# Classifier-to-Bias: Toward Unsupervised Automatic Bias Detection for Visual Classifiers

arXiv: https://arxiv.org/abs/2504.20902 · HTML: https://mlsanity.com/paper/2504.20902/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 58 of its 70 references that are in the map.
- First posted on arXiv 29 Apr 2025.

## Builds on (most cited first, 30 of 58)

- [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)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts](https://mlsanity.com/paper/2102.08981/) (2021)
- [Model Cards for Model Reporting](https://mlsanity.com/paper/1810.03993/) (2018)
- [Gemma: Open Models Based on Gemini Research and Technology](https://mlsanity.com/paper/2403.08295/) (2024)
- [Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models](https://mlsanity.com/paper/2309.01219/) (2023)
- [DataComp: In search of the next generation of multimodal datasets](https://mlsanity.com/paper/2304.14108/) (2023)
- [Bias and Fairness in Large Language Models: A Survey](https://mlsanity.com/paper/2309.00770/) (2023)
- [Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality](https://mlsanity.com/paper/2204.03162/) (2022)
- [Just Train Twice: Improving Group Robustness without Training Group Information](https://mlsanity.com/paper/2107.09044/) (2021)
- [Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints](https://mlsanity.com/paper/1707.09457/) (2017)
- [SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionality](https://mlsanity.com/paper/2306.14610/) (2023)
- [Women also Snowboard: Overcoming Bias in Captioning Models](https://mlsanity.com/paper/1803.09797/) (2018)
- [No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification Problems](https://mlsanity.com/paper/2011.12945/) (2020)
- [Domino: Discovering Systematic Errors with Cross-Modal Embeddings](https://mlsanity.com/paper/2203.14960/) (2022)
- [REVISE: A Tool for Measuring and Mitigating Bias in Visual Datasets](https://mlsanity.com/paper/2004.07999/) (2020)
- [Revisiting Weakly Supervised Pre-Training of Visual Perception Models](https://mlsanity.com/paper/2201.08371/) (2022)

## Built on by (most cited first, 4 of 4)

- [Processing and acquisition traces in visual encoders: What does CLIP know about your camera?](https://mlsanity.com/paper/2508.10637/) (2025)
- [SEM: Sparse Embedding Modulation for Post-Hoc Debiasing of Vision-Language Models](https://mlsanity.com/paper/2603.19028/) (2026)
- [StylisticBias: A Few Human Visual Cues Drive Most Social Biases in MLLMs](https://mlsanity.com/paper/2606.20527/) (2026)
- [GH-ESD: Grounded Hypothesis-Driven Error Slice Discovery for Instance-Level Vision Tasks](https://mlsanity.com/paper/2512.24592/) (2025)

## Abstract (arXiv)

A person downloading a pre-trained model from the web should be aware of its biases. Existing approaches for bias identification rely on datasets containing labels for the task of interest, something that a non-expert may not have access to, or may not have the necessary resources to collect: this greatly limits the number of tasks where model biases can be identified. In this work, we present Classifier-to-Bias (C2B), the first bias discovery framework that works without access to any labeled data: it only relies on a textual description of the classification task to identify biases in the target classification model. This description is fed to a large language model to generate bias proposals and corresponding captions depicting biases together with task-specific target labels. A retrieval model collects images for those captions, which are then used to assess the accuracy of the model w.r.t. the given biases. C2B is training-free, does not require any annotations, has no constraints on the list of biases, and can be applied to any pre-trained model on any classification task. Experiments on two publicly available datasets show that C2B discovers biases beyond those of the original datasets and outperforms a recent state-of-the-art bias detection baseline that relies on task-specific annotations, being a promising first step toward addressing task-agnostic unsupervised bias detection.