mlsanityData to 14 Oct 2026

Feature Space Analysis by Guided Diffusion Model

arXiv 2509.07936 ↗First posted 9 Sep 2025cs.CV eess.IVcited by 0

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

This paper aims to analyse the feature space of a vision-related Deep Neural Network (DNN) by proposing a decoder that can generate an image whose feature closely matches a user-specified feature. Supported by quantitative evidence of its high feature-matching accuracy, our decoder facilitates precise analysis of the DNN's feature space. Our decoder is implemented as a guided diffusion model that guides the 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. The key advantages of our decoder are its training-free applicability to analyse the feature spaces of different DNNs and its practical feasibility on a single COTS GPU. The experiments targeting CLIP's image encoder and ResNet-50 demonstrate the effectiveness of our decoder both as a feature-matching image generator and as a visual feature space analyser. The codes and data are available at https://github.com/ccilab-doshisha/FeatDec

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 47 of its 61 references that are in the map. First posted on arXiv 9 Sep 2025.

Builds on

47 of 61 references.

Closest ancestors · 14

Same direction, newest first

  1. 2025Test-Time Scaling of Diffusion Models via Noise Trajectory Search24 May
  2. 2025Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps16 Jan
  3. 2024Learning to Discretize Denoising Diffusion ODEs24 May
  4. 2023Fast Training of Diffusion Models with Masked Transformers15 Jun
  5. 2023Patch Diffusion: Faster and More Data-Efficient Training of Diffusion Models25 Apr
  6. 2023Universal Guidance for Diffusion Models14 Feb
  7. 2023UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Models9 Feb
  8. 2022Classifier-Free Diffusion Guidance26 Jul
  9. 2022Diffusion models as plug-and-play priors17 Jun
  10. 2022Learning Fast Samplers for Diffusion Models by Differentiating Through Sample Quality11 Feb
  11. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  12. 2021Diffusion Models Beat GANs on Image Synthesis11 May
2 more
  1. 2020Denoising Diffusion Implicit Models6 Oct
  2. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 33

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  5. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  6. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  7. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  8. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  9. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,614
  10. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,898
  11. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,431
  12. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,430
21 more
  1. 2022Exploring CLIP for Assessing the Look and Feel of Imagescited by 991
  2. 2023Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Modelscited by 702
  3. 2022Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Modelcited by 583
  4. 2022Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learningcited by 561
  5. 2020What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimationcited by 497
  6. 2014Long-term Recurrent Convolutional Networks for Visual Recognition and Descriptioncited by 484
  7. 2014Understanding Deep Image Representations by Inverting Themcited by 403
  8. 2023Diffusion Self-Guidance for Controllable Image Generationcited by 305
  9. 2023Text Embeddings Reveal (Almost) As Much As Textcited by 192
  10. 2023Language Model Inversioncited by 68
  11. 2021High Fidelity Visualization of What Your Self-Supervised Representation Knows Aboutcited by 66
  12. 2024Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Modelscited by 57
  13. 2024Inference-Time Alignment of Diffusion Models with Direct Noise Optimizationcited by 55
  14. 2022CLIP Itself is a Strong Fine-tuner: Achieving 85.7% and 88.0% Top-1 Accuracy with ViT-B and ViT-L on ImageNetcited by 35
  15. 2023Bridging Discrete and Backpropagation: Straight-Through and Beyondcited by 31
  16. 2022From t-SNE to UMAP with contrastive learningcited by 28
  17. 2023Predicated Diffusion: Predicate Logic-Based Attention Guidance for Text-to-Image Diffusion Modelscited by 16
  18. 2022Measures of Information Reflect Memorization Patternscited by 12
  19. 2021Understanding Invariance via Feedforward Inversion of Discriminatively Trained Classifierscited by 11
  20. 2024Unlocking Visual Secrets: Inverting Features with Diffusion Priors for Image Reconstructioncited by 5
  21. 2025Implicit Inversion turns CLIP into a Decodercited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025FeatInv: Spatially resolved mapping from feature space to input space using conditional diffusion models
  2. 2024Decoding Diffusion: A Scalable Framework for Unsupervised Analysis of Latent Space Biases and Representations Using Natural Language Prompts
  3. 2022Unifying Diffusion Models' Latent Space, with Applications to CycleDiffusion and Guidance
  4. 2021Diffusion Autoencoders: Toward a Meaningful and Decodable Representation
  5. 2023Variational Diffusion Auto-encoder: Latent Space Extraction from Pre-trained Diffusion Models
  6. 2022Exploring Vision Transformers as Diffusion Learners
  7. 2023Diffusion Models Beat GANs on Image Classification
  8. 2023Unsupervised Discovery of Interpretable Directions in h-space of Pre-trained Diffusion Models