paper-with-me

Papers

Self-Discovering Interpretable Diffusion Latent Directions for Responsible Text-to-Image Generation

2023-11-28 · CVPR 2024 1 · Hang Li, Chengzhi Shen, Philip Torr, Volker Tresp, Jindong Gu

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}.

📄 PDF Abstract BibTeX arXiv:2311.17216

Code (1)

hangligit/InterpretDiffusion jax

Tasks

Image GenerationText to Image GenerationText-to-Image Generation

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Discovering Interpretable Directions in the Semantic Latent Space of Diffusion Models

2023-03-20 · René Haas, Inbar Huberman-Spiegelglas, Rotem Mulayoff, Stella Graßhof 외

Denoising Diffusion Models (DDMs) have emerged as a strong competitor to Generative Adversarial Networks (GANs). However, despite their widespread use in image synthesis and editing applications, their latent space is st…

AttributeDenoisingImage Generation

Discovering Concept Directions from Diffusion-based Counterfactuals via Latent Clustering

2025-05-11 · Payal Varshney, Adriano Lucieri, Christoph Balada, Andreas Dengel 외

Concept-based explanations have emerged as an effective approach within Explainable Artificial Intelligence, enabling interpretable insights by aligning model decisions with human-understandable concepts. However, existi…

ClusteringcounterfactualExplainable artificial intelligence

Self-supervised Enhancement of Latent Discovery in GANs

2021-12-16 · Silpa Vadakkeeveetil Sreelatha, Adarsh Kappiyath, S Sumitra

Several methods for discovering interpretable directions in the latent space of pre-trained GANs have been proposed. Latent semantics discovered by unsupervised methods are relatively less disentangled than supervised me…

AttributeDisentanglementImage RetrievalRetrieval

DebiasDiff: Debiasing Text-to-image Diffusion Models with Self-discovering Latent Attribute Directions

2024-12-25 · Yilei Jiang, Weihong Li, Yiyuan Zhang, Minghong Cai 외

While Diffusion Models (DM) exhibit remarkable performance across various image generative tasks, they nonetheless reflect the inherent bias presented in the training set. As DMs are now widely used in real-world applica…

Attribute

Self-Attention Decomposition For Training Free Diffusion Editing

2025-10-26 · Tharun Anand, Mohammad Hassan Vali, Arno Solin, Green Rosh 외 arxiv

Diffusion models achieve remarkable fidelity in image synthesis, yet precise control over their outputs for targeted editing remains challenging. A key step toward controllability is to identify interpretable directions …