# DecAug: Out-of-Distribution Generalization via Decomposed Feature Representation and Semantic Augmentation

arXiv: https://arxiv.org/abs/2012.09382 · HTML: https://mlsanity.com/paper/2012.09382/

## Key facts

- Cited by 48 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Dec 2020.

## Built on by (most cited first, 30 of 48)

- [Domain Generalization by Mutual-Information Regularization with Pre-trained Models](https://mlsanity.com/paper/2203.10789/) (2022)
- [Learning Placeholders for Open-Set Recognition](https://mlsanity.com/paper/2103.15086/) (2021)
- [Towards a Theoretical Framework of Out-of-Distribution Generalization](https://mlsanity.com/paper/2106.04496/) (2021)
- [Towards Principled Disentanglement for Domain Generalization](https://mlsanity.com/paper/2111.13839/) (2021)
- [OoD-Bench: Quantifying and Understanding Two Dimensions of Out-of-Distribution Generalization](https://mlsanity.com/paper/2106.03721/) (2021)
- [NICO++: Towards Better Benchmarking for Domain Generalization](https://mlsanity.com/paper/2204.08040/) (2022)
- [Evading the Simplicity Bias: Training a Diverse Set of Models Discovers Solutions with Superior OOD Generalization](https://mlsanity.com/paper/2105.05612/) (2021)
- [SAND-mask: An Enhanced Gradient Masking Strategy for the Discovery of Invariances in Domain Generalization](https://mlsanity.com/paper/2106.02266/) (2021)
- [Model Agnostic Sample Reweighting for Out-of-Distribution Learning](https://mlsanity.com/paper/2301.09819/) (2023)
- [Invariant and Transportable Representations for Anti-Causal Domain Shifts](https://mlsanity.com/paper/2207.01603/) (2022)
- [A Style and Semantic Memory Mechanism for Domain Generalization](https://mlsanity.com/paper/2112.07517/) (2021)
- [Overcoming Simplicity Bias in Deep Networks using a Feature Sieve](https://mlsanity.com/paper/2301.13293/) (2023)
- [NAS-OoD: Neural Architecture Search for Out-of-Distribution Generalization](https://mlsanity.com/paper/2109.02038/) (2021)
- [Your Contrastive Learning Is Secretly Doing Stochastic Neighbor Embedding](https://mlsanity.com/paper/2205.14814/) (2022)
- [Adversarial Robustness for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2109.00946/) (2021)
- [Distribution Shift Inversion for Out-of-Distribution Prediction](https://mlsanity.com/paper/2306.08328/) (2023)
- [On Modality Bias Recognition and Reduction](https://mlsanity.com/paper/2202.12690/) (2022)
- [From Global to Local: Multi-scale Out-of-distribution Detection](https://mlsanity.com/paper/2308.10239/) (2023)
- [Optimization-based Causal Estimation from Heterogenous Environments](https://mlsanity.com/paper/2109.11990/) (2021)
- [Domain Generalization -- A Causal Perspective](https://mlsanity.com/paper/2209.15177/) (2022)
- [Explore and Exploit the Diverse Knowledge in Model Zoo for Domain Generalization](https://mlsanity.com/paper/2306.02595/) (2023)
- [Learn to Preserve and Diversify: Parameter-Efficient Group with Orthogonal Regularization for Domain Generalization](https://mlsanity.com/paper/2407.15085/) (2024)
- [HYPO: Hyperspherical Out-of-Distribution Generalization](https://mlsanity.com/paper/2402.07785/) (2024)
- [What Variables Affect Out-of-Distribution Generalization in Pretrained Models?](https://mlsanity.com/paper/2405.15018/) (2024)
- [ZooD: Exploiting Model Zoo for Out-of-Distribution Generalization](https://mlsanity.com/paper/2210.09236/) (2022)
- [Seeking Consistent Flat Minima for Better Domain Generalization via Refining Loss Landscapes](https://mlsanity.com/paper/2412.13573/) (2024)
- [Cross Contrasting Feature Perturbation for Domain Generalization](https://mlsanity.com/paper/2307.12502/) (2023)
- [Sill-Net: Feature Augmentation with Separated Illumination Representation](https://mlsanity.com/paper/2102.03539/) (2021)
- [Spuriousness-Aware Meta-Learning for Learning Robust Classifiers](https://mlsanity.com/paper/2406.10742/) (2024)
- [AHA: Human-Assisted Out-of-Distribution Generalization and Detection](https://mlsanity.com/paper/2410.08000/) (2024)

## Abstract (arXiv)

While deep learning demonstrates its strong ability to handle independent and identically distributed (IID) data, it often suffers from out-of-distribution (OoD) generalization, where the test data come from another distribution (w.r.t. the training one). Designing a general OoD generalization framework to a wide range of applications is challenging, mainly due to possible correlation shift and diversity shift in the real world. Most of the previous approaches can only solve one specific distribution shift, such as shift across domains or the extrapolation of correlation. To address that, we propose DecAug, a novel decomposed feature representation and semantic augmentation approach for OoD generalization. DecAug disentangles the category-related and context-related features. Category-related features contain causal information of the target object, while context-related features describe the attributes, styles, backgrounds, or scenes, causing distribution shifts between training and test data. The decomposition is achieved by orthogonalizing the two gradients (w.r.t. intermediate features) of losses for predicting category and context labels. Furthermore, we perform gradient-based augmentation on context-related features to improve the robustness of the learned representations. Experimental results show that DecAug outperforms other state-of-the-art methods on various OoD datasets, which is among the very few methods that can deal with different types of OoD generalization challenges.