activity
20182022
most citedRethinking Positional Encoding

30 citations · 49 across the 5 of their papers we have counts for

collaborators
Showing cs.LGShow all

5 papers · 1 filter

cs.LG20221 cited

On Regularizing Coordinate-MLPs

Sameera Ramasinghe, Lachlan MacDonald, Simon Lucey

We show that typical implicit regularization assumptions for deep neural networks (for regression) do not hold for coordinate-MLPs, a family of MLPs that are now ubiquitous in comp…

cs.LG202130 cited

Rethinking Positional Encoding

Jianqiao Zheng, Sameera Ramasinghe, Simon Lucey

It is well noted that coordinate based MLPs benefit -- in terms of preserving high-frequency information -- through the encoding of coordinate positions as an array of Fourier feat…

cs.LG2020

Conditional Generative Modeling via Learning the Latent Space

Sameera Ramasinghe, Kanchana Ranasinghe, Salman Khan +2

Although deep learning has achieved appealing results on several machine learning tasks, most of the models are deterministic at inference, limiting their application to single-mod…

cs.LG2019

Blended Convolution and Synthesis for Efficient Discrimination of 3D Shapes

Sameera Ramasinghe, Salman Khan, Nick Barnes +1

Existing networks directly learn feature representations on 3D point clouds for shape analysis. We argue that 3D point clouds are highly redundant and hold irregular (permutation-i…

cs.LG20193 cited

Volumetric Convolution: Automatic Representation Learning in Unit Ball

Sameera Ramasinghe, Salman Khan, Nick Barnes

Convolution is an efficient technique to obtain abstract feature representations using hierarchical layers in deep networks. Although performing convolution in Euclidean geometries…