Related papers: Learning Latent Spaces for Domain Generalization i…

Deep learning models obtain impressive accuracy in road scenes understanding, however they need a large quantity of labeled samples for their training. Additionally, such models do not generalise well to environments where the statistical…

Due to the existence of dataset shifts, the distributions of data acquired from different working conditions show significant differences in real-world industrial applications, which leads to performance degradation of traditional machine…

Temporal Domain Generalization (TDG) aims to generalize across temporal distribution shifts, e.g., lexical change over time. Prior work often addresses this by predicting future model weights. However, full model prediction is prohibitively…

Graph-based spatio-temporal neural networks are effective to model the spatial dependency among discrete points sampled irregularly from unstructured grids, thanks to the great expressiveness of graph neural networks. However, these models…

Cross-domain time series forecasting is a valuable task in various web applications. Despite its rapid advancement, achieving effective generalization across heterogeneous time series data remains a significant challenge. Existing methods…

Clinical machine learning models experience significantly degraded performance in datasets not seen during training, e.g., new hospitals or populations. Recent developments in domain generalization offer a promising solution to this problem…

Modeling dynamic temporal dependencies is a critical challenge in time series pre-training, which evolve due to distribution shifts and multi-scale patterns. This temporal variability severely impairs the generalization of pre-trained…

Researchers have been facing a difficult problem that data generation mechanisms could be influenced by internal or external factors leading to the training and test data with quite different distributions, consequently traditional…

Adapting machine learning models to medical time series across different domains remains a challenge due to complex temporal dependencies and dynamic distribution shifts. Current approaches often focus on isolated feature representations,…

How to handle domain shifts when recognizing or segmenting visual data across domains has been studied by learning and vision communities. In this paper, we address domain generalized semantic segmentation, in which the segmentation model…

Traditional place categorization approaches in robot vision assume that training and test images have similar visual appearance. Therefore, any seasonal, illumination and environmental changes typically lead to severe degradation in…

Domain shift refers to the well known problem that a model trained in one source domain performs poorly when applied to a target domain with different statistics. {Domain Generalization} (DG) techniques attempt to alleviate this issue by…

Existing domain generalization aims to learn a generalizable model to perform well even on unseen domains. For many real-world machine learning applications, the data distribution often shifts gradually along domain indices. For example, a…

For time series arising from latent dynamical systems, existing cross-domain generalization methods commonly assume that samples are comparably meaningful within a shared representation space. In real-world settings, however, different…

Self-awareness is the key capability of autonomous systems, e.g., autonomous driving network, which relies on highly efficient time series forecasting algorithm to enable the system to reason about the future state of the environment, as…

In recent years, advancements in deep learning have spurred the development of numerous models for Long-term Time Series Forecasting (LTSF). However, most existing approaches struggle to fully capture the complex and structured dependencies…

Clinical data is often affected by clinically irrelevant factors such as discrepancies between measurement devices or differing processing methods between sites. In the field of machine learning (ML), these factors are known as domains and…

We investigate a novel approach to time-series modeling, inspired by the successes of large pretrained foundation models. We introduce FAE (Foundation Auto-Encoders), a foundation generative-AI model for anomaly detection in time-series…

Modeling multivariate time series has long been a subject that has attracted researchers from a diverse range of fields including economics, finance, and traffic. A basic assumption behind multivariate time series forecasting is that its…

Latent variables (LVs) play a crucial role in encoder-decoder models by enabling effective data compression, prediction, and generation. Although their theoretical properties, such as generalization, have been extensively studied in…