Sotabase

Career

· Chief Scientist, OCTAVE - John Keells Group2025–
· Staff Research Scientist - Machine Learning AI, Google2020–2024
· Research Scientist, FiveAI2017–2020
· Quantitative Researcher In Machine Learning, Man AHL2016–2017
· Software Engineer, Orion Health2013–2014
· Doctor of Philosophy (Ph.D.), Engineering, The Australian National University2012–2013
· Software Engineer, WSO22010–2012
· Tutor (Part-time), ICBT City Campus2008–2012
· B.Sc. Engineering, Electronics and Telecommunication Engineering, University of Moratuwa2006–2010

Publications (33)

Conditional Random Fields as Recurrent Neural Networks
IEEE International Conference on Computer Vision · 2015
2,576
cited
Long-tail learning via logit adjustment
International Conference on Learning Representations · 2020
874
cited
Kernel Methods on the Riemannian Manifold of Symmetric Positive Definite Matrices
2013 IEEE Conference on Computer Vision and Pattern Recognition · 2013
310
cited
Rethinking FID: Towards a Better Evaluation Metric for Image Generation
Computer Vision and Pattern Recognition · 2023
290
cited
Kernel Methods on Riemannian Manifolds with Gaussian RBF Kernels
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2014
256
cited
Higher Order Conditional Random Fields in Deep Neural Networks
European Conference on Computer Vision · 2015
232
cited
Conditional Random Fields Meet Deep Neural Networks for Semantic Segmentation: Combining Probabilistic Graphical Models with Deep Learning for Structured Prediction
IEEE Signal Processing Magazine · 2018
130
cited
Expanding the Family of Grassmannian Kernels: An Embedding Perspective
European Conference on Computer Vision · 2014
99
cited
Optimizing over Radial Kernels on Compact Manifolds
2014 IEEE Conference on Computer Vision and Pattern Recognition · 2014
42
cited
Prototypical Priors: From Improving Classification to Zero-Shot Learning
British Machine Vision Conference · 2015
42
cited
A Framework for Shape Analysis via Hilbert Space Embedding
IEEE International Conference on Computer Vision · 2013
34
cited
In defense of dual-encoders for neural ranking
International Conference on Machine Learning · 2022
27
cited
Combining Multiple Manifold-Valued Descriptors for Improved Object Recognition
International Conference on Digital Image Computing: Techniques and Applications · 2013
25
cited
Higher Order Potentials in End-to-End Trainable Conditional Random Fields
arXiv.org · 2015
23
cited
Disentangling Sampling and Labeling Bias for Learning in Large-Output Spaces
International Conference on Machine Learning · 2021
12
cited
EmbedDistill: A Geometric Knowledge Distillation for Information Retrieval
arXiv.org · 2023
10
cited
Efficient Document Ranking with Learnable Late Interactions
arXiv.org · 2024
9
cited
Kernels on Riemannian Manifolds
2016
8
cited
Bipartite Conditional Random Fields for Panoptic Segmentation
British Machine Vision Conference · 2019
6
cited
Less is more: Selecting informative and diverse subsets with balancing constraints
2021
6
cited
Sotabase
Sadeep Jayasumana | Researcher Profile | Sotabase | Sotabase