activity
20152023
most citedLearning Efficient Point Cloud Generation for Dense 3D Object Reconstruction

167 citations · 780 across the 46 of their papers we have counts for

collaborators
Showing 2021 · cs.LGShow all

5 papers · 2 filters

cs.LG2021★ 3 cited

Learning Positional Embeddings for Coordinate-MLPs

Sameera Ramasinghe, Simon Lucey

We propose a novel method to enhance the performance of coordinate-MLPs by learning instance-specific positional embeddings. End-to-end optimization of positional embedding paramet…

cs.LG2021

Beyond Periodicity: Towards a Unifying Framework for Activations in Coordinate-MLPs

Sameera Ramasinghe, Simon Lucey

Coordinate-MLPs are emerging as an effective tool for modeling multidimensional continuous signals, overcoming many drawbacks associated with discrete grid-based approximations. Ho…

cs.LG2021★ 30 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.LG2021

Evading the Simplicity Bias: Training a Diverse Set of Models Discovers Solutions with Superior OOD Generalization

Damien Teney, Ehsan Abbasnejad, Simon Lucey +1

Neural networks trained with SGD were recently shown to rely preferentially on linearly-predictive features and can ignore complex, equally-predictive ones. This simplicity bias ca…

cs.LG2021

Reframing Neural Networks: Deep Structure in Overcomplete Representations

Calvin Murdock, George Cazenavette, Simon Lucey

In comparison to classical shallow representation learning techniques, deep neural networks have achieved superior performance in nearly every application benchmark. But despite th…