EiHi Net: Out-of-Distribution Generalization Paradigm
Not on the map. Why?
Abstract (arXiv)
This paper develops a new EiHi net to solve the out-of-distribution (OoD) generalization problem in deep learning. EiHi net is a model learning paradigm that can be blessed on any visual backbone. This paradigm can change the previous learning method of the deep model, namely find out correlations between inductive sample features and corresponding categories, which suffers from pseudo correlations between indecisive features and labels. We fuse SimCLR and VIC-Reg via explicitly and dynamically establishing the original - positive - negative sample pair as a minimal learning element, the deep model iteratively establishes a relationship close to the causal one between features and labels, while suppressing pseudo correlations. To further validate the proposed model, and strengthen the established causal relationships, we develop a human-in-the-loop strategy, with few guidance samples, to prune the representation space directly. Finally, it is shown that the developed EiHi net makes significant improvements in the most difficult and typical OoD dataset Nico, compared with the current SOTA results, without any domain (e.g. background, irrelevant features) information.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 23 of its 36 references that are in the map. First posted on arXiv 29 Sep 2022.
Builds on
23 of 36 references.
References · 23
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
- 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
- 2020Supervised Contrastive Learningcited by 2,803
- 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
- 2019Invariant Risk Minimizationcited by 1,832
- 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,818
- 2021VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learningcited by 1,013
- 2017Deeper, Broader and Artier Domain Generalizationcited by 983
- 2020Out-of-Distribution Generalization via Risk Extrapolation (REx)cited by 737
- 2016Deep Transfer Learning with Joint Adaptation Networkscited by 609
- 2021Deep Stable Learning for Out-Of-Distribution Generalizationcited by 153
11 more
- 2019Stable Learning via Sample Reweightingcited by 70
- 2017Beyond Sparsity: Tree Regularization of Deep Models for Interpretabilitycited by 68
- 2020Stable Prediction with Model Misspecification and Agnostic Distribution Shiftcited by 62
- 2019Test-Time Training with Self-Supervision for Generalization under Distribution Shiftscited by 55
- 2020DecAug: Out-of-Distribution Generalization via Decomposed Feature Representation and Semantic Augmentationcited by 48
- 2021Cross-Domain Empirical Risk Minimization for Unbiased Long-tailed Classificationcited by 19
- 2022CausPref: Causal Preference Learning for Out-of-Distribution Recommendationcited by 17
- 2019Active Multi-Kernel Domain Adaptation for Hyperspectral Image Classificationcited by 12
- 2022Interventional Contrastive Learning with Meta Semantic Regularizercited by 11
- 2017Independently Interpretable Lasso: A New Regularizer for Sparse Regression with Uncorrelated Variablescited by 6
- 2020Towards Interpretable and Robust Hand Detection via Pixel-wise Predictioncited by 2
Built on by
Citing papers per year: 2026: 1.
1 paper.