Search Results for author:
Found 8 papers, 4 papers with code
Topology-aware Robust Optimization for Out-of-distribution Generalization
Out-of-distribution (OOD) generalization is a challenging machine learning problem yet highly desirable in many high-stake applications.
Are Data-driven Explanations Robust against Out-of-distribution Data?
How to develop robust explanations against out-of-distribution data?
Calibrating Probabilistic Embeddings for Cross-Modal Retrieval
The key idea is to estimate the density ratio between the distributions of the two modalities, and use it to calibrate the similarity measurement in the embedding space.
Out-of-Domain Generalization from a Single Source: An Uncertainty Quantification Approach
We are concerned with a worst-case scenario in model generalization, in the sense that a model aims to perform well on many unseen domains while there is only one single domain available for training.
Uncertainty-guided Model Generalization to Unseen Domains
To the best of our knowledge, this is the first work to (1) access the generalization uncertainty from a single source and (2) leverage it to guide both input and label augmentation for robust generalization.
Uncertain Out-of-Domain Generalization
To the best of our knowledge, this is the first work to (1) access the generalization uncertainty from a single source and (2) leverage it to guide both input and label augmentation for robust generalization.
Learning to Learn Single Domain Generalization
We are concerned with a worst-case scenario in model generalization, in the sense that a model aims to perform well on many unseen domains while there is only one single domain available for training.
Geometry-Contrastive GAN for Facial Expression Transfer
Geometry information is introduced into cGANs as continuous conditions to guide the generation of facial expressions.
