Self-Discovering Interpretable Diffusion Latent Directions for Responsible Text-to-Image Generation
- URL: http://arxiv.org/abs/2311.17216v2
- Date: Thu, 28 Mar 2024 14:58:59 GMT
- Title: Self-Discovering Interpretable Diffusion Latent Directions for Responsible Text-to-Image Generation
- Authors: Hang Li, Chengzhi Shen, Philip Torr, Volker Tresp, Jindong Gu,
- Abstract summary: A risk with diffusion-based models is the potential generation of inappropriate content, such as biased or harmful images.
Previous work interprets vectors in an interpretable latent space of diffusion models as semantic concepts.
We propose a novel self-supervised approach to find interpretable latent directions for a given concept.
- Score: 36.93643249463899
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Diffusion-based models have gained significant popularity for text-to-image generation due to their exceptional image-generation capabilities. A risk with these models is the potential generation of inappropriate content, such as biased or harmful images. However, the underlying reasons for generating such undesired content from the perspective of the diffusion model's internal representation remain unclear. Previous work interprets vectors in an interpretable latent space of diffusion models as semantic concepts. However, existing approaches cannot discover directions for arbitrary concepts, such as those related to inappropriate concepts. In this work, we propose a novel self-supervised approach to find interpretable latent directions for a given concept. With the discovered vectors, we further propose a simple approach to mitigate inappropriate generation. Extensive experiments have been conducted to verify the effectiveness of our mitigation approach, namely, for fair generation, safe generation, and responsible text-enhancing generation. Project page: \url{https://interpretdiffusion.github.io}.
Related papers
- Six-CD: Benchmarking Concept Removals for Benign Text-to-image Diffusion Models [58.74606272936636]
Text-to-image (T2I) diffusion models have shown exceptional capabilities in generating images that closely correspond to textual prompts.
The models could be exploited for malicious purposes, such as generating images with violence or nudity, or creating unauthorized portraits of public figures in inappropriate contexts.
concept removal methods have been proposed to modify diffusion models to prevent the generation of malicious and unwanted concepts.
arXiv Detail & Related papers (2024-06-21T03:58:44Z) - Latent Directions: A Simple Pathway to Bias Mitigation in Generative AI [45.54709270833219]
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.
arXiv Detail & Related papers (2024-06-10T15:13:51Z) - Concept Arithmetics for Circumventing Concept Inhibition in Diffusion Models [58.065255696601604]
We use compositional property of diffusion models, which allows to leverage multiple prompts in a single image generation.
We argue that it is essential to consider all possible approaches to image generation with diffusion models that can be employed by an adversary.
arXiv Detail & Related papers (2024-04-21T16:35:16Z) - Bridging Generative and Discriminative Models for Unified Visual
Perception with Diffusion Priors [56.82596340418697]
We propose a simple yet effective framework comprising a pre-trained Stable Diffusion (SD) model containing rich generative priors, a unified head (U-head) capable of integrating hierarchical representations, and an adapted expert providing discriminative priors.
Comprehensive investigations unveil potential characteristics of Vermouth, such as varying granularity of perception concealed in latent variables at distinct time steps and various U-net stages.
The promising results demonstrate the potential of diffusion models as formidable learners, establishing their significance in furnishing informative and robust visual representations.
arXiv Detail & Related papers (2024-01-29T10:36:57Z) - Semantic Guidance Tuning for Text-To-Image Diffusion Models [3.3881449308956726]
We propose a training-free approach that modulates the guidance direction of diffusion models during inference.
We first decompose the prompt semantics into a set of concepts, and monitor the guidance trajectory in relation to each concept.
Based on this observation, we devise a technique to steer the guidance direction towards any concept from which the model diverges.
arXiv Detail & Related papers (2023-12-26T09:02:17Z) - Trade-offs in Fine-tuned Diffusion Models Between Accuracy and
Interpretability [5.865936619867771]
We unravel a consequential trade-off between image fidelity as gauged by conventional metrics and model interpretability in generative diffusion models.
We present a set of design principles for the development of truly interpretable generative models.
arXiv Detail & Related papers (2023-03-31T09:11:26Z) - Ablating Concepts in Text-to-Image Diffusion Models [57.9371041022838]
Large-scale text-to-image diffusion models can generate high-fidelity images with powerful compositional ability.
These models are typically trained on an enormous amount of Internet data, often containing copyrighted material, licensed images, and personal photos.
We propose an efficient method of ablating concepts in the pretrained model, preventing the generation of a target concept.
arXiv Detail & Related papers (2023-03-23T17:59:42Z) - Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image
Diffusion Models [103.61066310897928]
Recent text-to-image generative models have demonstrated an unparalleled ability to generate diverse and creative imagery guided by a target text prompt.
While revolutionary, current state-of-the-art diffusion models may still fail in generating images that fully convey the semantics in the given text prompt.
We analyze the publicly available Stable Diffusion model and assess the existence of catastrophic neglect, where the model fails to generate one or more of the subjects from the input prompt.
We introduce the concept of Generative Semantic Nursing (GSN), where we seek to intervene in the generative process on the fly during inference time to improve the faithfulness
arXiv Detail & Related papers (2023-01-31T18:10:38Z)
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.