# Mitigating Test-Time Bias for Fair Image Retrieval

arXiv: https://arxiv.org/abs/2305.19329 · HTML: https://mlsanity.com/paper/2305.19329/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 64 references that are in the map.
- First posted on arXiv 23 May 2023.

## Builds on (most cited first, 30 of 37)

- [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)
- [Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models](https://mlsanity.com/paper/1505.04870/) (2015)
- [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)
- [Certifying and removing disparate impact](https://mlsanity.com/paper/1412.3756/) (2014)
- [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)
- [Women also Snowboard: Overcoming Bias in Captioning Models](https://mlsanity.com/paper/1803.09797/) (2018)
- [Censoring Representations with an Adversary](https://mlsanity.com/paper/1511.05897/) (2015)
- [Debiasing Vision-Language Models via Biased Prompts](https://mlsanity.com/paper/2302.00070/) (2023)
- [ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models](https://mlsanity.com/paper/2204.08790/) (2022)
- [To be Robust or to be Fair: Towards Fairness in Adversarial Training](https://mlsanity.com/paper/2010.06121/) (2020)
- [Fairness in Recommendation Ranking through Pairwise Comparisons](https://mlsanity.com/paper/1903.00780/) (2019)
- [Open Vocabulary Semantic Segmentation with Patch Aligned Contrastive Learning](https://mlsanity.com/paper/2212.04994/) (2022)
- [Understanding and Evaluating Racial Biases in Image Captioning](https://mlsanity.com/paper/2106.08503/) (2021)
- [A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learning](https://mlsanity.com/paper/2203.11933/) (2022)
- [Optimization with Non-Differentiable Constraints with Applications to Fairness, Recall, Churn, and Other Goals](https://mlsanity.com/paper/1809.04198/) (2018)
- [Are Gender-Neutral Queries Really Gender-Neutral? Mitigating Gender Bias in Image Search](https://mlsanity.com/paper/2109.05433/) (2021)
- [FairFil: Contrastive Neural Debiasing Method for Pretrained Text Encoders](https://mlsanity.com/paper/2103.06413/) (2021)
- [Controlling Fairness and Bias in Dynamic Learning-to-Rank](https://mlsanity.com/paper/2005.14713/) (2020)
- [Image-text Retrieval: A Survey on Recent Research and Development](https://mlsanity.com/paper/2203.14713/) (2022)
- [Exposing and Mitigating Spurious Correlations for Cross-Modal Retrieval](https://mlsanity.com/paper/2304.03391/) (2023)
- [Assessing Multilingual Fairness in Pre-trained Multimodal Representations](https://mlsanity.com/paper/2106.06683/) (2021)
- [Fairness for Image Generation with Uncertain Sensitive Attributes](https://mlsanity.com/paper/2106.12182/) (2021)

## Built on by (most cited first, 20 of 20)

- [VisoGender: A dataset for benchmarking gender bias in image-text pronoun resolution](https://mlsanity.com/paper/2306.12424/) (2023)
- [On the Challenges and Opportunities in Generative AI](https://mlsanity.com/paper/2403.00025/) (2024)
- [Towards Trustworthy Retrieval Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2502.06872/) (2025)
- [Joint Vision-Language Social Bias Removal for CLIP](https://mlsanity.com/paper/2411.12785/) (2024)
- [BendVLM: Test-Time Debiasing of Vision-Language Embeddings](https://mlsanity.com/paper/2411.04420/) (2024)
- [Fairness and Bias Mitigation in Computer Vision: A Survey](https://mlsanity.com/paper/2408.02464/) (2024)
- [A Systematic Survey of Prompt Engineering on Vision-Language Foundation Models](https://mlsanity.com/paper/2307.12980/) (2023)
- [Organizing Unstructured Image Collections using Natural Language](https://mlsanity.com/paper/2410.05217/) (2024)
- [Bias Is a Subspace, Not a Coordinate: A Geometric Rethinking of Post-hoc Debiasing in Vision-Language Models](https://mlsanity.com/paper/2511.18123/) (2025)
- [Biases Propagate in Encoder-based Vision-Language Models: A Systematic Analysis From Intrinsic Measures to Zero-shot Retrieval Outcomes](https://mlsanity.com/paper/2506.06506/) (2025)
- [Interpretable Debiasing of Vision-Language Models for Social Fairness](https://mlsanity.com/paper/2602.24014/) (2026)
- [ASPIRE: Language-Guided Data Augmentation for Improving Robustness Against Spurious Correlations](https://mlsanity.com/paper/2308.10103/) (2023)
- [Is It Bad to Work All the Time? Cross-Cultural Evaluation of Social Norm Biases in GPT-4](https://mlsanity.com/paper/2505.18322/) (2025)
- [Negation-Aware Test-Time Adaptation for Vision-Language Models](https://mlsanity.com/paper/2507.19064/) (2025)
- [Mutual Learning for Hashing: Unlocking Strong Hash Functions from Weak Supervision](https://mlsanity.com/paper/2510.07703/) (2025)
- [Multi-Group Proportional Representation in Retrieval](https://mlsanity.com/paper/2407.08571/) (2024)
- [UFD-PRiME: Unsupervised Joint Learning of Optical Flow and Stereo Depth through Pixel-Level Rigid Motion Estimation](https://mlsanity.com/paper/2310.04712/) (2023)
- [A Note on Bias to Complete](https://mlsanity.com/paper/2402.11710/) (2024)
- [UniHash: Unifying Pointwise and Pairwise Hashing Paradigms](https://mlsanity.com/paper/2601.09828/) (2026)
- [ViD: Vision-Dominant Gender Bias Mitigation for Large Vision-Language Models](https://mlsanity.com/paper/2609.16647/) (2026)

## Abstract (arXiv)

We address the challenge of generating fair and unbiased image retrieval results given neutral textual queries (with no explicit gender or race connotations), while maintaining the utility (performance) of the underlying vision-language (VL) model. Previous methods aim to disentangle learned representations of images and text queries from gender and racial characteristics. However, we show these are inadequate at alleviating bias for the desired equal representation result, as there usually exists test-time bias in the target retrieval set. So motivated, we introduce a straightforward technique, Post-hoc Bias Mitigation (PBM), that post-processes the outputs from the pre-trained vision-language model. We evaluate our algorithm on real-world image search datasets, Occupation 1 and 2, as well as two large-scale image-text datasets, MS-COCO and Flickr30k. Our approach achieves the lowest bias, compared with various existing bias-mitigation methods, in text-based image retrieval result while maintaining satisfactory retrieval performance. The source code is publicly available at urlhttps://anonymous.4open.science/r/FairTextbasedImageRetrieval-D8B2.