# Variation of Gender Biases in Visual Recognition Models Before and After Finetuning

arXiv: https://arxiv.org/abs/2303.07615 · HTML: https://mlsanity.com/paper/2303.07615/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 43 references that are in the map.
- First posted on arXiv 14 Mar 2023.

## Builds on (most cited first, 30 of 34)

- [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)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Big Transfer (BiT): General Visual Representation Learning](https://mlsanity.com/paper/1912.11370/) (2019)
- [The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale](https://mlsanity.com/paper/1811.00982/) (2018)
- [Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints](https://mlsanity.com/paper/1707.09457/) (2017)
- [Multimodal datasets: misogyny, pornography, and malignant stereotypes](https://mlsanity.com/paper/2110.01963/) (2021)
- [Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation](https://mlsanity.com/paper/1911.11834/) (2019)
- [Large image datasets: A pyrrhic win for computer vision?](https://mlsanity.com/paper/2006.16923/) (2020)
- [Women also Snowboard: Overcoming Bias in Captioning Models](https://mlsanity.com/paper/1803.09797/) (2018)
- [Towards Fairer Datasets: Filtering and Balancing the Distribution of the People Subtree in the ImageNet Hierarchy](https://mlsanity.com/paper/1912.07726/) (2019)
- [Does Object Recognition Work for Everyone?](https://mlsanity.com/paper/1906.02659/) (2019)
- [REVISE: A Tool for Measuring and Mitigating Bias in Visual Datasets](https://mlsanity.com/paper/2004.07999/) (2020)
- [Why Can't I Dance in the Mall? Learning to Mitigate Scene Bias in Action Recognition](https://mlsanity.com/paper/1912.05534/) (2019)
- [Understanding and Evaluating Racial Biases in Image Captioning](https://mlsanity.com/paper/2106.08503/) (2021)
- [Image Representations Learned With Unsupervised Pre-Training Contain Human-like Biases](https://mlsanity.com/paper/2010.15052/) (2020)
- [Don't Judge an Object by Its Context: Learning to Overcome Contextual Bias](https://mlsanity.com/paper/2001.03152/) (2020)
- [Predictive Inequity in Object Detection](https://mlsanity.com/paper/1902.11097/) (2019)
- [Towards causal benchmarking of bias in face analysis algorithms](https://mlsanity.com/paper/2007.06570/) (2020)
- [Directional Bias Amplification](https://mlsanity.com/paper/2102.12594/) (2021)
- [A Moral Framework for Understanding of Fair ML through Economic Models of Equality of Opportunity](https://mlsanity.com/paper/1809.03400/) (2018)
- [Gender Artifacts in Visual Datasets](https://mlsanity.com/paper/2206.09191/) (2022)
- [Quantifying Societal Bias Amplification in Image Captioning](https://mlsanity.com/paper/2203.15395/) (2022)
- [InsideBias: Measuring Bias in Deep Networks and Application to Face Gender Biometrics](https://mlsanity.com/paper/2004.06592/) (2020)
- [When does Bias Transfer in Transfer Learning?](https://mlsanity.com/paper/2207.02842/) (2022)

## Built on by (most cited first, 3 of 3)

- [Fairness and Bias Mitigation in Computer Vision: A Survey](https://mlsanity.com/paper/2408.02464/) (2024)
- [Adventures of Trustworthy Vision-Language Models: A Survey](https://mlsanity.com/paper/2312.04231/) (2023)
- [Context Matters: Vision-Based Depression Detection Comparing Classical and Deep Approaches](https://mlsanity.com/paper/2604.10344/) (2026)

## Abstract (arXiv)

We introduce a framework to measure how biases change before and after fine-tuning a large scale visual recognition model for a downstream task. Deep learning models trained on increasing amounts of data are known to encode societal biases. Many computer vision systems today rely on models typically pretrained on large scale datasets. While bias mitigation techniques have been developed for tuning models for downstream tasks, it is currently unclear what are the effects of biases already encoded in a pretrained model. Our framework incorporates sets of canonical images representing individual and pairs of concepts to highlight changes in biases for an array of off-the-shelf pretrained models across model sizes, dataset sizes, and training objectives. Through our analyses, we find that (1) supervised models trained on datasets such as ImageNet-21k are more likely to retain their pretraining biases regardless of the target dataset compared to self-supervised models. We also find that (2) models finetuned on larger scale datasets are more likely to introduce new biased associations. Our results also suggest that (3) biases can transfer to finetuned models and the finetuning objective and dataset can impact the extent of transferred biases.