/paper/1607.08822/) (2016)
- [Just Train Twice: Improving Group Robustness without Training Group Information](https://mlsanity.com/paper/2107.09044/) (2021)
- [Universal Sentence Encoder](https://mlsanity.com/paper/1803.11175/) (2018)
- [Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints](https://mlsanity.com/paper/1707.09457/) (2017)
- [Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation](https://mlsanity.com/paper/1911.11834/) (2019)
- [A Survey of Human-in-the-loop for Machine Learning](https://mlsanity.com/paper/2108.00941/) (2021)
- [No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification Problems](https://mlsanity.com/paper/2011.12945/) (2020)
- [Correct-N-Contrast: A Contrastive Approach for Improving Robustness to Spurious Correlations](https://mlsanity.com/paper/2203.01517/) (2022)
- [Fair Attribute Classification through Latent Space De-biasing](https://mlsanity.com/paper/2012.01469/) (2020)
- [Talk-to-Edit: Fine-Grained Facial Editing via Dialog](https://mlsanity.com/paper/2109.04425/) (2021)
- [Don't Judge an Object by Its Context: Learning to Overcome Contextual Bias](https://mlsanity.com/paper/2001.03152/) (2020)
- [Fair Contrastive Learning for Facial Attribute Classification](https://mlsanity.com/paper/2203.16209/) (2022)
- [Discover and Cure: Concept-aware Mitigation of Spurious Correlation](https://mlsanity.com/paper/2305.00650/) (2023)
- [BiaSwap: Removing dataset bias with bias-tailored swapping augmentation](https://mlsanity.com/paper/2108.10008/) (2021)
- [Seeing through the Human Reporting Bias: Visual Classifiers from Noisy Human-Centric Labels](https://mlsanity.com/paper/1512.06974/) (2015)
- [Diagnosing and Rectifying Vision Models using Language](https://mlsanity.com/paper/2302.04269/) (2023)
- [Detecting Shortcut Learning for Fair Medical AI using Shortcut Testing](https://mlsanity.com/paper/2207.10384/) (2022)
- [Discover and Mitigate Unknown Biases with Debiasing Alternate Networks](https://mlsanity.com/paper/2207.10077/) (2022)
- [Discover the Unknown Biased Attribute of an Image Classifier](https://mlsanity.com/paper/2104.14556/) (2021)
- [Unsupervised Learning of Debiased Representations with Pseudo-Attributes](https://mlsanity.com/paper/2108.02943/) (2021)
- [Inspecting the Geographical Representativeness of Images from Text-to-Image Models](https://mlsanity.com/paper/2305.11080/) (2023)
- [Explicit Bias Discovery in Visual Question Answering Models](https://mlsanity.com/paper/1811.07789/) (2018)

## Built on by (most cited first, 1 of 1)

- [Configurable Fairness: Direct Optimization of Parity Metrics via Vision-Language Models](https://mlsanity.com/paper/2403.10624/) (2024)

## Abstract (arXiv)

Machine learning model bias can arise from dataset composition: correlated sensitive features can distort the downstream classification model's decision boundary and lead to performance differences along these features. Existing de-biasing works tackle the most prominent bias features, such as colors of digits or background of animals. However, real-world datasets often include a large number of feature correlations that intrinsically manifest in the data as common sense information. Such spurious visual cues can further reduce model robustness. Thus, domain practitioners desire a comprehensive understanding of correlations and the flexibility to address relevant biases. To this end, we propose a novel framework to extract comprehensive biases in image datasets based on textual descriptions, a common sense-rich modality. Specifically, features are constructed by clustering noun phrase embeddings with similar semantics. The presence of each feature across the dataset is inferred, and their co-occurrence statistics are measured, with spurious correlations optionally examined by a human-in-the-loop module. Downstream experiments show that our method uncovers novel model biases in multiple image benchmark datasets. Furthermore, the discovered bias can be mitigated by simple data re-weighting to de-correlate the features, outperforming state-of-the-art unsupervised bias mitigation methods.