1 code implementation • 8 Feb 2024 • Kelsey Lieberman, Shuai Yuan, Swarna Kamlam Ravindran, Carlo Tomasi
Although binary classification is a well-studied problem in computer vision, training reliable classifiers under severe class imbalance remains a challenging problem.
no code implementations • 25 Nov 2023 • Swarna Kamlam Ravindran, Carlo Tomasi
We show that low-level feature transforms play a pivotal role in this performance difference, postulate a new property of augmentations related to their data efficiency, and propose new ways to measure the diversity and realism of augmentations.
no code implementations • 7 Jun 2017 • Santhosh K. Ramakrishnan, Swarna Kamlam Ravindran, Anurag Mittal
Experiments show improvements over a simple re-detect-and-match framework as well as KLT in terms of speed/accuracy on different real-world applications, especially at the object boundaries.
no code implementations • 5 Dec 2014 • Swarna Kamlam Ravindran, Anurag Mittal
Feature or interest points typically use information aggregation in 2D patches which does not remain stable at object boundaries when there is object motion against a significantly varying background.