# Understanding and Evaluating Racial Biases in Image Captioning

arXiv: https://arxiv.org/abs/2106.08503 · HTML: https://mlsanity.com/paper/2106.08503/

## Key facts

- Cited by 108 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 85 references that are in the map.
- First posted on arXiv 16 Jun 2021.

## Builds on (most cited first, 30 of 45)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [Microsoft COCO Captions: Data Collection and Evaluation Server](https://mlsanity.com/paper/1504.00325/) (2015)
- [Datasheets for Datasets](https://mlsanity.com/paper/1803.09010/) (2018)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering](https://mlsanity.com/paper/1707.07998/) (2017)
- [Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks](https://mlsanity.com/paper/2004.06165/) (2020)
- [Language (Technology) is Power: A Critical Survey of "Bias" in NLP](https://mlsanity.com/paper/2005.14050/) (2020)
- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [Show and Tell: A Neural Image Caption Generator](https://mlsanity.com/paper/1411.4555/) (2014)
- [SPICE: Semantic Propositional Image Caption Evaluation](https://mlsanity.com/paper/1607.08822/) (2016)
- [Self-critical Sequence Training for Image Captioning](https://mlsanity.com/paper/1612.00563/) (2016)
- [Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints](https://mlsanity.com/paper/1707.09457/) (2017)
- [AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias](https://mlsanity.com/paper/1810.01943/) (2018)
- [Measurement and Fairness](https://mlsanity.com/paper/1912.05511/) (2019)
- [Attention on Attention for Image Captioning](https://mlsanity.com/paper/1908.06954/) (2019)
- [Image Captioning with Semantic Attention](https://mlsanity.com/paper/1603.03925/) (2016)
- [Data and its (dis)contents: A survey of dataset development and use in machine learning research](https://mlsanity.com/paper/2012.05345/) (2020)
- [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)
- [Examining Gender and Race Bias in Two Hundred Sentiment Analysis Systems](https://mlsanity.com/paper/1805.04508/) (2018)
- [Knowing When to Look: Adaptive Attention via A Visual Sentinel for Image Captioning](https://mlsanity.com/paper/1612.01887/) (2016)
- [A Comprehensive Survey of Deep Learning for Image Captioning](https://mlsanity.com/paper/1810.04020/) (2018)
- [Racial Bias in Hate Speech and Abusive Language Detection Datasets](https://mlsanity.com/paper/1905.12516/) (2019)
- [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)
- [Towards Accountability for Machine Learning Datasets: Practices from Software Engineering and Infrastructure](https://mlsanity.com/paper/2010.13561/) (2020)

## Built on by (most cited first, 30 of 108)

- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [GIT: A Generative Image-to-text Transformer for Vision and Language](https://mlsanity.com/paper/2205.14100/) (2022)
- [DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models](https://mlsanity.com/paper/2202.04053/) (2022)
- [Vision-Language Pre-training: Basics, Recent Advances, and Future Trends](https://mlsanity.com/paper/2210.09263/) (2022)
- [A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learning](https://mlsanity.com/paper/2203.11933/) (2022)
- [SafetyPrompts: a Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safety](https://mlsanity.com/paper/2404.05399/) (2024)
- [A Systematic Study of Bias Amplification](https://mlsanity.com/paper/2201.11706/) (2022)
- [FACET: Fairness in Computer Vision Evaluation Benchmark](https://mlsanity.com/paper/2309.00035/) (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)
- [A Decade's Battle on Dataset Bias: Are We There Yet?](https://mlsanity.com/paper/2403.08632/) (2024)
- [Inspecting the Geographical Representativeness of Images from Text-to-Image Models](https://mlsanity.com/paper/2305.11080/) (2023)
- [Gender and Racial Bias in Visual Question Answering Datasets](https://mlsanity.com/paper/2205.08148/) (2022)
- [Adaptive Testing of Computer Vision Models](https://mlsanity.com/paper/2212.02774/) (2022)
- [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)
- [Measuring Representational Harms in Image Captioning](https://mlsanity.com/paper/2206.07173/) (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)
- [On Learning Fairness and Accuracy on Multiple Subgroups](https://mlsanity.com/paper/2210.10837/) (2022)
- [Overwriting Pretrained Bias with Finetuning Data](https://mlsanity.com/paper/2303.06167/) (2023)
- [GenderBias-VL: Benchmarking Gender Bias in Vision Language Models via Counterfactual Probing](https://mlsanity.com/paper/2407.00600/) (2024)
- [FairGRAPE: Fairness-aware GRAdient Pruning mEthod for Face Attribute Classification](https://mlsanity.com/paper/2207.10888/) (2022)
- [Bias Mimicking: A Simple Sampling Approach for Bias Mitigation](https://mlsanity.com/paper/2209.15605/) (2022)
- [Balancing the Picture: Debiasing Vision-Language Datasets with Synthetic Contrast Sets](https://mlsanity.com/paper/2305.15407/) (2023)
- [Position: Measure Dataset Diversity, Don't Just Claim It](https://mlsanity.com/paper/2407.08188/) (2024)
- [MultiHateClip: A Multilingual Benchmark Dataset for Hateful Video Detection on YouTube and Bilibili](https://mlsanity.com/paper/2408.03468/) (2024)
- [Would Deep Generative Models Amplify Bias in Future Models?](https://mlsanity.com/paper/2404.03242/) (2024)
- [Consensus and Subjectivity of Skin Tone Annotation for ML Fairness](https://mlsanity.com/paper/2305.09073/) (2023)

## Abstract (arXiv)

Image captioning is an important task for benchmarking visual reasoning and for enabling accessibility for people with vision impairments. However, as in many machine learning settings, social biases can influence image captioning in undesirable ways. In this work, we study bias propagation pathways within image captioning, focusing specifically on the COCO dataset. Prior work has analyzed gender bias in captions using automatically-derived gender labels; here we examine racial and intersectional biases using manual annotations. Our first contribution is in annotating the perceived gender and skin color of 28,315 of the depicted people after obtaining IRB approval. Using these annotations, we compare racial biases present in both manual and automatically-generated image captions. We demonstrate differences in caption performance, sentiment, and word choice between images of lighter versus darker-skinned people. Further, we find the magnitude of these differences to be greater in modern captioning systems compared to older ones, thus leading to concerns that without proper consideration and mitigation these differences will only become increasingly prevalent. Code and data is available at https://princetonvisualai.github.io/imagecaptioning-bias .