Hierarchical Variational Autoencoder for Visual Counterfactuals
Not on the map. Why?
Abstract (arXiv)
Conditional Variational Auto Encoders (VAE) are gathering significant attention as an Explainable Artificial Intelligence (XAI) tool. The codes in the latent space provide a theoretically sound way to produce counterfactuals, i.e. alterations resulting from an intervention on a targeted semantic feature. To be applied on real images more complex models are needed, such as Hierarchical CVAE. This comes with a challenge as the naive conditioning is no longer effective. In this paper we show how relaxing the effect of the posterior leads to successful counterfactuals and we introduce VAEX an Hierarchical VAE designed for this approach that can visually audit a classifier in applications.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 22 of its 32 references that are in the map. First posted on arXiv 1 Feb 2021.
Builds on
22 of 32 references.
References · 22
- 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
- 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
- 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
- 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
- 2017Squeeze-and-Excitation Networkscited by 4,789
- 2014Deep Learning Face Attributes in the Wildcited by 3,693
- 2017Axiomatic Attribution for Deep Networkscited by 3,384
- 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 2,010
- 2019An Introduction to Variational Autoencoderscited by 1,000
- 2017Causal Effect Inference with Deep Latent-Variable Modelscited by 410
- 2019A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAIcited by 404
- 2016Ladder Variational Autoencoderscited by 318
10 more
- 2017AttGAN: Facial Attribute Editing by Only Changing What You Wantcited by 242
- 2016Variational Lossy Autoencodercited by 176
- 2019Learning Model-Agnostic Counterfactual Explanations for Tabular Datacited by 146
- 2019BIVA: A Very Deep Hierarchy of Latent Variables for Generative Modelingcited by 109
- 2020Good Counterfactuals and Where to Find Them: A Case-Based Technique for Generating Counterfactuals for Explainable AI (XAI)cited by 79
- 2017A causal framework for explaining the predictions of black-box sequence-to-sequence modelscited by 58
- 2018Counterfactuals uncover the modular structure of deep generative modelscited by 51
- 2020Balancing reconstruction error and Kullback-Leibler divergence in Variational Autoencoderscited by 30
- 2019Counterfactual Reasoning for Fair Clinical Risk Predictioncited by 28
- 2020Plausible Counterfactuals: Auditing Deep Learning Classifiers with Realistic Adversarial Examplescited by 9
Built on by
Citing papers per year: 2024: 1.
1 paper.