# Visual Feature Attribution using Wasserstein GANs

arXiv: https://arxiv.org/abs/1711.08998 · HTML: https://mlsanity.com/paper/1711.08998/

## Key facts

- Cited by 47 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Nov 2017.

## Built on by (most cited first, 30 of 47)

- [Diffusion Models for Medical Anomaly Detection](https://mlsanity.com/paper/2203.04306/) (2022)
- [Explainable artificial intelligence (XAI) in deep learning-based medical image analysis](https://mlsanity.com/paper/2107.10912/) (2021)
- [Explainable AI (XAI): A Systematic Meta-Survey of Current Challenges and Future Opportunities](https://mlsanity.com/paper/2111.06420/) (2021)
- [Transparency of Deep Neural Networks for Medical Image Analysis: A Review of Interpretability Methods](https://mlsanity.com/paper/2111.02398/) (2021)
- [Delving into Masked Autoencoders for Multi-Label Thorax Disease Classification](https://mlsanity.com/paper/2210.12843/) (2022)
- [Diffusion Models for Counterfactual Generation and Anomaly Detection in Brain Images](https://mlsanity.com/paper/2308.02062/) (2023)
- [ICAM-reg: Interpretable Classification and Regression with Feature Attribution for Mapping Neurological Phenotypes in Individual Scans](https://mlsanity.com/paper/2103.02561/) (2021)
- [Challenges for machine learning in clinical translation of big data imaging studies](https://mlsanity.com/paper/2107.05630/) (2021)
- [Learn-Explain-Reinforce: Counterfactual Reasoning and Its Guidance to Reinforce an Alzheimer's Disease Diagnosis Model](https://mlsanity.com/paper/2108.09451/) (2021)
- [Do Users Benefit From Interpretable Vision? A User Study, Baseline, And Dataset](https://mlsanity.com/paper/2204.11642/) (2022)
- [FakeNews: GAN-based generation of realistic 3D volumetric data -- A systematic review and taxonomy](https://mlsanity.com/paper/2207.01390/) (2022)
- [Morphological feature visualization of Alzheimer's disease via Multidirectional Perception GAN](https://mlsanity.com/paper/2111.12886/) (2021)
- [Jekyll: Attacking Medical Image Diagnostics using Deep Generative Models](https://mlsanity.com/paper/2104.02107/) (2021)
- [Counterfactual Image Synthesis for Discovery of Personalized Predictive Image Markers](https://mlsanity.com/paper/2208.02311/) (2022)
- [Inherently Interpretable Multi-Label Classification Using Class-Specific Counterfactuals](https://mlsanity.com/paper/2303.00500/) (2023)
- [Brainomaly: Unsupervised Neurologic Disease Detection Utilizing Unannotated T1-weighted Brain MR Images](https://mlsanity.com/paper/2302.09200/) (2023)
- [ACAT: Adversarial Counterfactual Attention for Classification and Detection in Medical Imaging](https://mlsanity.com/paper/2303.15421/) (2023)
- [A Framework for Interpretability in Machine Learning for Medical Imaging](https://mlsanity.com/paper/2310.01685/) (2023)
- [Multiscale Metamorphic VAE for 3D Brain MRI Synthesis](https://mlsanity.com/paper/2301.03588/) (2023)
- [Towards Unbiased COVID-19 Lesion Localisation and Segmentation via Weakly Supervised Learning](https://mlsanity.com/paper/2103.00780/) (2021)
- [Distinguishing Healthy Ageing from Dementia: a Biomechanical Simulation of Brain Atrophy using Deep Networks](https://mlsanity.com/paper/2108.08214/) (2021)
- [Generative Adversarial Networks and Other Generative Models](https://mlsanity.com/paper/2207.03887/) (2022)
- [Applications of interpretable deep learning in neuroimaging: a comprehensive review](https://mlsanity.com/paper/2406.17792/) (2024)
- [The Mind's Eye: Visualizing Class-Agnostic Features of CNNs](https://mlsanity.com/paper/2101.12447/) (2021)
- [Leveraging Conditional Generative Models in a General Explanation Framework of Classifier Decisions](https://mlsanity.com/paper/2106.10947/) (2021)
- [Where is the disease? Semi-supervised pseudo-normality synthesis from an abnormal image](https://mlsanity.com/paper/2106.15345/) (2021)
- [Harmonizing Pathological and Normal Pixels for Pseudo-healthy Synthesis](https://mlsanity.com/paper/2203.15347/) (2022)
- [How Well Do Feature-Additive Explainers Explain Feature-Additive Predictors?](https://mlsanity.com/paper/2310.18496/) (2023)
- [Identifying Spurious Correlations using Counterfactual Alignment](https://mlsanity.com/paper/2312.02186/) (2023)
- [VALD-MD: Visual Attribution via Latent Diffusion for Medical Diagnostics](https://mlsanity.com/paper/2401.01414/) (2024)

## Abstract (arXiv)

Attributing the pixels of an input image to a certain category is an important and well-studied problem in computer vision, with applications ranging from weakly supervised localisation to understanding hidden effects in the data. In recent years, approaches based on interpreting a previously trained neural network classifier have become the de facto state-of-the-art and are commonly used on medical as well as natural image datasets. In this paper, we discuss a limitation of these approaches which may lead to only a subset of the category specific features being detected. To address this problem we develop a novel feature attribution technique based on Wasserstein Generative Adversarial Networks (WGAN), which does not suffer from this limitation. We show that our proposed method performs substantially better than the state-of-the-art for visual attribution on a synthetic dataset and on real 3D neuroimaging data from patients with mild cognitive impairment (MCI) and Alzheimer's disease (AD). For AD patients the method produces compellingly realistic disease effect maps which are very close to the observed effects.