# Designing Counterfactual Generators using Deep Model Inversion

arXiv: https://arxiv.org/abs/2109.14274 · HTML: https://mlsanity.com/paper/2109.14274/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 40 references that are in the map.
- First posted on arXiv 29 Sep 2021.

## Builds on (most cited first, 29 of 29)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Implicit Neural Representations with Periodic Activation Functions](https://mlsanity.com/paper/2006.09661/) (2020)
- [Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains](https://mlsanity.com/paper/2006.10739/) (2020)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)](https://mlsanity.com/paper/1902.03368/) (2019)
- [Learning Continuous Image Representation with Local Implicit Image Function](https://mlsanity.com/paper/2012.09161/) (2020)
- [Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion](https://mlsanity.com/paper/1912.08795/) (2019)
- [Understanding Deep Image Representations by Inverting Them](https://mlsanity.com/paper/1412.0035/) (2014)
- [Learning Loss for Active Learning](https://mlsanity.com/paper/1905.03677/) (2019)
- [Counterfactual Visual Explanations](https://mlsanity.com/paper/1904.07451/) (2019)
- [Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives](https://mlsanity.com/paper/1802.07623/) (2018)
- [Interpretable Counterfactual Explanations Guided by Prototypes](https://mlsanity.com/paper/1907.02584/) (2019)
- [Inverting Visual Representations with Convolutional Networks](https://mlsanity.com/paper/1506.02753/) (2015)
- [Explaining Image Classifiers by Counterfactual Generation](https://mlsanity.com/paper/1807.08024/) (2018)
- [Counterfactual Generative Networks](https://mlsanity.com/paper/2101.06046/) (2021)
- [Visualizing Deep Convolutional Neural Networks Using Natural Pre-Images](https://mlsanity.com/paper/1512.02017/) (2015)
- [Explanation by Progressive Exaggeration](https://mlsanity.com/paper/1911.00483/) (2019)
- [Intermediate Layer Optimization for Inverse Problems using Deep Generative Models](https://mlsanity.com/paper/2102.07364/) (2021)
- [CounteRGAN: Generating Realistic Counterfactuals with Residual Generative Adversarial Nets](https://mlsanity.com/paper/2009.05199/) (2020)
- [Accurate and Robust Feature Importance Estimation under Distribution Shifts](https://mlsanity.com/paper/2009.14454/) (2020)

## Built on by (most cited first, 15 of 15)

- [Diffusion Models for Counterfactual Explanations](https://mlsanity.com/paper/2203.15636/) (2022)
- [Mechanistic Mode Connectivity](https://mlsanity.com/paper/2211.08422/) (2022)
- [Adversarial Counterfactual Visual Explanations](https://mlsanity.com/paper/2303.09962/) (2023)
- [Predicting is not Understanding: Recognizing and Addressing Underspecification in Machine Learning](https://mlsanity.com/paper/2207.02598/) (2022)
- [Latent Diffusion Counterfactual Explanations](https://mlsanity.com/paper/2310.06668/) (2023)
- [Global Counterfactual Directions](https://mlsanity.com/paper/2404.12488/) (2024)
- [Rethinking Visual Counterfactual Explanations Through Region Constraint](https://mlsanity.com/paper/2410.12591/) (2024)
- [Principled Knowledge Extrapolation with GANs](https://mlsanity.com/paper/2205.13444/) (2022)
- [SKDCGN: Source-free Knowledge Distillation of Counterfactual Generative Networks using cGANs](https://mlsanity.com/paper/2208.04226/) (2022)
- [Leaping Into Memories: Space-Time Deep Feature Synthesis](https://mlsanity.com/paper/2303.09941/) (2023)
- [Graph Community Augmentation with GMM-based Modeling in Latent Space](https://mlsanity.com/paper/2412.01163/) (2024)
- [Personalized Path Recourse for Reinforcement Learning Agents](https://mlsanity.com/paper/2312.08724/) (2023)
- [Leveraging a Simulator for Learning Causal Representations from Post-Treatment Covariates for CATE](https://mlsanity.com/paper/2502.05037/) (2025)
- [Explaining Low Perception Model Competency with High-Competency Counterfactuals](https://mlsanity.com/paper/2504.05254/) (2025)
- [Targeted Visual Counterfactual Explanations for Contrastive Vision-Language Model](https://mlsanity.com/paper/2609.37638/) (2026)

## Abstract (arXiv)

Explanation techniques that synthesize small, interpretable changes to a given image while producing desired changes in the model prediction have become popular for introspecting black-box models. Commonly referred to as counterfactuals, the synthesized explanations are required to contain discernible changes (for easy interpretability) while also being realistic (consistency to the data manifold). In this paper, we focus on the case where we have access only to the trained deep classifier and not the actual training data. While the problem of inverting deep models to synthesize images from the training distribution has been explored, our goal is to develop a deep inversion approach to generate counterfactual explanations for a given query image. Despite their effectiveness in conditional image synthesis, we show that existing deep inversion methods are insufficient for producing meaningful counterfactuals. We propose DISC (Deep Inversion for Synthesizing Counterfactuals) that improves upon deep inversion by utilizing (a) stronger image priors, (b) incorporating a novel manifold consistency objective and (c) adopting a progressive optimization strategy. We find that, in addition to producing visually meaningful explanations, the counterfactuals from DISC are effective at learning classifier decision boundaries and are robust to unknown test-time corruptions.