# Generative Interventions for Causal Learning

arXiv: https://arxiv.org/abs/2012.12265 · HTML: https://mlsanity.com/paper/2012.12265/

## Key facts

- Cited by 45 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Dec 2020.

## Built on by (most cited first, 30 of 45)

- [Fake it till you make it: Learning transferable representations from synthetic ImageNet clones](https://mlsanity.com/paper/2212.08420/) (2022)
- [Generative Models as a Data Source for Multiview Representation Learning](https://mlsanity.com/paper/2106.05258/) (2021)
- [GAN-Supervised Dense Visual Alignment](https://mlsanity.com/paper/2112.05143/) (2021)
- [Ensembling with Deep Generative Views](https://mlsanity.com/paper/2104.14551/) (2021)
- [Faithful Explanations of Black-box NLP Models Using LLM-generated Counterfactuals](https://mlsanity.com/paper/2310.00603/) (2023)
- [Discrete Representations Strengthen Vision Transformer Robustness](https://mlsanity.com/paper/2111.10493/) (2021)
- [OrphicX: A Causality-Inspired Latent Variable Model for Interpreting Graph Neural Networks](https://mlsanity.com/paper/2203.15209/) (2022)
- [Beyond the Contact: Discovering Comprehensive Affordance for 3D Objects from Pre-trained 2D Diffusion Models](https://mlsanity.com/paper/2401.12978/) (2024)
- [Causal Reasoning Meets Visual Representation Learning: A Prospective Study](https://mlsanity.com/paper/2204.12037/) (2022)
- [Self-Interpretable Time Series Prediction with Counterfactual Explanations](https://mlsanity.com/paper/2306.06024/) (2023)
- [Causal Transportability for Visual Recognition](https://mlsanity.com/paper/2204.12363/) (2022)
- [General Intelligence Requires Rethinking Exploration](https://mlsanity.com/paper/2211.07819/) (2022)
- [Causal Deep Learning](https://mlsanity.com/paper/2303.02186/) (2023)
- [CHORUS: Learning Canonicalized 3D Human-Object Spatial Relations from Unbounded Synthesized Images](https://mlsanity.com/paper/2308.12288/) (2023)
- [LARGE: Latent-Based Regression through GAN Semantics](https://mlsanity.com/paper/2107.11186/) (2021)
- [Convolutional Visual Prompt for Robust Visual Perception](https://mlsanity.com/paper/2303.00198/) (2023)
- [A Review of the Role of Causality in Developing Trustworthy AI Systems](https://mlsanity.com/paper/2302.06975/) (2023)
- [Data Augmentations for Improved (Large) Language Model Generalization](https://mlsanity.com/paper/2310.12803/) (2023)
- [GDA: Generalized Diffusion for Robust Test-time Adaptation](https://mlsanity.com/paper/2404.00095/) (2024)
- [Causal reasoning in typical computer vision tasks](https://mlsanity.com/paper/2307.13992/) (2023)
- [Interpreting and Controlling Vision Foundation Models via Text Explanations](https://mlsanity.com/paper/2310.10591/) (2023)
- [Emerging Synergies in Causality and Deep Generative Models: A Survey](https://mlsanity.com/paper/2301.12351/) (2023)
- [Instrumental Variable-Driven Domain Generalization with Unobserved Confounders](https://mlsanity.com/paper/2110.01438/) (2021)
- [Better May Not Be Fairer: A Study on Subgroup Discrepancy in Image Classification](https://mlsanity.com/paper/2212.08649/) (2022)
- [Instance-Conditioned GAN Data Augmentation for Representation Learning](https://mlsanity.com/paper/2303.09677/) (2023)
- [Rating Sentiment Analysis Systems for Bias through a Causal Lens](https://mlsanity.com/paper/2302.02038/) (2023)
- [Advances in Automatically Rating the Trustworthiness of Text Processing Services](https://mlsanity.com/paper/2302.09079/) (2023)
- [RobustCLEVR: A Benchmark and Framework for Evaluating Robustness in Object-centric Learning](https://mlsanity.com/paper/2308.14899/) (2023)
- [3D Magic Mirror: Clothing Reconstruction from a Single Image via a Causal Perspective](https://mlsanity.com/paper/2204.13096/) (2022)
- [Out of Distribution Generalization via Interventional Style Transfer in Single-Cell Microscopy](https://mlsanity.com/paper/2306.11890/) (2023)

## Abstract (arXiv)

We introduce a framework for learning robust visual representations that generalize to new viewpoints, backgrounds, and scene contexts. Discriminative models often learn naturally occurring spurious correlations, which cause them to fail on images outside of the training distribution. In this paper, we show that we can steer generative models to manufacture interventions on features caused by confounding factors. Experiments, visualizations, and theoretical results show this method learns robust representations more consistent with the underlying causal relationships. Our approach improves performance on multiple datasets demanding out-of-distribution generalization, and we demonstrate state-of-the-art performance generalizing from ImageNet to ObjectNet dataset.