Out-of-Distribution Learning
Out-of-Distribution learning is concerned with developing methods where the distribution of the data processed at test time may be different from the distrib...
Research
Immersive Analytics
Recent advanecs in augmented, mixed, and virtual reality, coupled with the need to perform analysis and decision-making on large-scale collections of volumet...
Novelty and Anomaly Detection
Detecting the presence of outliers, like novelties or anomalies, with respect to a particular distribution has numerous applications in computer vision and i...
Resources
CCSA Code
Code repository of the Classification and Contrastive Semantic Alignment domain adaptation model.