# Visual Causal Feature Learning

arXiv: https://arxiv.org/abs/1412.2309 · HTML: https://mlsanity.com/paper/1412.2309/

## Key facts

- Cited by 59 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Dec 2014.

## Built on by (most cited first, 30 of 59)

- [Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability](https://mlsanity.com/paper/2301.04709/) (2023)
- [Weakly supervised causal representation learning](https://mlsanity.com/paper/2203.16437/) (2022)
- [CITRIS: Causal Identifiability from Temporal Intervened Sequences](https://mlsanity.com/paper/2202.03169/) (2022)
- [Distilling Causal Effect of Data in Class-Incremental Learning](https://mlsanity.com/paper/2103.01737/) (2021)
- [Nonparametric Identifiability of Causal Representations from Unknown Interventions](https://mlsanity.com/paper/2306.00542/) (2023)
- [Interventional Video Grounding with Dual Contrastive Learning](https://mlsanity.com/paper/2106.11013/) (2021)
- [Towards Principled Disentanglement for Domain Generalization](https://mlsanity.com/paper/2111.13839/) (2021)
- [Desiderata for Representation Learning: A Causal Perspective](https://mlsanity.com/paper/2109.03795/) (2021)
- [How Deep Learning Sees the World: A Survey on Adversarial Attacks & Defenses](https://mlsanity.com/paper/2305.10862/) (2023)
- [Learning latent causal graphs via mixture oracles](https://mlsanity.com/paper/2106.15563/) (2021)
- [Human Trajectory Prediction via Counterfactual Analysis](https://mlsanity.com/paper/2107.14202/) (2021)
- [Causal Effect Identification in Cluster DAGs](https://mlsanity.com/paper/2202.12263/) (2022)
- [Learning nonparametric latent causal graphs with unknown interventions](https://mlsanity.com/paper/2306.02899/) (2023)
- [Compositional Abstraction Error and a Category of Causal Models](https://mlsanity.com/paper/2103.15758/) (2021)
- [Neural Algorithmic Reasoning with Causal Regularisation](https://mlsanity.com/paper/2302.10258/) (2023)
- [OLIVES Dataset: Ophthalmic Labels for Investigating Visual Eye Semantics](https://mlsanity.com/paper/2209.11195/) (2022)
- [Robust Emotion Recognition in Context Debiasing](https://mlsanity.com/paper/2403.05963/) (2024)
- [Causal Abstraction with Soft Interventions](https://mlsanity.com/paper/2211.12270/) (2022)
- [Image-based Treatment Effect Heterogeneity](https://mlsanity.com/paper/2206.06417/) (2022)
- [Counterfactual Intervention Feature Transfer for Visible-Infrared Person Re-identification](https://mlsanity.com/paper/2208.00967/) (2022)
- [The Landscape of Causal Discovery Data: Grounding Causal Discovery in Real-World Applications](https://mlsanity.com/paper/2412.01953/) (2024)
- [The Blessings of Unlabeled Background in Untrimmed Videos](https://mlsanity.com/paper/2103.13183/) (2021)
- [Targeted Reduction of Causal Models](https://mlsanity.com/paper/2311.18639/) (2023)
- [Causal models in string diagrams](https://mlsanity.com/paper/2304.07638/) (2023)
- [On the Equivalence of Causal Models: A Category-Theoretic Approach](https://mlsanity.com/paper/2201.06981/) (2022)
- [Towards Unbiased Visual Emotion Recognition via Causal Intervention](https://mlsanity.com/paper/2107.12096/) (2021)
- [Explanatory Paradigms in Neural Networks](https://mlsanity.com/paper/2202.11838/) (2022)
- [Beyond Object Recognition: A New Benchmark towards Object Concept Learning](https://mlsanity.com/paper/2212.02710/) (2022)
- [Toward Falsifying Causal Graphs Using a Permutation-Based Test](https://mlsanity.com/paper/2305.09565/) (2023)
- [Enhancing Adversarial Contrastive Learning via Adversarial Invariant Regularization](https://mlsanity.com/paper/2305.00374/) (2023)

## Abstract (arXiv)

We provide a rigorous definition of the visual cause of a behavior that is broadly applicable to the visually driven behavior in humans, animals, neurons, robots and other perceiving systems. Our framework generalizes standard accounts of causal learning to settings in which the causal variables need to be constructed from micro-variables. We prove the Causal Coarsening Theorem, which allows us to gain causal knowledge from observational data with minimal experimental effort. The theorem provides a connection to standard inference techniques in machine learning that identify features of an image that correlate with, but may not cause, the target behavior. Finally, we propose an active learning scheme to learn a manipulator function that performs optimal manipulations on the image to automatically identify the visual cause of a target behavior. We illustrate our inference and learning algorithms in experiments based on both synthetic and real data.