# Mitigating Gender Bias in Captioning Systems

arXiv: https://arxiv.org/abs/2006.08315 · HTML: https://mlsanity.com/paper/2006.08315/

## Key facts

- Cited by 50 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jun 2020.

## Built on by (most cited first, 30 of 50)

- [Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond](https://mlsanity.com/paper/2304.13712/) (2023)
- [DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models](https://mlsanity.com/paper/2202.04053/) (2022)
- [Understanding and Evaluating Racial Biases in Image Captioning](https://mlsanity.com/paper/2106.08503/) (2021)
- [Are Gender-Neutral Queries Really Gender-Neutral? Mitigating Gender Bias in Image Search](https://mlsanity.com/paper/2109.05433/) (2021)
- [IAIA-BL: A Case-based Interpretable Deep Learning Model for Classification of Mass Lesions in Digital Mammography](https://mlsanity.com/paper/2103.12308/) (2021)
- [Large Language Models Can be Lazy Learners: Analyze Shortcuts in In-Context Learning](https://mlsanity.com/paper/2305.17256/) (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)
- [Directional Bias Amplification](https://mlsanity.com/paper/2102.12594/) (2021)
- [Uncurated Image-Text Datasets: Shedding Light on Demographic Bias](https://mlsanity.com/paper/2304.02828/) (2023)
- [Gender and Racial Bias in Visual Question Answering Datasets](https://mlsanity.com/paper/2205.08148/) (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)
- [Assessing Multilingual Fairness in Pre-trained Multimodal Representations](https://mlsanity.com/paper/2106.06683/) (2021)
- [CLIP the Bias: How Useful is Balancing Data in Multimodal Learning?](https://mlsanity.com/paper/2403.04547/) (2024)
- [Visual Abductive Reasoning](https://mlsanity.com/paper/2203.14040/) (2022)
- [Identifying Implicit Social Biases in Vision-Language Models](https://mlsanity.com/paper/2411.00997/) (2024)
- [Would Deep Generative Models Amplify Bias in Future Models?](https://mlsanity.com/paper/2404.03242/) (2024)
- [Debiasing Methods for Fairer Neural Models in Vision and Language Research: A Survey](https://mlsanity.com/paper/2211.05617/) (2022)
- [Fairness and Bias in Multimodal AI: A Survey](https://mlsanity.com/paper/2406.19097/) (2024)
- [Model-Agnostic Gender Debiased Image Captioning](https://mlsanity.com/paper/2304.03693/) (2023)
- [BendVLM: Test-Time Debiasing of Vision-Language Embeddings](https://mlsanity.com/paper/2411.04420/) (2024)
- [A Unified Framework and Dataset for Assessing Societal Bias in Vision-Language Models](https://mlsanity.com/paper/2402.13636/) (2024)
- [Resampled Datasets Are Not Enough: Mitigating Societal Bias Beyond Single Attributes](https://mlsanity.com/paper/2407.03623/) (2024)
- [What's in a Caption? Dataset-Specific Linguistic Diversity and Its Effect on Visual Description Models and Metrics](https://mlsanity.com/paper/2205.06253/) (2022)
- [Distribution Aware Metrics for Conditional Natural Language Generation](https://mlsanity.com/paper/2209.07518/) (2022)
- [Evaluating Bias and Fairness in Gender-Neutral Pretrained Vision-and-Language Models](https://mlsanity.com/paper/2310.17530/) (2023)
- [Visual Data Diagnosis and Debiasing with Concept Graphs](https://mlsanity.com/paper/2409.18055/) (2024)
- [Interpretable Debiasing of Vision-Language Models for Social Fairness](https://mlsanity.com/paper/2602.24014/) (2026)
- [ImageCaptioner2: Image Captioner for Image Captioning Bias Amplification Assessment](https://mlsanity.com/paper/2304.04874/) (2023)

## Abstract (arXiv)

Image captioning has made substantial progress with huge supporting image collections sourced from the web. However, recent studies have pointed out that captioning datasets, such as COCO, contain gender bias found in web corpora. As a result, learning models could heavily rely on the learned priors and image context for gender identification, leading to incorrect or even offensive errors. To encourage models to learn correct gender features, we reorganize the COCO dataset and present two new splits COCO-GB V1 and V2 datasets where the train and test sets have different gender-context joint distribution. Models relying on contextual cues will suffer from huge gender prediction errors on the anti-stereotypical test data. Benchmarking experiments reveal that most captioning models learn gender bias, leading to high gender prediction errors, especially for women. To alleviate the unwanted bias, we propose a new Guided Attention Image Captioning model (GAIC) which provides self-guidance on visual attention to encourage the model to capture correct gender visual evidence. Experimental results validate that GAIC can significantly reduce gender prediction errors with a competitive caption quality. Our codes and the designed benchmark datasets are available at https://github.com/datamllab/Mitigating_Gender_Bias_In_Captioning_System.