no code implementations • 24 May 2024 • Sahan Liyanaarachchi, Kanchana Thilakarathna, Sennur Ulukus
If enough clients have responded back, the round is deemed successful and the local gradients of all the clients that responded back are used to update the global model.
no code implementations • 25 Dec 2019 • Kanchana Ranasinghe, Sahan Liyanaarachchi, Harsha Ranasinghe, Mayuka Jayawardhana
Tracking multiple objects in real time is essential for a variety of real-world applications, with self-driving industry being at the foremost.
1 code implementation • 11 Dec 2019 • Sadeep Jayasumana, Kanchana Ranasinghe, Mayuka Jayawardhana, Sahan Liyanaarachchi, Harsha Ranasinghe
To tackle this problem, we propose a CRF model, named Bipartite CRF or BCRF, with two types of random variables for semantic and instance labels.