Mitigating Gender Bias in Captioning Systems

By Ruixiang Tang, Mengnan Du, Yuening Li, Zirui Liu, Xia Hu. 2020

78 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Multimodal Learning, AI Ethics, Fairness & Society

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Mohit Bansal
2. Jaemin Cho
3. Abhaysinh Zala
4. Cynthia Rudin
5. Alina Jade Barnett
6. Xia Hu
7. Chaofan Tao
8. Haoming Jiang

In Computer Vision and Pattern Recognition

1. Jaemin Cho
2. Mohit Bansal
3. Cynthia Rudin
4. Abhaysinh Zala
5. Xia Hu
6. Alina Jade Barnett
7. Chaofan Tao
8. Hongye Jin

In Multimodal Learning

1. Jaemin Cho
2. Abhaysinh Zala
3. Mohit Bansal
4. Ruixiang Tang
5. Xia Hu
6. Zhe Gan
7. Lijuan Wang
8. Zicheng Liu

In AI Ethics, Fairness & Society

1. Mohit Bansal
2. Cynthia Rudin
3. Octavio Loyola-González
4. Adrian Weller
5. Yuval Pinter
6. Sarah Wiegreffe

Citations in the corpus

• A case-based interpretable deep learning model for classification of mass lesions in digital mammography (2021, methodology): “Ways to direct model attention include data augmentation [16, 33, 8], techniques that combat hand-selected confounders [51, 50], techniques that combat learned confounders [58], and an approach where a human critic manually approves the attention map during training [43].”
• Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond (2023, background): “The shortcut learning problem has been observed in various natural language understanding tasks under the pretraining and fine-tuning paradigm, where models heavily rely on spurious correlations between input and labels in the fine-tuning data for prediction [35, 39, 107, 109, 128, 129].”
• DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generative Transformers (2022, background): “[7, 8, 55] examined social biases on the image captioning datasets: MS COCO [36] and LAION-400M.”
• DALL-EVAL: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models (2022, unknown): “[9, 8, 76, 12, 92, 38, 80, 37] examine social biases in image-text datasets.”