mlsanityData to 14 Oct 2026

Meta-Causal Feature Learning for Out-of-Distribution Generalization

arXiv 2208.10156 ↗First posted 22 Aug 2022cs.CVcited by 14

Not on the map. Why?

Abstract (arXiv)

Causal inference has become a powerful tool to handle the out-of-distribution (OOD) generalization problem, which aims to extract the invariant features. However, conventional methods apply causal learners from multiple data splits, which may incur biased representation learning from imbalanced data distributions and difficulty in invariant feature learning from heterogeneous sources. To address these issues, this paper presents a balanced meta-causal learner (BMCL), which includes a balanced task generation module (BTG) and a meta-causal feature learning module (MCFL). Specifically, the BTG module learns to generate balanced subsets by a self-learned partitioning algorithm with constraints on the proportions of sample classes and contexts. The MCFL module trains a meta-learner adapted to different distributions. Experiments conducted on NICO++ dataset verified that BMCL effectively identifies the class-invariant visual regions for classification and may serve as a general framework to improve the performance of the state-of-the-art methods.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 41 of its 45 references that are in the map. First posted on arXiv 22 Aug 2022.

Builds on

41 of 45 references.

References · 41

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  3. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  4. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  5. 2018CBAM: Convolutional Block Attention Modulecited by 2,477
  6. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  7. 2019Invariant Risk Minimizationcited by 1,854
  8. 2020The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalizationcited by 1,850
  9. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,432
  10. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
  11. 2020Meta-Learning in Neural Networks: A Surveycited by 950
  12. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 766
29 more
  1. 2018Exploring the Limits of Weakly Supervised Pretrainingcited by 605
  2. 2015Causal inference using invariant prediction: identification and confidence intervalscited by 536
  3. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 436
  4. 2018Dynamic Few-Shot Visual Learning without Forgettingcited by 385
  5. 2019Counterfactual Visual Explanationscited by 313
  6. 2019Don't Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biasescited by 280
  7. 2020Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effectcited by 256
  8. 2018Learning Not to Learn: Training Deep Neural Networks with Biased Datacited by 255
  9. 2020Invariant Risk Minimization Gamescited by 188
  10. 2020Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformationcited by 185
  11. 2015Cost Sensitive Learning of Deep Feature Representations from Imbalanced Datacited by 167
  12. 2019A Meta-Transfer Objective for Learning to Disentangle Causal Mechanismscited by 158
  13. 2017Invariant Causal Prediction for Nonlinear Modelscited by 140
  14. 2016Information Dropout: Learning Optimal Representations Through Noisy Computationcited by 132
  15. 2015Relay Backpropagation for Effective Learning of Deep Convolutional Neural Networkscited by 115
  16. 2022NICO++: Towards Better Benchmarking for Domain Generalizationcited by 86
  17. 2021Causal Attention for Unbiased Visual Recognitioncited by 80
  18. 2018Incremental Few-Shot Learning with Attention Attractor Networkscited by 66
  19. 2017Invariant Causal Prediction for Sequential Datacited by 63
  20. 2021Out of Distribution Generalization in Machine Learningcited by 60
  21. 2021Style Normalization and Restitution for Domain Generalization and Adaptationcited by 46
  22. 2020Counterfactual Fairness with Disentangled Causal Effect Variational Autoencodercited by 45
  23. 2022Out-of-distribution Generalization with Causal Invariant Transformationscited by 45
  24. 2021Transporting Causal Mechanisms for Unsupervised Domain Adaptationcited by 38
  25. 2014Maximin effects in inhomogeneous large-scale datacited by 32
  26. 2017Causally Regularized Learning with Agnostic Data Selection Biascited by 29
  27. 2022Constructing Balance from Imbalance for Long-tailed Image Recognitioncited by 25
  28. 2020Enforcing Predictive Invariance across Structured Biomedical Domainscited by 23
  29. 2018Counterfactual Normalization: Proactively Addressing Dataset Shift and Improving Reliability Using Causal Mechanismscited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 3; 2024: 4; 2025: 5; 2026: 1.

14 papers.

Sort:

By area:

  1. 2024Vision-and-Language Navigation via Causal Learningcited by 51
  2. 2023Cross-Silo Prototypical Calibration for Federated Learning with Non-IID Datacited by 35
  3. 2023Unbiased Scene Graph Generation via Two-stage Causal Modelingcited by 21
  4. 2025A Causal Adjustment Module for Debiasing Scene Graph Generationcited by 14
  5. 2022A Survey of Deep Causal Models and Their Industrial Applicationscited by 10
  6. 2023Class-level Structural Relation Modelling and Smoothing for Visual Representation Learningcited by 9
  7. 2025Federated Out-of-Distribution Generalization: A Causal Augmentation Viewcited by 4
  8. 2025Federated Deconfounding and Debiasing Learning for Out-of-Distribution Generalizationcited by 4
  9. 2025Global Intervention and Distillation for Federated Out-of-Distribution Generalizationcited by 3
  10. 2024Unifying Visual and Semantic Feature Spaces with Diffusion Models for Enhanced Cross-Modal Alignmentcited by 1
  11. 2025Robust Egocentric Referring Video Object Segmentation via Dual-Modal Causal Interventioncited by 1
  12. 2024Causality-based Cross-Modal Representation Learning for Vision-and-Language Navigationcited by 0
2 more
  1. 2024Comparative Study of Neighbor-based Methods for Local Outlier Detectioncited by 0
  2. 2026Causal Transfer in Medical Image Analysiscited by 0