Machine learning models, while progressively advanced, rely heavily on the IID assumption,
which is often unfulfilled in practice due to inevitable distribution shifts. This renders them …

Different distribution shifts require different algorithmic and operational interventions.
Methodological research must be grounded by the specific shifts they address. Although …

Open set recognition (OSR) constitutes a critical endeavor within the domain of computer
vision, frequently deployed in applications, such as autonomous driving and medical …

Abstract In visual-based Reinforcement Learning (RL), agents often struggle to generalize
well to environmental variations in the state space that were not observed during training …

Abstract Domain generalization aims to solve the challenge of Out-of-Distribution (OOD)
generalization by leveraging common knowledge learned from multiple training domains to …

Medical image multi-object segmentation aims to accurately extract each object that is great
significant for the medical image analysis. Although several methods based on deep …

Single domain generalization aims to train a model that can generalize well to multiple
unseen target domains by leveraging the knowledge in a related source domain. Recent …

Stable learning aims to leverage the knowledge in a relevant source domain to learn a
prediction model that can generalize well to target domains. Recent advances in stable …

The challenge of Out-of-Distribution (OOD) generalization poses a foundational concern for
the application of machine learning algorithms to risk-sensitive areas. Inspired by traditional …

Due to the challenge posed by multi-source and heterogeneous data collected from diverse
environments, causal relationships among features can exhibit variations influenced by …