Search Results for author: Subha Fernando

Found 9 papers, 1 papers with code

Optimized Information Flow for Transformer Tracking

1 code implementation13 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.

Effect of Pressure for Compositionality on Language Emergence

no code implementations29 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.

End-To-End Data-Dependent Routing in Multi-Path Neural Networks

no code implementations6 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.

Optimizing robotic swarm based construction tasks

no code implementations17 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.

Feature-Dependent Cross-Connections in Multi-Path Neural Networks

no code implementations24 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.

Context-Aware Multipath Networks

no code implementations26 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.

Image Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.