用扩散模型精准生成指定特征的图像，揭示神经网络如何编码视觉属性。
Feature Space Analysis by Guided Diffusion Model
- 基于预训练扩散模型，通过引导反向生成使图像特征逼近用户指定目标。
- 生成图像的特征与指定特征的欧氏距离极小，验证了特征空间的可解析性。
- 无需额外训练，单块消费级显卡即可运行，适合快速分析多种视觉模型。
深度神经网络内部特征提取过程存在黑箱问题。针对视觉领域，本文提出一种解码器，可生成特征与用户指定特征高度匹配的图像。该解码器采用引导扩散模型，在反向生成过程中最小化每一步生成图像特征与目标特征的欧氏距离，确保匹配可靠性。相比以往方法，此设计首次实现了特征匹配的确定性保证。实验以CLIP图像编码器、ResNet-50和视觉变换器为目标，结果表明生成图像特征与指定特征高度一致，并揭示了不同模型对颜色、纹理、语义等属性的编码方式。该方法无需额外训练，可在单块消费级GPU上运行，具备高效、通用优势。
原文摘要 · Abstract (English)
One of the key issues in Deep Neural Networks (DNNs) is the black-box nature of their internal feature extraction process. Targeting vision-related domains, this paper focuses on analysing the feature space of a DNN by proposing a decoder that can generate images whose features are guaranteed to closely match a user-specified feature. Owing to this guarantee that is missed in past studies, our decoder allows us to evidence which of various image attributes are encoded into the user-specified feature. Our decoder is implemented as a guided diffusion model that guides the reverse image generation of a pre-trained diffusion model to minimise the Euclidean distance between the feature of a clean image estimated at each step and the user-specified feature. One practical advantage of our decoder is that it can analyse feature spaces of different DNNs with no additional training and run on a single COTS GPU. The experimental results targeting CLIP's image encoder, ResNet-50 and vision transformer demonstrate that images generated by our decoder have features remarkably similar to the user-specified ones and reveal valuable insights into these DNNs' feature spaces.
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。