Social Reward: Evaluating and Enhancing Generative AI through Million-User Feedback from an Online Creative Community

• URL: http://arxiv.org/abs/2402.09872v1
• Date: Thu, 15 Feb 2024 10:56:31 GMT
• Title: Social Reward: Evaluating and Enhancing Generative AI through Million-User Feedback from an Online Creative Community
• Authors: Arman Isajanyan, Artur Shatveryan, David Kocharyan, Zhangyang Wang, Humphrey Shi
• Abstract summary: Social reward as a form of community recognition provides a strong source of motivation for users of online platforms to engage and contribute with content. This work pioneers a paradigm shift, unveiling Social Reward - an innovative reward modeling framework. We embark on an extensive journey of dataset curation and refinement, drawing from Picsart: an online visual creation and editing platform.
• Score: 63.949893724058846
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Social reward as a form of community recognition provides a strong source of motivation for users of online platforms to engage and contribute with content. The recent progress of text-conditioned image synthesis has ushered in a collaborative era where AI empowers users to craft original visual artworks seeking community validation. Nevertheless, assessing these models in the context of collective community preference introduces distinct challenges. Existing evaluation methods predominantly center on limited size user studies guided by image quality and prompt alignment. This work pioneers a paradigm shift, unveiling Social Reward - an innovative reward modeling framework that leverages implicit feedback from social network users engaged in creative editing of generated images. We embark on an extensive journey of dataset curation and refinement, drawing from Picsart: an online visual creation and editing platform, yielding a first million-user-scale dataset of implicit human preferences for user-generated visual art named Picsart Image-Social. Our analysis exposes the shortcomings of current metrics in modeling community creative preference of text-to-image models' outputs, compelling us to introduce a novel predictive model explicitly tailored to address these limitations. Rigorous quantitative experiments and user study show that our Social Reward model aligns better with social popularity than existing metrics. Furthermore, we utilize Social Reward to fine-tune text-to-image models, yielding images that are more favored by not only Social Reward, but also other established metrics. These findings highlight the relevance and effectiveness of Social Reward in assessing community appreciation for AI-generated artworks, establishing a closer alignment with users' creative goals: creating popular visual art. Codes can be accessed at https://github.com/Picsart-AI-Research/Social-Reward

Related papers

• KITTEN: A Knowledge-Intensive Evaluation of Image Generation on Visual Entities [93.74881034001312]
  We conduct a systematic study on the fidelity of entities in text-to-image generation models. We focus on their ability to generate a wide range of real-world visual entities, such as landmark buildings, aircraft, plants, and animals. Our findings reveal that even the most advanced text-to-image models often fail to generate entities with accurate visual details.
  arXiv  Detail & Related papers  (2024-10-15T17:50:37Z)
• Safeguard Text-to-Image Diffusion Models with Human Feedback Inversion [51.931083971448885]
  We propose a framework named Human Feedback Inversion (HFI), where human feedback on model-generated images is condensed into textual tokens guiding the mitigation or removal of problematic images. Our experimental results demonstrate our framework significantly reduces objectionable content generation while preserving image quality, contributing to the ethical deployment of AI in the public sphere.
  arXiv  Detail & Related papers  (2024-07-17T05:21:41Z)
• Exploring the Use of Abusive Generative AI Models on Civitai [22.509955105958625]
  We study the use of Civitai, the largest AIGC social platform, for generating abusive content. We construct a comprehensive dataset covering 87K models and 2M images. We discuss strategies for moderation to better govern these platforms.
  arXiv  Detail & Related papers  (2024-07-16T06:18:03Z)
• Balancing User Preferences by Social Networks: A Condition-Guided Social Recommendation Model for Mitigating Popularity Bias [64.73474454254105]
  Social recommendation models weave social interactions into their design to provide uniquely personalized recommendation results for users. Existing social recommendation models fail to address the issues of popularity bias and the redundancy of social information. We propose a Condition-Guided Social Recommendation Model (named CGSoRec) to mitigate the model's popularity bias.
  arXiv  Detail & Related papers  (2024-05-27T02:45:01Z)
• Collaborative Interactive Evolution of Art in the Latent Space of Deep Generative Models [1.4425878137951238]
  We first employ GANs that are trained to produce creative images using an architecture known as Creative Adversarial Networks (CANs) We then employ an evolutionary approach to navigate within the latent space of the models to discover images. We use automatic aesthetic and collaborative interactive human evaluation metrics to assess the generated images.
  arXiv  Detail & Related papers  (2024-03-28T17:40:15Z)
• #PoetsOfInstagram: Navigating The Practices And Challenges Of Novice Poets On Instagram [22.17344487934666]
  We employ qualitative analysis to explore motivations, experiences, and algorithmic influence within Instagram's poetry community. We demonstrate that participants prioritize conforming to algorithmic constraints for visibility, yet maintain their community's values of integrity and originality. We introduce the concept of Algorithmically Mediated Creative Labor, a phenomenon specific to non-monetizing creative users.
  arXiv  Detail & Related papers  (2024-02-29T16:55:44Z)
• Exploring Social Bias in Downstream Applications of Text-to-Image Foundation Models [72.06006736916821]
  We use synthetic images to probe two applications of text-to-image models, image editing and classification, for social bias. Using our methodology, we uncover meaningful and significant inter-sectional social biases in textitStable Diffusion, a state-of-the-art open-source text-to-image model. Our findings caution against the uninformed adoption of text-to-image foundation models for downstream tasks and services.
  arXiv  Detail & Related papers  (2023-12-05T14:36:49Z)
• FaceStudio: Put Your Face Everywhere in Seconds [23.381791316305332]
  Identity-preserving image synthesis seeks to maintain a subject's identity while adding a personalized, stylistic touch. Traditional methods, such as Textual Inversion and DreamBooth, have made strides in custom image creation. Our research introduces a novel approach to identity-preserving synthesis, with a particular focus on human images.
  arXiv  Detail & Related papers  (2023-12-05T11:02:45Z)
• Disentangled Contrastive Learning for Social Recommendation [28.606016662435117]
  Social recommendations utilize social relations to enhance the representation learning for recommendations. We propose a novel Disentangled contrastive learning framework for social Recommendations DcRec.
  arXiv  Detail & Related papers  (2022-08-18T09:15:18Z)
• Enhancing Social Relation Inference with Concise Interaction Graph and Discriminative Scene Representation [56.25878966006678]
  We propose an approach of textbfPRactical textbfInference in textbfSocial rtextbfElation (PRISE) It concisely learns interactive features of persons and discriminative features of holistic scenes. PRISE achieves 6.8$%$ improvement for domain classification in PIPA dataset.
  arXiv  Detail & Related papers  (2021-07-30T04:20:13Z)

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.