30 citations · 49 across the 5 of their papers we have counts for
5 papers · 1 filter
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…
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…
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…
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…
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…