# EiHi Net: Out-of-Distribution Generalization Paradigm

arXiv: https://arxiv.org/abs/2209.14946 · HTML: https://mlsanity.com/paper/2209.14946/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 36 references that are in the map.
- First posted on arXiv 29 Sep 2022.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction](https://mlsanity.com/paper/2103.03230/) (2021)
- [VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning](https://mlsanity.com/paper/2105.04906/) (2021)
- [Deeper, Broader and Artier Domain Generalization](https://mlsanity.com/paper/1710.03077/) (2017)
- [Out-of-Distribution Generalization via Risk Extrapolation (REx)](https://mlsanity.com/paper/2003.00688/) (2020)
- [Deep Transfer Learning with Joint Adaptation Networks](https://mlsanity.com/paper/1605.06636/) (2016)
- [Deep Stable Learning for Out-Of-Distribution Generalization](https://mlsanity.com/paper/2104.07876/) (2021)
- [Stable Learning via Sample Reweighting](https://mlsanity.com/paper/1911.12580/) (2019)
- [Beyond Sparsity: Tree Regularization of Deep Models for Interpretability](https://mlsanity.com/paper/1711.06178/) (2017)
- [Stable Prediction with Model Misspecification and Agnostic Distribution Shift](https://mlsanity.com/paper/2001.11713/) (2020)
- [Test-Time Training with Self-Supervision for Generalization under Distribution Shifts](https://mlsanity.com/paper/1909.13231/) (2019)
- [DecAug: Out-of-Distribution Generalization via Decomposed Feature Representation and Semantic Augmentation](https://mlsanity.com/paper/2012.09382/) (2020)
- [Cross-Domain Empirical Risk Minimization for Unbiased Long-tailed Classification](https://mlsanity.com/paper/2112.14380/) (2021)
- [CausPref: Causal Preference Learning for Out-of-Distribution Recommendation](https://mlsanity.com/paper/2202.03984/) (2022)
- [Active Multi-Kernel Domain Adaptation for Hyperspectral Image Classification](https://mlsanity.com/paper/1904.05200/) (2019)
- [Interventional Contrastive Learning with Meta Semantic Regularizer](https://mlsanity.com/paper/2206.14702/) (2022)
- [Independently Interpretable Lasso: A New Regularizer for Sparse Regression with Uncorrelated Variables](https://mlsanity.com/paper/1711.01796/) (2017)
- [Towards Interpretable and Robust Hand Detection via Pixel-wise Prediction](https://mlsanity.com/paper/2001.04163/) (2020)

## Built on by (most cited first, 1 of 1)

- [Implicit Non-Causal Factors are Out via Dataset Splitting for Domain Generalization Object Detection](https://mlsanity.com/paper/2601.19127/) (2026)

## 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.