# Are Gender-Neutral Queries Really Gender-Neutral? Mitigating Gender Bias in Image Search

arXiv: https://arxiv.org/abs/2109.05433 · HTML: https://mlsanity.com/paper/2109.05433/

## Key facts

- Cited by 90 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 51 references that are in the map.
- First posted on arXiv 12 Sep 2021.

## Builds on (most cited first, 30 of 35)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [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)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Microsoft COCO Captions: Data Collection and Evaluation Server](https://mlsanity.com/paper/1504.00325/) (2015)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Deep Visual-Semantic Alignments for Generating Image Descriptions](https://mlsanity.com/paper/1412.2306/) (2014)
- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [Counterfactual Fairness](https://mlsanity.com/paper/1703.06856/) (2017)
- [Learning Representations by Maximizing Mutual Information Across Views](https://mlsanity.com/paper/1906.00910/) (2019)
- [Certifying and removing disparate impact](https://mlsanity.com/paper/1412.3756/) (2014)
- [Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods](https://mlsanity.com/paper/1804.06876/) (2018)
- [A Reductions Approach to Fair Classification](https://mlsanity.com/paper/1803.02453/) (2018)
- [Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints](https://mlsanity.com/paper/1707.09457/) (2017)
- [Stacked Cross Attention for Image-Text Matching](https://mlsanity.com/paper/1803.08024/) (2018)
- [Keystroke Dynamics as Part of Lifelogging](https://mlsanity.com/paper/2010.10144/) (2020)
- [Large-Scale Adversarial Training for Vision-and-Language Representation Learning](https://mlsanity.com/paper/2006.06195/) (2020)
- [Women also Snowboard: Overcoming Bias in Captioning Models](https://mlsanity.com/paper/1803.09797/) (2018)
- [Learning Fine-grained Image Similarity with Deep Ranking](https://mlsanity.com/paper/1404.4661/) (2014)
- [Black is to Criminal as Caucasian is to Police: Detecting and Removing Multiclass Bias in Word Embeddings](https://mlsanity.com/paper/1904.04047/) (2019)
- [Inherent Tradeoffs in Learning Fair Representations](https://mlsanity.com/paper/1906.08386/) (2019)
- [Fairness in Recommendation Ranking through Pairwise Comparisons](https://mlsanity.com/paper/1903.00780/) (2019)
- [Equity of Attention: Amortizing Individual Fairness in Rankings](https://mlsanity.com/paper/1805.01788/) (2018)
- [Image Representations Learned With Unsupervised Pre-Training Contain Human-like Biases](https://mlsanity.com/paper/2010.15052/) (2020)
- [Optimization with Non-Differentiable Constraints with Applications to Fairness, Recall, Churn, and Other Goals](https://mlsanity.com/paper/1809.04198/) (2018)
- [Controlling Fairness and Bias in Dynamic Learning-to-Rank](https://mlsanity.com/paper/2005.14713/) (2020)
- [Mitigating Gender Bias in Captioning Systems](https://mlsanity.com/paper/2006.08315/) (2020)
- [Instance-aware Image and Sentence Matching with Selective Multimodal LSTM](https://mlsanity.com/paper/1611.05588/) (2016)

## Built on by (most cited first, 30 of 90)

- [Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale](https://mlsanity.com/paper/2211.03759/) (2022)
- [DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models](https://mlsanity.com/paper/2202.04053/) (2022)
- [What does CLIP know about a red circle? Visual prompt engineering for VLMs](https://mlsanity.com/paper/2304.06712/) (2023)
- [Debiasing Vision-Language Models via Biased Prompts](https://mlsanity.com/paper/2302.00070/) (2023)
- [A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learning](https://mlsanity.com/paper/2203.11933/) (2022)
- [DeAR: Debiasing Vision-Language Models with Additive Residuals](https://mlsanity.com/paper/2303.10431/) (2023)
- [Examining Gender and Racial Bias in Large Vision-Language Models Using a Novel Dataset of Parallel Images](https://mlsanity.com/paper/2402.05779/) (2024)
- [SocialCounterfactuals: Probing and Mitigating Intersectional Social Biases in Vision-Language Models with Counterfactual Examples](https://mlsanity.com/paper/2312.00825/) (2023)
- [Uncurated Image-Text Datasets: Shedding Light on Demographic Bias](https://mlsanity.com/paper/2304.02828/) (2023)
- [VisoGender: A dataset for benchmarking gender bias in image-text pronoun resolution](https://mlsanity.com/paper/2306.12424/) (2023)
- [Discover and Mitigate Unknown Biases with Debiasing Alternate Networks](https://mlsanity.com/paper/2207.10077/) (2022)
- [Contrastive Language-Vision AI Models Pretrained on Web-Scraped Multimodal Data Exhibit Sexual Objectification Bias](https://mlsanity.com/paper/2212.11261/) (2022)
- [American == White in Multimodal Language-and-Image AI](https://mlsanity.com/paper/2207.00691/) (2022)
- [T2IAT: Measuring Valence and Stereotypical Biases in Text-to-Image Generation](https://mlsanity.com/paper/2306.00905/) (2023)
- [Gender Artifacts in Visual Datasets](https://mlsanity.com/paper/2206.09191/) (2022)
- [Exposing and Mitigating Spurious Correlations for Cross-Modal Retrieval](https://mlsanity.com/paper/2304.03391/) (2023)
- [CLIP the Bias: How Useful is Balancing Data in Multimodal Learning?](https://mlsanity.com/paper/2403.04547/) (2024)
- [Evidence for Hypodescent in Visual Semantic AI](https://mlsanity.com/paper/2205.10764/) (2022)
- [Markedness in Visual Semantic AI](https://mlsanity.com/paper/2205.11378/) (2022)
- [Exploiting Cultural Biases via Homoglyphs in Text-to-Image Synthesis](https://mlsanity.com/paper/2209.08891/) (2022)
- [The Rich Get Richer: Disparate Impact of Semi-Supervised Learning](https://mlsanity.com/paper/2110.06282/) (2021)
- [Addressing Fairness Issues in Deep Learning-Based Medical Image Analysis: A Systematic Review](https://mlsanity.com/paper/2209.13177/) (2022)
- [Balancing the Picture: Debiasing Vision-Language Datasets with Synthetic Contrast Sets](https://mlsanity.com/paper/2305.15407/) (2023)
- [Identifying Implicit Social Biases in Vision-Language Models](https://mlsanity.com/paper/2411.00997/) (2024)
- [Survey of Social Bias in Vision-Language Models](https://mlsanity.com/paper/2309.14381/) (2023)
- [Unmasking and Improving Data Credibility: A Study with Datasets for Training Harmless Language Models](https://mlsanity.com/paper/2311.11202/) (2023)
- [VLBiasBench: A Comprehensive Benchmark for Evaluating Bias in Large Vision-Language Model](https://mlsanity.com/paper/2406.14194/) (2024)
- [FairerCLIP: Debiasing CLIP's Zero-Shot Predictions using Functions in RKHSs](https://mlsanity.com/paper/2403.15593/) (2024)
- [MPCHAT: Towards Multimodal Persona-Grounded Conversation](https://mlsanity.com/paper/2305.17388/) (2023)
- [Zero-Shot Robustification of Zero-Shot Models](https://mlsanity.com/paper/2309.04344/) (2023)

## Abstract (arXiv)

Internet search affects people's cognition of the world, so mitigating biases in search results and learning fair models is imperative for social good. We study a unique gender bias in image search in this work: the search images are often gender-imbalanced for gender-neutral natural language queries. We diagnose two typical image search models, the specialized model trained on in-domain datasets and the generalized representation model pre-trained on massive image and text data across the internet. Both models suffer from severe gender bias. Therefore, we introduce two novel debiasing approaches: an in-processing fair sampling method to address the gender imbalance issue for training models, and a post-processing feature clipping method base on mutual information to debias multimodal representations of pre-trained models. Extensive experiments on MS-COCO and Flickr30K benchmarks show that our methods significantly reduce the gender bias in image search models.