DecAug: Out-of-Distribution Generalization via Decomposed Feature Representation and Semantic Augmentation
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.
Code (1)
Tasks
Domain GeneralizationImage ClassificationOut-of-Distribution GeneralizationSimilar Papers 제목 키워드 기반
DecAug: Augmenting HOI Detection via Decomposition
Human-object interaction (HOI) detection requires a large amount of annotated data. Current algorithms suffer from insufficient training samples and category imbalance within datasets. To increase data efficiency, in thi…
Data AugmentationDomain GeneralizationHuman-Object Interaction DetectionObjectTowards Robust Out-of-Distribution Generalization: Data Augmentation and Neural Architecture Search Approaches
Deep learning has been demonstrated with tremendous success in recent years. Despite so, its performance in practice often degenerates drastically when encountering out-of-distribution (OoD) data, i.e. training and test …
Data AugmentationNeural Architecture SearchOut-of-Distribution GeneralizationDecomposed Soft Prompt Guided Fusion Enhancing for Compositional Zero-Shot Learning
Compositional Zero-Shot Learning (CZSL) aims to recognize novel concepts formed by known states and objects during training. Existing methods either learn the combined state-object representation, challenging the general…
Compositional Zero-Shot LearningNovel ConceptsObjectZero-Shot LearningOffline Meta-Reinforcement Learning with Flow-Based Task Inference and Adaptive Correction of Feature Overgeneralization
Offline meta-reinforcement learning (OMRL) combines the strengths of learning from diverse datasets in offline RL with the adaptability to new tasks of meta-RL, promising safe and efficient knowledge acquisition by RL ag…
Reinforcement LearningOffline RLHOLa: Zero-Shot HOI Detection with Low-Rank Decomposed VLM Feature Adaptation
Zero-shot human-object interaction (HOI) detection remains a challenging task, particularly in generalizing to unseen actions. Existing methods address this challenge by tapping Vision-Language Models (VLMs) to access kn…