mlsanityData to 7 Oct 2026

Causal reasoning in typical computer vision tasks

arXiv 2307.13992 ↗First posted 26 Jul 2023cs.CVcited by 12

On the map: LLM reasoning → Multimodal reasoning

Abstract (arXiv)

Deep learning has revolutionized the field of artificial intelligence. Based on the statistical correlations uncovered by deep learning-based methods, computer vision has contributed to tremendous growth in areas like autonomous driving and robotics. Despite being the basis of deep learning, such correlation is not stable and is susceptible to uncontrolled factors. In the absence of the guidance of prior knowledge, statistical correlations can easily turn into spurious correlations and cause confounders. As a result, researchers are now trying to enhance deep learning methods with causal theory. Causal theory models the intrinsic causal structure unaffected by data bias and is effective in avoiding spurious correlations. This paper aims to comprehensively review the existing causal methods in typical vision and vision-language tasks such as semantic segmentation, object detection, and image captioning. The advantages of causality and the approaches for building causal paradigms will be summarized. Future roadmaps are also proposed, including facilitating the development of causal theory and its application in other complex scenes and systems.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Placed in Multimodal reasoning, one of 17 directions in LLM reasoning. Builds on 58 of its 122 references that are in the map. First posted on arXiv 26 Jul 2023.

Builds on

58 of 122 references.

Closest ancestors · 2

Same direction, newest first

  1. 2022Cross-Modal Causal Relational Reasoning for Event-Level Visual Question Answering26 Jul
  2. 2022Causal Reasoning Meets Visual Representation Learning: A Prospective Study26 Apr

Other references · 56

  1. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,069
  2. 2019OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledgecited by 1,114
  3. 2021CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classificationcited by 806
  4. 2021MViTv2: Improved Multiscale Vision Transformers for Classification and Detectioncited by 516
  5. 2019Unified Vision-Language Pre-Training for Image Captioning and VQAcited by 494
  6. 2021Bottleneck Transformers for Visual Recognitioncited by 364
  7. 2019Meshed-Memory Transformer for Image Captioningcited by 343
  8. 2020Counterfactual VQA: A Cause-Effect Look at Language Biascited by 266
  9. 2020Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effectcited by 256
  10. 2020Causal Intervention for Weakly-Supervised Semantic Segmentationcited by 229
  11. 2020Domain Generalization using Causal Matchingcited by 224
  12. 2020X-Linear Attention Networks for Image Captioningcited by 198
38 more
  1. 2019Causality matters in medical imagingcited by 193
  2. 2022A Survey of Vision-Language Pre-Trained Modelscited by 177
  3. 2021VOLO: Vision Outlooker for Visual Recognitioncited by 164
  4. 2020Counterfactual Samples Synthesizing for Robust Visual Question Answeringcited by 153
  5. 2022Causality Inspired Representation Learning for Domain Generalizationcited by 136
  6. 2019Explaining Classifiers with Causal Concept Effect (CaCE)cited by 135
  7. 2021Causality-inspired Single-source Domain Generalization for Medical Image Segmentationcited by 118
  8. 2021Distilling Causal Effect of Data in Class-Incremental Learningcited by 117
  9. 2020Interventional Few-Shot Learningcited by 112
  10. 2019Towards Causal VQA: Revealing and Reducing Spurious Correlations by Invariant and Covariant Semantic Editingcited by 108
  11. 2022Causal Machine Learning: A Survey and Open Problemscited by 107
  12. 2021CPT: A Pre-Trained Unbalanced Transformer for Both Chinese Language Understanding and Generationcited by 81
  13. 2021Causal Attention for Unbiased Visual Recognitioncited by 80
  14. 2020Monocular Depth Estimation Based On Deep Learning: An Overviewcited by 68
  15. 2022Invariant Grounding for Video Question Answeringcited by 68
  16. 2020Deconfounded Image Captioning: A Causal Retrospectcited by 65
  17. 2020Learning Causal Semantic Representation for Out-of-Distribution Predictioncited by 60
  18. 2020Generative Interventions for Causal Learningcited by 45
  19. 2022Causal Inference in Recommender Systems: A Survey and Future Directionscited by 44
  20. 2023Meta-causal Learning for Single Domain Generalizationcited by 43
  21. 2020DeVLBert: Learning Deconfounded Visio-Linguistic Representationscited by 42
  22. 2021Transporting Causal Mechanisms for Unsupervised Domain Adaptationcited by 38
  23. 2019Sunny and Dark Outside?! Improving Answer Consistency in VQA through Entailed Question Generationcited by 36
  24. 2023Multi-view Adversarial Discriminator: Mine the Non-causal Factors for Object Detection in Unseen Domainscited by 24
  25. 2022Causal Transportability for Visual Recognitioncited by 23
  26. 2021Contrastive ACE: Domain Generalization Through Alignment of Causal Mechanismscited by 20
  27. 2022Causal Balancing for Domain Generalizationcited by 20
  28. 2013The Recovery of Causal Poly-Trees from Statistical Datacited by 19
  29. 2013A General Algorithm for Deciding Transportability of Experimental Resultscited by 17
  30. 2022CaRTS: Causality-driven Robot Tool Segmentation from Vision and Kinematics Datacited by 16
  31. 2022Visual Semantic Segmentation Based on Few/Zero-Shot Learning: An Overviewcited by 16
  32. 2022Disentangle and Remerge: Interventional Knowledge Distillation for Few-Shot Object Detection from A Conditional Causal Perspectivecited by 13
  33. 2022Structural Causal 3D Reconstructioncited by 12
  34. 2021Conterfactual Generative Zero-Shot Semantic Segmentationcited by 10
  35. 2022A Survey of Deep Causal Models and Their Industrial Applicationscited by 10
  36. 2021A Machine Learning Surrogate Modeling Benchmark for Temperature Field Reconstruction of Heat-Source Systemscited by 8
  37. 2022Domain Generalization via Contrastive Causal Learningcited by 8
  38. 2014Statistical Causality from a Decision-Theoretic Perspectivecited by 7

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 4; 2025: 5; 2026: 2.

12 papers.

  1. 2024Mitigating Modality Prior-Induced Hallucinations in Multimodal Large Language Models via Deciphering Attention Causalitycited by 42
  2. 2023The role of causality in explainable artificial intelligencecited by 17
  3. 2024The Pursuit of Fairness in Artificial Intelligence Models: A Surveycited by 13
  4. 2025Pedestrian Intention Prediction via Vision-Language Foundation Modelscited by 5
  5. 2024Quantifying Context Bias in Domain Adaptation for Object Detectioncited by 2
  6. 2025Seeing Beyond Frames: Zero-Shot Pedestrian Intention Prediction with Raw Temporal Video and Multimodal Cuescited by 2
  7. 2025Novel Class Discovery for Point Cloud Segmentation via Joint Learning of Causal Representation and Reasoningcited by 2
  8. 2024OccludeNet: A Causal Journey into Mixed-View Actor-Centric Video Action Recognition under Occlusionscited by 0
  9. 2025VisionLogic: Discovering and Grounding Decision-Relevant Visual Conceptscited by 0
  10. 2025Mitigating Context Bias in Domain Adaptation for Object Detection using Mask Poolingcited by 0
  11. 2026Leveraging Causal Reasoning Method for Explaining Medical Image Segmentation Modelscited by 0
  12. 2026MTF-Net: Multi-Modal Temporal Feature Fusion Network for Pedestrian Intention Predictioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025CAUSAL3D: A Comprehensive Benchmark for Causal Learning from Visual Data
  2. 2025What's Missing in Vision-Language Models? Probing Their Struggles with Causal Order Reasoning
  3. 2026From Prompts to Tokens: Internalizing Causal Supervision in Vision-Language Model for Multi-Image Causal Reasoning
  4. 2026CCRV-Bench: Constraint-Based Evaluation of Causal Reasoning in Vision-Language Models
  5. 2025Causal-HalBench: Uncovering LVLMs Object Hallucinations Through Causal Intervention
  6. 2025CausalVLBench: Benchmarking Visual Causal Reasoning in Large Vision-Language Models
  7. 2024CausAdv: A Causal-based Framework for Detecting Adversarial Examples
  8. 2025CauSight: Learning to Supersense for Visual Causal Discovery