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

• URL: http://arxiv.org/abs/2505.21032v1
• Date: Tue, 27 May 2025 11:07:34 GMT
• Title: FeatInv: Spatially resolved mapping from feature space to input space using conditional diffusion models
• Authors: Nils Neukirch, Johanna Vielhaben, Nils Strodthoff,
• Abstract summary: Internal representations are crucial for understanding deep neural networks.<n>While mapping from feature space to input space aids in interpreting the former, existing approaches often rely on crude approximations.<n>We propose using a conditional diffusion model to learn such a mapping in a probabilistic manner.
• Score: 0.9503773054285559
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing [62.447497430479174]
  Drawing to reason in space is a novel paradigm that enables LVLMs to reason through elementary drawing operations in the visual space.<n>Our model, named VILASR, consistently outperforms existing methods across diverse spatial reasoning benchmarks.
  arXiv  Detail & Related papers  (2025-06-11T17:41:50Z)
• The Origins of Representation Manifolds in Large Language Models [52.68554895844062]
  We show that cosine similarity in representation space may encode the intrinsic geometry of a feature through shortest, on-manifold paths.<n>The critical assumptions and predictions of the theory are validated on text embeddings and token activations of large language models.
  arXiv  Detail & Related papers  (2025-05-23T13:31:22Z)
• Decoding Diffusion: A Scalable Framework for Unsupervised Analysis of Latent Space Biases and Representations Using Natural Language Prompts [68.48103545146127]
  This paper proposes a novel framework for unsupervised exploration of diffusion latent spaces. We directly leverage natural language prompts and image captions to map latent directions. Our method provides a more scalable and interpretable understanding of the semantic knowledge encoded within diffusion models.
  arXiv  Detail & Related papers  (2024-10-25T21:44:51Z)
• LatentBKI: Open-Dictionary Continuous Mapping in Visual-Language Latent Spaces with Quantifiable Uncertainty [6.986230616834552]
  This paper introduces a novel probabilistic mapping algorithm, LatentBKI, which enables open-vocabulary mapping with quantifiable uncertainty.<n>LatentBKI is evaluated against similar explicit semantic mapping and VL mapping frameworks on the popular Matterport3D and Semantic KITTI datasets.<n>Real-world experiments demonstrate applicability to challenging indoor environments.
  arXiv  Detail & Related papers  (2024-10-15T17:02:32Z)
• Input Space Mode Connectivity in Deep Neural Networks [5.8470747480006695]
  We extend the concept of loss landscape mode connectivity to the input space of deep neural networks. We present theoretical and empirical evidence of its presence in the input space of deep networks. We exploit mode connectivity to obtain new insights about adversarial examples and demonstrate its potential for adversarial detection.
  arXiv  Detail & Related papers  (2024-09-09T17:03:43Z)
• Latent Functional Maps: a spectral framework for representation alignment [34.20582953800544]
  We introduce a multi-purpose framework to the representation learning community, which allows to: (i) compare different spaces in an interpretable way and measure their intrinsic similarity; (ii) find correspondences between them, both in unsupervised and weakly supervised settings, and (iii) to effectively transfer representations between distinct spaces. We validate our framework on various applications, ranging from stitching to retrieval tasks, and on multiple modalities, demonstrating that Latent Functional Maps can serve as a swiss-army knife for representation alignment.
  arXiv  Detail & Related papers  (2024-06-20T10:43:28Z)
• Diffusion Features to Bridge Domain Gap for Semantic Segmentation [2.8616666231199424]
  This paper investigates the approach that leverages the sampling and fusion techniques to harness the features of diffusion models efficiently. By leveraging the strength of text-to-image generation capability, we introduce a new training framework designed to implicitly learn posterior knowledge from it.
  arXiv  Detail & Related papers  (2024-06-02T15:33:46Z)
• Diffusion Model with Cross Attention as an Inductive Bias for Disentanglement [58.9768112704998]
  Disentangled representation learning strives to extract the intrinsic factors within observed data. We introduce a new perspective and framework, demonstrating that diffusion models with cross-attention can serve as a powerful inductive bias. This is the first work to reveal the potent disentanglement capability of diffusion models with cross-attention, requiring no complex designs.
  arXiv  Detail & Related papers  (2024-02-15T05:07:54Z)
• Transforming Feature Space to Interpret Machine Learning Models [91.62936410696409]
  This contribution proposes a novel approach that interprets machine-learning models through the lens of feature space transformations. It can be used to enhance unconditional as well as conditional post-hoc diagnostic tools. A case study on remote-sensing landcover classification with 46 features is used to demonstrate the potential of the proposed approach.
  arXiv  Detail & Related papers  (2021-04-09T10:48:11Z)
• Evidential Sparsification of Multimodal Latent Spaces in Conditional Variational Autoencoders [63.46738617561255]
  We consider the problem of sparsifying the discrete latent space of a trained conditional variational autoencoder. We use evidential theory to identify the latent classes that receive direct evidence from a particular input condition and filter out those that do not. Experiments on diverse tasks, such as image generation and human behavior prediction, demonstrate the effectiveness of our proposed technique.
  arXiv  Detail & Related papers  (2020-10-19T01:27:21Z)
• A generalizable saliency map-based interpretation of model outcome [1.14219428942199]
  We propose a non-intrusive interpretability technique that uses the input and output of the model to generate a saliency map. Experiments show that our interpretability method can reconstruct the salient part of the input with a classification accuracy of 89%.
  arXiv  Detail & Related papers  (2020-06-16T20:34:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.