15 citations · 21 across the 7 of their papers we have counts for
7 papers
An Underexplored Dilemma between Confidence and Calibration in Quantized Neural Networks
Guoxuan Xia, Sangwon Ha, Tiago Azevedo +1
Modern convolutional neural networks (CNNs) are known to be overconfident in terms of their calibration on unseen input data. That is to say, they are more confident than they are…
New Insights on the Thermodynamic Equilibrium of Black Hole and Thermal Radiation
Ruifeng Zheng
The thermal balance between the black hole and surrounding thermal radiation is an interesting topic. The primordial black hole is a type of black hole formed in the early universe…
Towards Efficient Point Cloud Graph Neural Networks Through Architectural Simplification
Shyam A. Tailor, René de Jong, Tiago Azevedo +2
In recent years graph neural network (GNN)-based approaches have become a popular strategy for processing point cloud data, regularly achieving state-of-the-art performance on a va…
Stochastic-Shield: A Probabilistic Approach Towards Training-Free Adversarial Defense in Quantized CNNs
Lorena Qendro, Sangwon Ha, René de Jong +1
Quantized neural networks (NN) are the common standard to efficiently deploy deep learning models on tiny hardware platforms. However, we notice that quantized NNs are as vulnerabl…
On the Effects of Quantisation on Model Uncertainty in Bayesian Neural Networks
Martin Ferianc, Partha Maji, Matthew Mattina +1
Bayesian neural networks (BNNs) are making significant progress in many research areas where decision-making needs to be accompanied by uncertainty estimation. Being able to quanti…
Stochastic-YOLO: Efficient Probabilistic Object Detection under Dataset Shifts
Tiago Azevedo, René de Jong, Matthew Mattina +1
In image classification tasks, the evaluation of models' robustness to increased dataset shifts with a probabilistic framework is very well studied. However, object detection (OD)…
Efficient Winograd or Cook-Toom Convolution Kernel Implementation on Widely Used Mobile CPUs
Partha Maji, Andrew Mundy, Ganesh Dasika +3
The Winograd or Cook-Toom class of algorithms help to reduce the overall compute complexity of many modern deep convolutional neural networks (CNNs). Although there has been a lot…