5 papers
Domain Generalization in-the-Wild: Disentangling Classification from Domain-Aware Representations
Ha Min Son, Zhe Zhao, Shahbaz Rezaei +1
Evaluating domain generalization (DG) for foundational models like CLIP is challenging, as web-scale pretraining data potentially covers many existing benchmarks. Consequently, cur…
FixCLR: Negative-Class Contrastive Learning for Semi-Supervised Domain Generalization
Ha Min Son, Shahbaz Rezaei, Xin Liu
Semi-supervised domain generalization (SSDG) aims to solve the problem of generalizing to out-of-distribution data when only a few labels are available. Due to label scarcity, appl…
On the Necessity of Multi-Domain Explanation: An Uncertainty Principle Approach for Deep Time Series Models
Shahbaz Rezaei, Avishai Halev, Xin Liu
A prevailing approach to explain time series models is to generate attribution in time domain. A recent development in time series XAI is the concept of explanation spaces, where a…
Explanation Space: A New Perspective into Time Series Interpretability
Shahbaz Rezaei, Xin Liu
Human understandable explanation of deep learning models is essential for various critical and sensitive applications. Unlike image or tabular data where the importance of each inp…
Benchmarking Counterfactual Interpretability in Deep Learning Models for Time Series Classification
Ziwen Kan, Shahbaz Rezaei, Xin Liu
The popularity of deep learning methods in the time series domain boosts interest in interpretability studies, including counterfactual (CF) methods. CF methods identify minimal ch…