mlsanityData to 7 Oct 2026

Discovering Causal Signals in Images

arXiv 1605.08179 ↗First posted 26 May 2016stat.ML cs.CVcited by 79

Not on the map. Why?

Abstract (arXiv)

This paper establishes the existence of observable footprints that reveal the "causal dispositions" of the object categories appearing in collections of images. We achieve this goal in two steps. First, we take a learning approach to observational causal discovery, and build a classifier that achieves state-of-the-art performance on finding the causal direction between pairs of random variables, given samples from their joint distribution. Second, we use our causal direction classifier to effectively distinguish between features of objects and features of their contexts in collections of static images. Our experiments demonstrate the existence of a relation between the direction of causality and the difference between objects and their contexts, and by the same token, the existence of observable signals that reveal the causal dispositions of objects.

Key facts. Cited by 79 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 May 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2019: 1; 2020: 0; 2021: 20; 2022: 14; 2023: 17; 2024: 15; 2025: 8; 2026: 4.

79 papers.

Sort:

By area:

  1. 2019Causal Confusion in Imitation Learningcited by 286
  2. 2021Towards Causal Representation Learningcited by 207
  3. 2021Deep Stable Learning for Out-Of-Distribution Generalizationcited by 153
  4. 2021You are AllSet: A Multiset Function Framework for Hypergraph Neural Networkscited by 124
  5. 2021Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identificationcited by 114
  6. 2023Nonparametric Identifiability of Causal Representations from Unknown Interventionscited by 105
  7. 2021Interventional Video Grounding with Dual Contrastive Learningcited by 94
  8. 2021A Survey on Bias in Visual Datasetscited by 84
  9. 2021Evading the Simplicity Bias: Training a Diverse Set of Models Discovers Solutions with Superior OOD Generalizationcited by 83
  10. 2021Generalizing Graph Neural Networks on Out-Of-Distribution Graphscited by 69
  11. 2021Learning latent causal graphs via mixture oraclescited by 55
  12. 2021Human Trajectory Prediction via Counterfactual Analysiscited by 42
38 more
  1. 2022Continual Normalization: Rethinking Batch Normalization for Online Continual Learningcited by 40
  2. 2022From Statistical to Causal Learningcited by 40
  3. 2021ACRE: Abstract Causal REasoning Beyond Covariationcited by 30
  4. 2022Debiased Graph Neural Networks with Agnostic Label Selection Biascited by 25
  5. 2023A Closer Look at In-Context Learning under Distribution Shiftscited by 25
  6. 2024Robust Emotion Recognition in Context Debiasingcited by 24
  7. 2023Causal Reinforcement Learning: A Surveycited by 22
  8. 2022Image-based Treatment Effect Heterogeneitycited by 20
  9. 2022Counterfactual Intervention Feature Transfer for Visible-Infrared Person Re-identificationcited by 18
  10. 2021Object-Aware Regularization for Addressing Causal Confusion in Imitation Learningcited by 16
  11. 2022Towards Domain Generalization in Object Detectioncited by 16
  12. 2023New Insights for the Stability-Plasticity Dilemma in Online Continual Learningcited by 16
  13. 2021XAI Handbook: Towards a Unified Framework for Explainable AIcited by 14
  14. 2023Cross-Modal Causal Intervention for Medical Report Generationcited by 14
  15. 2022Disentangle and Remerge: Interventional Knowledge Distillation for Few-Shot Object Detection from A Conditional Causal Perspectivecited by 13
  16. 2021Extracting Causal Visual Features for Limited label Classificationcited by 12
  17. 2021Contrastive Reasoning in Neural Networkscited by 11
  18. 2021Towards Unbiased Visual Emotion Recognition via Causal Interventioncited by 11
  19. 2021ML4C: Seeing Causality Through Latent Vicinitycited by 11
  20. 2022Explanatory Paradigms in Neural Networkscited by 11
  21. 2025Visual Jenga: Discovering Object Dependencies via Counterfactual Inpaintingcited by 11
  22. 2024Learning by Watching: A Review of Video-based Learning Approaches for Robot Manipulationcited by 10
  23. 2024CELLO: Causal Evaluation of Large Vision-Language Modelscited by 10
  24. 2025Fair Deepfake Detectors Can Generalizecited by 7
  25. 2021Mini-Batch Consistent Slot Set Encoder for Scalable Set Encodingcited by 6
  26. 2023Causal Clothes-Invariant Feature Learning for Cloth-Changing Person Re-IDcited by 6
  27. 2023CAT-Walk: Inductive Hypergraph Learning via Set Walkscited by 6
  28. 2023Predictive Coding beyond Correlationscited by 6
  29. 2023RobustCLEVR: A Benchmark and Framework for Evaluating Robustness in Object-centric Learningcited by 6
  30. 2023Causality-Driven One-Shot Learning for Prostate Cancer Grading from MRIcited by 6
  31. 2024Towards Deconfounded Image-Text Matching with Causal Inferencecited by 6
  32. 2024Facial Action Unit Detection by Adaptively Constraining Self-Attention and Causally Deconfounding Samplecited by 6
  33. 2022Learning Latent Structural Causal Modelscited by 5
  34. 2024Dynamically Anchored Prompting for Task-Imbalanced Continual Learningcited by 5
  35. 2021iReason: Multimodal Commonsense Reasoning using Videos and Natural Language with Interpretabilitycited by 4
  36. 2021Encoding Causal Macrovariablescited by 4
  37. 2022A Review and Roadmap of Deep Learning Causal Discovery in Different Variable Paradigmscited by 4
  38. 2025Causal-LLaVA: Causal Disentanglement for Mitigating Hallucination in Multimodal Large Language Modelscited by 4

50 most cited of 79 All 79 (JSON)