Latent Directions: A Simple Pathway to Bias Mitigation in Generative AI

• URL: http://arxiv.org/abs/2406.06352v1
• Date: Mon, 10 Jun 2024 15:13:51 GMT
• Title: Latent Directions: A Simple Pathway to Bias Mitigation in Generative AI
• Authors: Carolina Lopez Olmos, Alexandros Neophytou, Sunando Sengupta, Dim P. Papadopoulos,
• Abstract summary: Mitigating biases in generative AI and, particularly in text-to-image models, is of high importance given their growing implications in society. Our work introduces a novel approach to achieve diverse and inclusive synthetic images by learning a direction in the latent space. It is possible to linearly combine these learned latent directions to introduce new mitigations, and if desired, integrate it with text embedding adjustments.
• Score: 45.54709270833219
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Mitigating biases in generative AI and, particularly in text-to-image models, is of high importance given their growing implications in society. The biased datasets used for training pose challenges in ensuring the responsible development of these models, and mitigation through hard prompting or embedding alteration, are the most common present solutions. Our work introduces a novel approach to achieve diverse and inclusive synthetic images by learning a direction in the latent space and solely modifying the initial Gaussian noise provided for the diffusion process. Maintaining a neutral prompt and untouched embeddings, this approach successfully adapts to diverse debiasing scenarios, such as geographical biases. Moreover, our work proves it is possible to linearly combine these learned latent directions to introduce new mitigations, and if desired, integrate it with text embedding adjustments. Furthermore, text-to-image models lack transparency for assessing bias in outputs, unless visually inspected. Thus, we provide a tool to empower developers to select their desired concepts to mitigate. The project page with code is available online.

Related papers

• Training-free Composite Scene Generation for Layout-to-Image Synthesis [29.186425845897947]
  This paper introduces a novel training-free approach designed to overcome adversarial semantic intersections during the diffusion conditioning phase. We propose two innovative constraints: 1) an inter-token constraint that resolves token conflicts to ensure accurate concept synthesis; and 2) a self-attention constraint that improves pixel-to-pixel relationships. Our evaluations confirm the effectiveness of leveraging layout information for guiding the diffusion process, generating content-rich images with enhanced fidelity and complexity.
  arXiv  Detail & Related papers  (2024-07-18T15:48:07Z)
• AITTI: Learning Adaptive Inclusive Token for Text-to-Image Generation [53.65701943405546]
  We learn adaptive inclusive tokens to shift the attribute distribution of the final generative outputs. Our method requires neither explicit attribute specification nor prior knowledge of the bias distribution. Our method achieves comparable performance to models that require specific attributes or editing directions for generation.
  arXiv  Detail & Related papers  (2024-06-18T17:22:23Z)
• Can Prompt Modifiers Control Bias? A Comparative Analysis of Text-to-Image Generative Models [8.419004940268023]
  This study examines the presence and manipulation of societal biases in leading text-to-image models: Stable Diffusion, DALL-E 3, and Adobe Firefly. Our findings reveal the challenges and potential of prompt engineering in controlling biases, highlighting the critical need for ethical AI development. This work advances AI ethics by not only revealing the nuanced dynamics of bias in text-to-image generation models but also by offering a novel framework for future research in controlling bias.
  arXiv  Detail & Related papers  (2024-06-09T00:54:57Z)
• Debiasing Multimodal Large Language Models [61.6896704217147]
  Large Vision-Language Models (LVLMs) have become indispensable tools in computer vision and natural language processing. Our investigation reveals a noteworthy bias in the generated content, where the output is primarily influenced by the underlying Large Language Models (LLMs) prior to the input image. To rectify these biases and redirect the model's focus toward vision information, we introduce two simple, training-free strategies.
  arXiv  Detail & Related papers  (2024-03-08T12:35:07Z)
• Debiasing Vision-Language Models via Biased Prompts [79.04467131711775]
  We propose a general approach for debiasing vision-language foundation models by projecting out biased directions in the text embedding. We show that debiasing only the text embedding with a calibrated projection matrix suffices to yield robust classifiers and fair generative models.
  arXiv  Detail & Related papers  (2023-01-31T20:09:33Z)
• Proactive Pseudo-Intervention: Causally Informed Contrastive Learning For Interpretable Vision Models [103.64435911083432]
  We present a novel contrastive learning strategy called it Proactive Pseudo-Intervention (PPI) PPI leverages proactive interventions to guard against image features with no causal relevance. We also devise a novel causally informed salience mapping module to identify key image pixels to intervene, and show it greatly facilitates model interpretability.
  arXiv  Detail & Related papers  (2020-12-06T20:30:26Z)
• Encoding Robustness to Image Style via Adversarial Feature Perturbations [72.81911076841408]
  We adapt adversarial training by directly perturbing feature statistics, rather than image pixels, to produce robust models. Our proposed method, Adversarial Batch Normalization (AdvBN), is a single network layer that generates worst-case feature perturbations during training.
  arXiv  Detail & Related papers  (2020-09-18T17:52:34Z)

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.