mlsanityData to 7 Oct 2026

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

arXiv 2109.05433 ↗First posted 12 Sep 2021cs.CV cs.CLcited by 90

Not on the map. Why?

Cited by 42 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

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.

Key facts. Cited by 90 papers in the map (data through 7 Oct 2026). Builds on 35 of its 51 references that are in the map. First posted on arXiv 12 Sep 2021.

Builds on

35 of 51 references.

References · 35

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  6. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  7. 2015Microsoft COCO Captions: Data Collection and Evaluation Servercited by 1,447
  8. 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,304
  9. 2014Deep Visual-Semantic Alignments for Generating Image Descriptionscited by 966
  10. 2016Semantics derived automatically from language corpora contain human-like biasescited by 894
  11. 2017Counterfactual Fairnesscited by 802
  12. 2019Learning Representations by Maximizing Mutual Information Across Viewscited by 733
23 more
  1. 2014Certifying and removing disparate impactcited by 715
  2. 2018Gender Bias in Coreference Resolution: Evaluation and Debiasing Methodscited by 657
  3. 2018A Reductions Approach to Fair Classificationcited by 585
  4. 2017Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraintscited by 420
  5. 2018Stacked Cross Attention for Image-Text Matchingcited by 414
  6. 2020Keystroke Dynamics as Part of Lifeloggingcited by 334
  7. 2020Large-Scale Adversarial Training for Vision-and-Language Representation Learningcited by 327
  8. 2018Women also Snowboard: Overcoming Bias in Captioning Modelscited by 236
  9. 2014Learning Fine-grained Image Similarity with Deep Rankingcited by 189
  10. 2019Black is to Criminal as Caucasian is to Police: Detecting and Removing Multiclass Bias in Word Embeddingscited by 146
  11. 2019Inherent Tradeoffs in Learning Fair Representationscited by 144
  12. 2019Fairness in Recommendation Ranking through Pairwise Comparisonscited by 127
  13. 2018Equity of Attention: Amortizing Individual Fairness in Rankingscited by 124
  14. 2020Image Representations Learned With Unsupervised Pre-Training Contain Human-like Biasescited by 107
  15. 2018Optimization with Non-Differentiable Constraints with Applications to Fairness, Recall, Churn, and Other Goalscited by 103
  16. 2020Controlling Fairness and Bias in Dynamic Learning-to-Rankcited by 67
  17. 2020Mitigating Gender Bias in Captioning Systemscited by 50
  18. 2016Instance-aware Image and Sentence Matching with Selective Multimodal LSTMcited by 43
  19. 2018Explicit Bias Discovery in Visual Question Answering Modelscited by 42
  20. 2017Estimating Mutual Information for Discrete-Continuous Mixturescited by 34
  21. 2020Adaptive Offline Quintuplet Loss for Image-Text Matchingcited by 26
  22. 2019Female Librarians and Male Computer Programmers? Gender Bias in Occupational Images on Digital Media Platformscited by 13
  23. 2015Fairness Constraints: Mechanisms for Fair Classificationcited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 16; 2023: 18; 2024: 31; 2025: 14; 2026: 10.

90 papers.

Sort:

By area:

  1. 2022Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scalecited by 262
  2. 2022DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Modelscited by 230
  3. 2023What does CLIP know about a red circle? Visual prompt engineering for VLMscited by 215
  4. 2023Debiasing Vision-Language Models via Biased Promptscited by 147
  5. 2022A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learningcited by 104
  6. 2023DeAR: Debiasing Vision-Language Models with Additive Residualscited by 70
  7. 2024Examining Gender and Racial Bias in Large Vision-Language Models Using a Novel Dataset of Parallel Imagescited by 55
  8. 2023SocialCounterfactuals: Probing and Mitigating Intersectional Social Biases in Vision-Language Models with Counterfactual Examplescited by 53
  9. 2023VisoGender: A dataset for benchmarking gender bias in image-text pronoun resolutioncited by 52
  10. 2023Uncurated Image-Text Datasets: Shedding Light on Demographic Biascited by 51
  11. 2022Discover and Mitigate Unknown Biases with Debiasing Alternate Networkscited by 47
  12. 2022Contrastive Language-Vision AI Models Pretrained on Web-Scraped Multimodal Data Exhibit Sexual Objectification Biascited by 43
38 more
  1. 2022American == White in Multimodal Language-and-Image AIcited by 39
  2. 2023T2IAT: Measuring Valence and Stereotypical Biases in Text-to-Image Generationcited by 39
  3. 2022Gender Artifacts in Visual Datasetscited by 38
  4. 2023Exposing and Mitigating Spurious Correlations for Cross-Modal Retrievalcited by 35
  5. 2024CLIP the Bias: How Useful is Balancing Data in Multimodal Learning?cited by 35
  6. 2022Evidence for Hypodescent in Visual Semantic AIcited by 30
  7. 2022Markedness in Visual Semantic AIcited by 29
  8. 2022Exploiting Cultural Biases via Homoglyphs in Text-to-Image Synthesiscited by 29
  9. 2021The Rich Get Richer: Disparate Impact of Semi-Supervised Learningcited by 28
  10. 2022Addressing Fairness Issues in Deep Learning-Based Medical Image Analysis: A Systematic Reviewcited by 27
  11. 2023Balancing the Picture: Debiasing Vision-Language Datasets with Synthetic Contrast Setscited by 27
  12. 2024Identifying Implicit Social Biases in Vision-Language Modelscited by 27
  13. 2023Survey of Social Bias in Vision-Language Modelscited by 26
  14. 2023Unmasking and Improving Data Credibility: A Study with Datasets for Training Harmless Language Modelscited by 26
  15. 2024VLBiasBench: A Comprehensive Benchmark for Evaluating Bias in Large Vision-Language Modelcited by 26
  16. 2024FairerCLIP: Debiasing CLIP's Zero-Shot Predictions using Functions in RKHSscited by 25
  17. 2023MPCHAT: Towards Multimodal Persona-Grounded Conversationcited by 24
  18. 2023Zero-Shot Robustification of Zero-Shot Modelscited by 24
  19. 2023MultiModal Bias: Introducing a Framework for Stereotypical Bias Assessment beyond Gender and Race in Vision Language Modelscited by 23
  20. 2022Debiasing Methods for Fairer Neural Models in Vision and Language Research: A Surveycited by 22
  21. 2022FairCLIP: Social Bias Elimination based on Attribute Prototype Learning and Representation Neutralizationcited by 20
  22. 2023Mitigating Test-Time Bias for Fair Image Retrievalcited by 20
  23. 2024Fairness and Bias in Multimodal AI: A Surveycited by 19
  24. 2024SANER: Annotation-free Societal Attribute Neutralizer for Debiasing CLIPcited by 19
  25. 2024A Unified Debiasing Approach for Vision-Language Models across Modalities and Taskscited by 18
  26. 2022DialogCC: An Automated Pipeline for Creating High-Quality Multi-Modal Dialogue Datasetcited by 17
  27. 2024BendVLM: Test-Time Debiasing of Vision-Language Embeddingscited by 17
  28. 2024Joint Vision-Language Social Bias Removal for CLIPcited by 17
  29. 2023Parrot Captions Teach CLIP to Spot Textcited by 16
  30. 2022Contrastive Visual Semantic Pretraining Magnifies the Semantics of Natural Language Representationscited by 14
  31. 2025Debiasing Multimodal Large Language Models via Noise-Aware Preference Optimizationcited by 14
  32. 2023Evaluating the Fairness of Discriminative Foundation Models in Computer Visioncited by 12
  33. 2024Fairness and Bias Mitigation in Computer Vision: A Surveycited by 12
  34. 2024Controllable Prompt Tuning For Balancing Group Distributional Robustnesscited by 10
  35. 2024Social Perception of Faces in a Vision-Language Modelcited by 10
  36. 2025BBQ-V: Benchmarking Visual Stereotype Bias in Large Multimodal Modelscited by 10
  37. 2024Enhancing Domain Adaptation through Prompt Gradient Alignmentcited by 8
  38. 2024Stark: Social Long-Term Multi-Modal Conversation with Persona Commonsense Knowledgecited by 8

50 most cited of 90 All 90 (JSON)