3 papers
cs.LG2024
Training Over a Distribution of Hyperparameters for Enhanced Performance and Adaptability on Imbalanced Classification
Kelsey Lieberman, Swarna Kamlam Ravindran, Shuai Yuan +1
Although binary classification is a well-studied problem, training reliable classifiers under severe class imbalance remains a challenge. Recent techniques mitigate the ill effects…
cs.CV2023
RandMSAugment: A Mixed-Sample Augmentation for Limited-Data Scenarios
Swarna Kamlam Ravindran, Carlo Tomasi
The high costs of annotating large datasets suggests a need for effectively training CNNs with limited data, and data augmentation is a promising direction. We study foundational a…
cs.CV2017
CoMaL Tracking: Tracking Points at the Object Boundaries
Santhosh K. Ramakrishnan, Swarna Kamlam Ravindran, Anurag Mittal
Traditional point tracking algorithms such as the KLT use local 2D information aggregation for feature detection and tracking, due to which their performance degrades at the object…