# FeatInv: Spatially resolved mapping from feature space to input space using conditional diffusion models

arXiv: https://arxiv.org/abs/2505.21032 · HTML: https://mlsanity.com/paper/2505.21032/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 27 of its 36 references that are in the map.
- First posted on arXiv 27 May 2025.

## Placed in

- Diffusion models / [Diffusion foundations and sampling](https://mlsanity.com/diffusion/diffusion-foundations-and-sampling/)

## Builds on (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Natural Adversarial Examples](https://mlsanity.com/paper/1907.07174/) (2019)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [Perceiver: General Perception with Iterative Attention](https://mlsanity.com/paper/2103.03206/) (2021)
- [GLIGEN: Open-Set Grounded Text-to-Image Generation](https://mlsanity.com/paper/2301.07093/) (2023)
- [Network Dissection: Quantifying Interpretability of Deep Visual Representations](https://mlsanity.com/paper/1704.05796/) (2017)
- [Diffusion Autoencoders: Toward a Meaningful and Decodable Representation](https://mlsanity.com/paper/2111.15640/) (2021)
- [Mechanistic Interpretability for AI Safety -- A Review](https://mlsanity.com/paper/2404.14082/) (2024)
- [ResNet strikes back: An improved training procedure in timm](https://mlsanity.com/paper/2110.00476/) (2021)
- [Generating Images with Perceptual Similarity Metrics based on Deep Networks](https://mlsanity.com/paper/1602.02644/) (2016)
- [Text Embeddings Reveal (Almost) As Much As Text](https://mlsanity.com/paper/2310.06816/) (2023)
- [Synthesizing the preferred inputs for neurons in neural networks via deep generator networks](https://mlsanity.com/paper/1605.09304/) (2016)
- [A Practical Review of Mechanistic Interpretability for Transformer-Based Language Models](https://mlsanity.com/paper/2407.02646/) (2024)
- [A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation](https://mlsanity.com/paper/2306.07304/) (2023)
- [Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Tasks](https://mlsanity.com/paper/2310.19909/) (2023)
- [High Fidelity Visualization of What Your Self-Supervised Representation Knows About](https://mlsanity.com/paper/2112.09164/) (2021)
- [A Disentangling Invertible Interpretation Network for Explaining Latent Representations](https://mlsanity.com/paper/2004.13166/) (2020)
- [Multi-dimensional concept discovery (MCD): A unifying framework with completeness guarantees](https://mlsanity.com/paper/2301.11911/) (2023)
- [Towards Artistic Image Aesthetics Assessment: a Large-scale Dataset and a New Method](https://mlsanity.com/paper/2303.15166/) (2023)
- [A Survey of Diffusion Based Image Generation Models: Issues and Their Solutions](https://mlsanity.com/paper/2308.13142/) (2023)
- [A Practical Method for Generating String Counterfactuals](https://mlsanity.com/paper/2402.11355/) (2024)

## Built on by (most cited first, 2 of 2)

- [ProtoMask: Segmentation-Guided Prototype Learning](https://mlsanity.com/paper/2510.00683/) (2025)
- [How Far Does a Shared Linear Map Go? Probing Feature-Space Manipulability for Image Editing](https://mlsanity.com/paper/2605.11203/) (2026)

## Abstract (arXiv)

Internal representations are crucial for understanding deep neural networks, such as their properties and reasoning patterns, but remain difficult to interpret. While mapping from feature space to input space aids in interpreting the former, existing approaches often rely on crude approximations. We propose using a conditional diffusion model - a pretrained high-fidelity diffusion model conditioned on spatially resolved feature maps - to learn such a mapping in a probabilistic manner. We demonstrate the feasibility of this approach across various pretrained image classifiers from CNNs to ViTs, showing excellent reconstruction capabilities. Through qualitative comparisons and robustness analysis, we validate our method and showcase possible applications, such as the visualization of concept steering in input space or investigations of the composite nature of the feature space. This approach has broad potential for improving feature space understanding in computer vision models.