# Invariance Principle Meets Vicinal Risk Minimization

arXiv: https://arxiv.org/abs/2407.05765 · HTML: https://mlsanity.com/paper/2407.05765/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jul 2024.

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

- [Semantic Data Augmentation Enhanced Invariant Risk Minimization for Medical Image Domain Generalization](https://mlsanity.com/paper/2502.05593/) (2025)

## Abstract (arXiv)

Deep learning models excel in computer vision tasks but often fail to generalize to out-of-distribution (OOD) domains. Invariant Risk Minimization (IRM) aims to address OOD generalization by learning domain-invariant features. However, IRM struggles with datasets exhibiting significant diversity shifts. While data augmentation methods like Mixup and Semantic Data Augmentation (SDA) enhance diversity, they risk over-augmentation and label instability. To address these challenges, we propose a domain-shared Semantic Data Augmentation (SDA) module, a novel implementation of Variance Risk Minimization (VRM) designed to enhance dataset diversity while maintaining label consistency. We further provide a Rademacher complexity analysis, establishing a tighter generalization error bound compared to baseline methods. Extensive evaluations on OOD benchmarks, including PACS, VLCS, OfficeHome, and TerraIncognita, demonstrate consistent performance improvements over state-of-the-art domain generalization methods.