1 code implementation • 13 Feb 2024 • Janani Kugarajeevan, Thanikasalam Kokul, Amirthalingam Ramanan, Subha Fernando
One-stream Transformer trackers have shown outstanding performance in challenging benchmark datasets over the last three years, as they enable interaction between the target template and search region tokens to extract target-oriented features with mutual guidance.
no code implementations • IEEE Access 2023 • Janani Thangavel, Thanikasalam Kokul, Amirthalingam Ramanan, Subha Fernando
Single-object tracking is a well-known and challenging research topic in computer vision.
no code implementations • 29 Sep 2021 • Mihira Kasun Vithanage, Rukshan Darshana Wijesinghe, Alex Xavier, Dumindu Tissera, Sanath Jayasena, Subha Fernando
In this paper, we present a learning environment where agents are pressured to make their emerging languages compositional by incorporating a metric of topological similarity into the loss function.
no code implementations • 6 Jul 2021 • Dumindu Tissera, Rukshan Wijessinghe, Kasun Vithanage, Alex Xavier, Subha Fernando, Ranga Rodrigo
Having multiple parallel convolutional/dense operations in each layer solves this problem, but without any context-dependent allocation of resources among these operations: the parallel computations tend to learn similar features making the widening process less effective.
no code implementations • 6 Jul 2021 • Dumindu Tissera, Kasun Vithanage, Rukshan Wijesinghe, Alex Xavier, Sanath Jayasena, Subha Fernando, Ranga Rodrigo
The network parameters pose as the parameters of those distributions.
no code implementations • 17 Jun 2021 • Teshan Liyanage, Subha Fernando
Social insects in nature such as ants, termites and bees construct their colonies collaboratively in a very efficient process.
no code implementations • 16 Feb 2021 • Rukshan Wijesinghe, Kasun Vithanage, Dumindu Tissera, Alex Xavier, Subha Fernando, Jayathu Samarawickrama
Recent advances in Reinforcement Learning (RL) have surpassed human-level performance in many simulated environments.
no code implementations • 24 Jun 2020 • Dumindu Tissera, Kasun Vithanage, Rukshan Wijesinghe, Kumara Kahatapitiya, Subha Fernando, Ranga Rodrigo
As opposed to conventional network widening, multi-path architectures restrict the quadratic increment of complexity to a linear scale.
no code implementations • 26 Jul 2019 • Dumindu Tissera, Kumara Kahatapitiya, Rukshan Wijesinghe, Subha Fernando, Ranga Rodrigo
In view of this, networks which can allocate resources according to the context of the input and regulate flow of information across the network are effective.
Ranked #2 on Image Classification on Kuzushiji-MNIST