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

by   Haoyue Bai, et al.

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.


page 2

page 7

page 11


Tackling Long-Tailed Category Distribution Under Domain Shifts

Machine learning models fail to perform well on real-world applications ...

Improved OOD Generalization via Conditional Invariant Regularizer

Recently, generalization on out-of-distribution (OOD) data with correlat...

Maximum Mean Discrepancy for Generalization in the Presence of Distribution and Missingness Shift

Covariate shifts are a common problem in predictive modeling on real-wor...

OoD-Bench: Benchmarking and Understanding Out-of-Distribution Generalization Datasets and Algorithms

Deep learning has achieved tremendous success with independent and ident...

Towards Domain Generalization in Object Detection

Despite the striking performance achieved by modern detectors when train...

Adaptive Feature Representation for Visual Tracking

Robust feature representation plays significant role in visual tracking....

AutoDO: Robust AutoAugment for Biased Data with Label Noise via Scalable Probabilistic Implicit Differentiation

AutoAugment has sparked an interest in automated augmentation methods fo...