paper-with-me

Papers

Feature Space Analysis by Guided Diffusion Model

2025-09-09 · Kimiaki Shirahama, Miki Yanobu, Kaduki Yamashita, Miho Ohsaki arxiv

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.

📄 PDF Abstract BibTeX arXiv:2509.07936

Code (0)

등록된 구현이 없습니다.

Tasks

Image Generation

Similar Papers 제목 키워드 기반

DVG-Diffusion: Dual-View Guided Diffusion Model for CT Reconstruction from X-Rays

2025-03-22 · Xing Xie, Jiawei Liu, Huijie Fan, Zhi Han 외

Directly reconstructing 3D CT volume from few-view 2D X-rays using an end-to-end deep learning network is a challenging task, as X-ray images are merely projection views of the 3D CT volume. In this work, we facilitate c…

CT ReconstructionImage to 3D

FSDiffReg: Feature-wise and Score-wise Diffusion-guided Unsupervised Deformable Image Registration for Cardiac Images

2023-07-22 · Yi Qin, Xiaomeng Li

Unsupervised deformable image registration is one of the challenging tasks in medical imaging. Obtaining a high-quality deformation field while preserving deformation topology remains demanding amid a series of deep-lear…

Image Registration

DGSSM: Diffusion guided state-space models for multimodal salient object detection

2026-04-19 · Suklav Ghosh, Arijit Sur, Pinaki Mitra arxiv

Salient object detection (SOD) requires modeling both long-range contextual dependencies and fine-grained structural details, which remains challenging for convolutional, transformer-based, and Mamba-based state space mo…

Salient Object Detection

DocShaDiffusion: Diffusion Model in Latent Space for Document Image Shadow Removal

2025-07-02 · Wenjie Liu, Bingshu Wang, Ze Wang, C. L. Philip Chen arxiv

Document shadow removal is a crucial task in the field of document image enhancement. However, existing methods tend to remove shadows with constant color background and ignore color shadows. In this paper, we first desi…

Image Shadow RemovalImage Enhancement

PRedItOR: Text Guided Image Editing with Diffusion Prior

2023-02-15 · Hareesh Ravi, Sachin Kelkar, Midhun Harikumar, Ajinkya Kale

Diffusion models have shown remarkable capabilities in generating high quality and creative images conditioned on text. An interesting application of such models is structure preserving text guided image editing. Existin…

Decodertext-guided-image-editing