4 papers
Towards Continual Test-Time Adaptation of Vision-Language Models in Open-Vocabulary Semantic Segmentation
Chandler Timm C. Doloriel, Yunbei Zhang, Sarthak Kumar Maharana +5
Open-vocabulary semantic segmentation (OVSS) relies on vision-language alignment to recognize arbitrary text-defined categories, yet this alignment is fragile under continual test-…
Continual Test-Time Adaptation via Entropy Sensitivity-Guidance in Strict Online Setting
Chandler Timm C. Doloriel, Yunbei Zhang, Muhammad Salman Siddiqui +4
Test-time adaptation (TTA) promises robustness under distribution shift by updating a pretrained model on unlabeled test data, but strict online TTA with batch size one and no acce…
CAST: Closed-form Analytic Semantic Transfer for Zero-Shot Classifier Extension
William Heyden, Habib Ullah, Muhammad Salman Siddiqui +1
Large pre-trained models have become foundational components of modern machine learning systems. Yet adapting these models to novel categories typically requires examples from the…
RevCD -- Reversed Conditional Diffusion for Generalized Zero-Shot Learning
William Heyden, Habib Ullah, M. Salman Siddiqui +1
In Generalized Zero-Shot Learning (GZSL), we aim to recognize both seen and unseen categories using a model trained only on seen categories. In computer vision, this translates int…