Related papers: Situating the social issues of image generation models in the model life cycle: a sociotechnical approach

Situating the social issues of image generation models in the model life cycle: a sociotechnical approach

URL: http://arxiv.org/abs/2311.18345v2
Date: Tue, 23 Jul 2024 01:39:55 GMT
Title: Situating the social issues of image generation models in the model life cycle: a sociotechnical approach
Authors: Amelia Katirai, Noa Garcia, Kazuki Ide, Yuta Nakashima, Atsuo Kishimoto,
Abstract summary: This paper reports on a novel, comprehensive categorization of the social issues associated with image generation models. We identify seven issue clusters arising from image generation models: data issues, intellectual property, bias, privacy, and the impacts on the informational, cultural, and natural environments. We argue that the risks posed by image generation models are comparable in severity to the risks posed by large language models.
Score: 20.99805435959377
License: http://creativecommons.org/licenses/by/4.0/
Abstract: The race to develop image generation models is intensifying, with a rapid increase in the number of text-to-image models available. This is coupled with growing public awareness of these technologies. Though other generative AI models--notably, large language models--have received recent critical attention for the social and other non-technical issues they raise, there has been relatively little comparable examination of image generation models. This paper reports on a novel, comprehensive categorization of the social issues associated with image generation models. At the intersection of machine learning and the social sciences, we report the results of a survey of the literature, identifying seven issue clusters arising from image generation models: data issues, intellectual property, bias, privacy, and the impacts on the informational, cultural, and natural environments. We situate these social issues in the model life cycle, to aid in considering where potential issues arise, and mitigation may be needed. We then compare these issue clusters with what has been reported for large language models. Ultimately, we argue that the risks posed by image generation models are comparable in severity to the risks posed by large language models, and that the social impact of image generation models must be urgently considered.

Related papers

Analyzing Quality, Bias, and Performance in Text-to-Image Generative Models [0.0]
Despite advances in generative models, most studies ignore the presence of bias. In this paper, we examine several text-to-image models not only by qualitatively assessing their performance in generating accurate images of human faces, groups, and specified numbers of objects but also by presenting a social bias analysis. As expected, models with larger capacity generate higher-quality images. However, we also document the inherent gender or social biases these models possess, offering a more complete understanding of their impact and limitations.
arXiv Detail & Related papers (2024-06-28T14:10:42Z)
A Taxonomy of the Biases of the Images created by Generative Artificial Intelligence [2.0257616108612373]
Generative artificial intelligence models show an amazing performance creating unique content automatically just by being given a prompt by the user. We analyze in detail how the generated content by these models can be strongly biased with respect to a plethora of variables. We discuss the social, political and economical implications of these biases and possible ways to mitigate them.
arXiv Detail & Related papers (2024-05-02T22:01:28Z)
T-HITL Effectively Addresses Problematic Associations in Image Generation and Maintains Overall Visual Quality [52.5529784801908]
We focus on addressing the generation of problematic associations between demographic groups and semantic concepts. We propose a new methodology with twice-human-in-the-loop (T-HITL) that promises improvements in both reducing problematic associations and also maintaining visual quality.
arXiv Detail & Related papers (2024-02-27T00:29:33Z)
New Job, New Gender? Measuring the Social Bias in Image Generation Models [85.26441602999014]
Image generation models are susceptible to generating content that perpetuates social stereotypes and biases. We propose BiasPainter, a framework that can accurately, automatically and comprehensively trigger social bias in image generation models. BiasPainter can achieve 90.8% accuracy on automatic bias detection, which is significantly higher than the results reported in previous work.
arXiv Detail & Related papers (2024-01-01T14:06:55Z)
Limitations of Face Image Generation [12.11955119100926]
We study the efficacy and shortcomings of generative models in the context of face generation. We identify several limitations of face image generation that include faithfulness to the text prompt, demographic disparities, and distributional shifts. We present an analytical model that provides insights into how training data selection contributes to the performance of generative models.
arXiv Detail & Related papers (2023-09-13T19:33:26Z)
RenAIssance: A Survey into AI Text-to-Image Generation in the Era of Large Model [93.8067369210696]
Text-to-image generation (TTI) refers to the usage of models that could process text input and generate high fidelity images based on text descriptions. Diffusion models are one prominent type of generative model used for the generation of images through the systematic introduction of noises with repeating steps. In the era of large models, scaling up model size and the integration with large language models have further improved the performance of TTI models.
arXiv Detail & Related papers (2023-09-02T03:27:20Z)
Foundational Models Defining a New Era in Vision: A Survey and Outlook [151.49434496615427]
Vision systems to see and reason about the compositional nature of visual scenes are fundamental to understanding our world. The models learned to bridge the gap between such modalities coupled with large-scale training data facilitate contextual reasoning, generalization, and prompt capabilities at test time. The output of such models can be modified through human-provided prompts without retraining, e.g., segmenting a particular object by providing a bounding box, having interactive dialogues by asking questions about an image or video scene or manipulating the robot's behavior through language instructions.
arXiv Detail & Related papers (2023-07-25T17:59:18Z)
How well can Text-to-Image Generative Models understand Ethical Natural Language Interventions? [67.97752431429865]
We study the effect on the diversity of the generated images when adding ethical intervention. Preliminary studies indicate that a large change in the model predictions is triggered by certain phrases such as 'irrespective of gender'
arXiv Detail & Related papers (2022-10-27T07:32:39Z)
Membership Inference Attacks Against Text-to-image Generation Models [23.39695974954703]
This paper performs the first privacy analysis of text-to-image generation models through the lens of membership inference. We propose three key intuitions about membership information and design four attack methodologies accordingly. All of the proposed attacks can achieve significant performance, in some cases even close to an accuracy of 1, and thus the corresponding risk is much more severe than that shown by existing membership inference attacks.
arXiv Detail & Related papers (2022-10-03T14:31:39Z)
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)

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