Contrastive Language-Vision AI Models Pretrained on Web-Scraped Multimodal Data Exhibit Sexual Objectification Bias

• URL: http://arxiv.org/abs/2212.11261v2
• Date: Mon, 15 May 2023 23:49:27 GMT
• Title: Contrastive Language-Vision AI Models Pretrained on Web-Scraped Multimodal Data Exhibit Sexual Objectification Bias
• Authors: Robert Wolfe, Yiwei Yang, Bill Howe, Aylin Caliskan
• Abstract summary: We show that language-vision AI models trained on web scrapes learn biases of sexual objectification. Images of female professionals are likely to be associated with sexual descriptions relative to images of male professionals.
• Score: 11.6727088473067
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Nine language-vision AI models trained on web scrapes with the Contrastive Language-Image Pretraining (CLIP) objective are evaluated for evidence of a bias studied by psychologists: the sexual objectification of girls and women, which occurs when a person's human characteristics, such as emotions, are disregarded and the person is treated as a body. We replicate three experiments in psychology quantifying sexual objectification and show that the phenomena persist in AI. A first experiment uses standardized images of women from the Sexual OBjectification and EMotion Database, and finds that human characteristics are disassociated from images of objectified women: the model's recognition of emotional state is mediated by whether the subject is fully or partially clothed. Embedding association tests (EATs) return significant effect sizes for both anger (d >0.80) and sadness (d >0.50), associating images of fully clothed subjects with emotions. GRAD-CAM saliency maps highlight that CLIP gets distracted from emotional expressions in objectified images. A second experiment measures the effect in a representative application: an automatic image captioner (Antarctic Captions) includes words denoting emotion less than 50% as often for images of partially clothed women than for images of fully clothed women. A third experiment finds that images of female professionals (scientists, doctors, executives) are likely to be associated with sexual descriptions relative to images of male professionals. A fourth experiment shows that a prompt of "a [age] year old girl" generates sexualized images (as determined by an NSFW classifier) up to 73% of the time for VQGAN-CLIP and Stable Diffusion; the corresponding rate for boys never surpasses 9%. The evidence indicates that language-vision AI models trained on web scrapes learn biases of sexual objectification, which propagate to downstream applications.

Related papers

• The Male CEO and the Female Assistant: Evaluation and Mitigation of Gender Biases in Text-To-Image Generation of Dual Subjects [58.27353205269664]
  We propose the Paired Stereotype Test (PST) framework, which queries T2I models to depict two individuals assigned with male-stereotyped and female-stereotyped social identities. PST queries T2I models to depict two individuals assigned with male-stereotyped and female-stereotyped social identities. Using PST, we evaluate two aspects of gender biases -- the well-known bias in gendered occupation and a novel aspect: bias in organizational power.
  arXiv  Detail & Related papers  (2024-02-16T21:32:27Z)
• Stable Diffusion Exposed: Gender Bias from Prompt to Image [25.702257177921048]
  This paper introduces an evaluation protocol that analyzes the impact of gender indicators at every step of the generation process on Stable Diffusion images. Our findings include the existence of differences in the depiction of objects, such as instruments tailored for specific genders, and shifts in overall layouts.
  arXiv  Detail & Related papers  (2023-12-05T10:12:59Z)
• Socratis: Are large multimodal models emotionally aware? [63.912414283486555]
  Existing emotion prediction benchmarks do not consider the diversity of emotions that an image and text can elicit in humans due to various reasons. We propose Socratis, a societal reactions benchmark, where each image-caption (IC) pair is annotated with multiple emotions and the reasons for feeling them. We benchmark the capability of state-of-the-art multimodal large language models to generate the reasons for feeling an emotion given an IC pair.
  arXiv  Detail & Related papers  (2023-08-31T13:59:35Z)
• VisoGender: A dataset for benchmarking gender bias in image-text pronoun resolution [80.57383975987676]
  VisoGender is a novel dataset for benchmarking gender bias in vision-language models. We focus on occupation-related biases within a hegemonic system of binary gender, inspired by Winograd and Winogender schemas. We benchmark several state-of-the-art vision-language models and find that they demonstrate bias in resolving binary gender in complex scenes.
  arXiv  Detail & Related papers  (2023-06-21T17:59:51Z)
• Stereotypes and Smut: The (Mis)representation of Non-cisgender Identities by Text-to-Image Models [6.92043136971035]
  We investigate how multimodal models handle diverse gender identities. We find certain non-cisgender identities are consistently (mis)represented as less human, more stereotyped and more sexualised. These improvements could pave the way for a future where change is led by the affected community.
  arXiv  Detail & Related papers  (2023-05-26T16:28:49Z)
• Smiling Women Pitching Down: Auditing Representational and Presentational Gender Biases in Image Generative AI [0.6990493129893111]
  We examined the prevalence of two occupational gender biases in 15,300 DALL-E 2 images spanning 153 occupations. DALL-E 2 underrepresents women in male-dominated fields while overrepresenting them in female-dominated occupations. Our computational algorithm auditing study demonstrates more pronounced representational and presentational biases in DALL-E 2 compared to Google Images.
  arXiv  Detail & Related papers  (2023-05-17T20:59:10Z)
• Auditing Gender Presentation Differences in Text-to-Image Models [54.16959473093973]
  We study how gender is presented differently in text-to-image models. By probing gender indicators in the input text, we quantify the frequency differences of presentation-centric attributes. We propose an automatic method to estimate such differences.
  arXiv  Detail & Related papers  (2023-02-07T18:52:22Z)
• DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models [73.12069620086311]
  We investigate the visual reasoning capabilities and social biases of text-to-image models. First, we measure three visual reasoning skills: object recognition, object counting, and spatial relation understanding. Second, we assess the gender and skin tone biases by measuring the gender/skin tone distribution of generated images.
  arXiv  Detail & Related papers  (2022-02-08T18:36:52Z)
• Real-time Emotion and Gender Classification using Ensemble CNN [0.0]
  This paper is the implementation of an Ensemble CNN for building a real-time system that can detect emotion and gender of the person. Our work can predict emotion and gender on single face images as well as multiple face images.
  arXiv  Detail & Related papers  (2021-11-15T13:51:35Z)
• Image Representations Learned With Unsupervised Pre-Training Contain Human-like Biases [3.0349733976070015]
  We develop a novel method for quantifying biased associations between representations of social concepts and attributes in images. We find that state-of-the-art unsupervised models trained on ImageNet, a popular benchmark image dataset, automatically learn racial, gender, and intersectional biases.
  arXiv  Detail & Related papers  (2020-10-28T15:55:49Z)
• InsideBias: Measuring Bias in Deep Networks and Application to Face Gender Biometrics [73.85525896663371]
  This work explores the biases in learning processes based on deep neural network architectures. We employ two gender detection models based on popular deep neural networks. We propose InsideBias, a novel method to detect biased models.
  arXiv  Detail & Related papers  (2020-04-14T15:20:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.