# FairCLIP: Social Bias Elimination based on Attribute Prototype Learning and Representation Neutralization

arXiv: https://arxiv.org/abs/2210.14562 · HTML: https://mlsanity.com/paper/2210.14562/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 32 references that are in the map.
- First posted on arXiv 26 Oct 2022.

## Builds on (most cited first, 27 of 27)

- [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)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs](https://mlsanity.com/paper/2111.02114/) (2021)
- [Conditional Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2203.05557/) (2022)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks](https://mlsanity.com/paper/2004.06165/) (2020)
- [CLIP-Adapter: Better Vision-Language Models with Feature Adapters](https://mlsanity.com/paper/2110.04544/) (2021)
- [ClipCap: CLIP Prefix for Image Captioning](https://mlsanity.com/paper/2111.09734/) (2021)
- [Age Progression/Regression by Conditional Adversarial Autoencoder](https://mlsanity.com/paper/1702.08423/) (2017)
- [How Much Can CLIP Benefit Vision-and-Language Tasks?](https://mlsanity.com/paper/2107.06383/) (2021)
- [Learning to Prompt for Open-Vocabulary Object Detection with Vision-Language Model](https://mlsanity.com/paper/2203.14940/) (2022)
- [Fairness-Aware Ranking in Search & Recommendation Systems with Application to LinkedIn Talent Search](https://mlsanity.com/paper/1905.01989/) (2019)
- [Evaluating CLIP: Towards Characterization of Broader Capabilities and Downstream Implications](https://mlsanity.com/paper/2108.02818/) (2021)
- [Image Representations Learned With Unsupervised Pre-Training Contain Human-like Biases](https://mlsanity.com/paper/2010.15052/) (2020)
- [A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learning](https://mlsanity.com/paper/2203.11933/) (2022)
- [An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models](https://mlsanity.com/paper/2110.08527/) (2021)
- [Are Gender-Neutral Queries Really Gender-Neutral? Mitigating Gender Bias in Image Search](https://mlsanity.com/paper/2109.05433/) (2021)
- [Enabling Multimodal Generation on CLIP via Vision-Language Knowledge Distillation](https://mlsanity.com/paper/2203.06386/) (2022)
- [CLIP-GEN: Language-Free Training of a Text-to-Image Generator with CLIP](https://mlsanity.com/paper/2203.00386/) (2022)
- [DeVLBert: Learning Deconfounded Visio-Linguistic Representations](https://mlsanity.com/paper/2008.06884/) (2020)
- [Assessing Multilingual Fairness in Pre-trained Multimodal Representations](https://mlsanity.com/paper/2106.06683/) (2021)
- [Towards Accuracy-Fairness Paradox: Adversarial Example-based Data Augmentation for Visual Debiasing](https://mlsanity.com/paper/2007.13632/) (2020)
- [ROSITA: Enhancing Vision-and-Language Semantic Alignments via Cross- and Intra-modal Knowledge Integration](https://mlsanity.com/paper/2108.07073/) (2021)
- [Evidence for Hypodescent in Visual Semantic AI](https://mlsanity.com/paper/2205.10764/) (2022)

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

- [Examining Gender and Racial Bias in Large Vision-Language Models Using a Novel Dataset of Parallel Images](https://mlsanity.com/paper/2402.05779/) (2024)
- [CLIP the Bias: How Useful is Balancing Data in Multimodal Learning?](https://mlsanity.com/paper/2403.04547/) (2024)
- [Fair Text-to-Image Diffusion via Fair Mapping](https://mlsanity.com/paper/2311.17695/) (2023)
- [Balancing the Picture: Debiasing Vision-Language Datasets with Synthetic Contrast Sets](https://mlsanity.com/paper/2305.15407/) (2023)
- [FairerCLIP: Debiasing CLIP's Zero-Shot Predictions using Functions in RKHSs](https://mlsanity.com/paper/2403.15593/) (2024)
- [Gender Biases in Automatic Evaluation Metrics for Image Captioning](https://mlsanity.com/paper/2305.14711/) (2023)
- [Zero-Shot Robustification of Zero-Shot Models](https://mlsanity.com/paper/2309.04344/) (2023)
- [Auditing Gender Presentation Differences in Text-to-Image Models](https://mlsanity.com/paper/2302.03675/) (2023)
- [Mitigating Test-Time Bias for Fair Image Retrieval](https://mlsanity.com/paper/2305.19329/) (2023)
- [A Unified Debiasing Approach for Vision-Language Models across Modalities and Tasks](https://mlsanity.com/paper/2410.07593/) (2024)
- [Harm Amplification in Text-to-Image Models](https://mlsanity.com/paper/2402.01787/) (2024)
- [BBQ-V: Benchmarking Visual Stereotype Bias in Large Multimodal Models](https://mlsanity.com/paper/2502.08779/) (2025)
- [Nearest Neighbor Normalization Improves Multimodal Retrieval](https://mlsanity.com/paper/2410.24114/) (2024)
- [Foundation Model-oriented Robustness: Robust Image Model Evaluation with Pretrained Models](https://mlsanity.com/paper/2308.10632/) (2023)
- [PRISM: Reducing Spurious Implicit Biases in Vision-Language Models with LLM-Guided Embedding Projection](https://mlsanity.com/paper/2507.08979/) (2025)
- [Unveiling the "Fairness Seesaw": Discovering and Mitigating Gender and Race Bias in Vision-Language Models](https://mlsanity.com/paper/2505.23798/) (2025)
- [Which One? Leveraging Context Between Objects and Multiple Views for Language Grounding](https://mlsanity.com/paper/2311.06694/) (2023)
- [Multi-Group Proportional Representation in Retrieval](https://mlsanity.com/paper/2407.08571/) (2024)
- [Cross-modality debiasing: using language to mitigate sub-population shifts in imaging](https://mlsanity.com/paper/2403.07888/) (2024)
- [Bias Redistribution in Visual Machine Unlearning: Does Forgetting One Group Harm Another?](https://mlsanity.com/paper/2604.08111/) (2026)

## Abstract (arXiv)

The Vision-Language Pre-training (VLP) models like CLIP have gained popularity in recent years. However, many works found that the social biases hidden in CLIP easily manifest in downstream tasks, especially in image retrieval, which can have harmful effects on human society. In this work, we propose FairCLIP to eliminate the social bias in CLIP-based image retrieval without damaging the retrieval performance achieving the compatibility between the debiasing effect and the retrieval performance. FairCLIP is divided into two steps: Attribute Prototype Learning (APL) and Representation Neutralization (RN). In the first step, we extract the concepts needed for debiasing in CLIP. We use the query with learnable word vector prefixes as the extraction structure. In the second step, we first divide the attributes into target and bias attributes. By analysis, we find that both attributes have an impact on the bias. Therefore, we try to eliminate the bias by using Re-Representation Matrix (RRM) to achieve the neutralization of the representation. We compare the debiasing effect and retrieval performance with other methods, and experiments demonstrate that FairCLIP can achieve the best compatibility. Although FairCLIP is used to eliminate bias in image retrieval, it achieves the neutralization of the representation which is common to all CLIP downstream tasks. This means that FairCLIP can be applied as a general debiasing method for other fairness issues related to CLIP.