用B-cos模块让文生图模型生成过程可解释，看清每个词如何影响图像。
Interpretable Diffusion Models with B-cos Networks
- 引入B-cos模块构建可解释的文生图扩散模型
- 能准确反映提示词与图像的语义对齐关系
- 适合需要理解生成逻辑的AI研究者和应用开发
文生图扩散模型通过迭代去噪随机噪声生成图像，条件为文本提示。尽管该技术推动了图像生成的进展，但常无法准确体现提示中所有语义信息，且此类失败难以自动检测。本文提出一种基于B-cos模块构建的扩散模型架构，具备内在可解释性。该方法能揭示每个提示词如何影响生成图像，通过可视化受各词影响的像素区域提供解释。实验表明，B-cos扩散模型在保持高质量图像生成的同时，可提供有意义的提示-图像对齐洞察。
原文摘要 · Abstract (English)
Text-to-image diffusion models generate images by iteratively denoising random noise, conditioned on a prompt. While these models have enabled impressive progress in image generation, they often fail to accurately reflect all semantic information described in the prompt -- failures that are difficult to detect automatically. In this work, we introduce a diffusion model architecture built with B-cos modules that offers inherent interpretability. Our approach provides insight into how individual prompt tokens affect the generated image by producing explanations that highlight the pixel regions influenced by each token. We demonstrate that B-cos diffusion models can produce high-quality images while providing meaningful insights into prompt-image alignment.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。