Search Results for author:
Found 15 papers, 6 papers with code
JetLOV: Enhancing Jet Tree Tagging through Neural Network Learning of Optimal LundNet Variables
Machine learning has played a pivotal role in advancing physics, with deep learning notably contributing to solving complex classification problems such as jet tagging in the field of jet physics.
Probabilistic Weight Fixing: Large-scale training of neural network weight uncertainties for quantization
Weight-sharing quantization has emerged as a technique to reduce energy expenditure during inference in large neural networks by constraining their weights to a limited set of values.
MatSpectNet: Material Segmentation Network with Domain-Aware and Physically-Constrained Hyperspectral Reconstruction
The network leverages the principles of colour perception in modern cameras to constrain the reconstructed hyperspectral images and employs the domain adaptation method to generalise the hyperspectral reconstruction capability from a spectral recovery dataset to material segmentation datasets.
DBAT: Dynamic Backward Attention Transformer for Material Segmentation with Cross-Resolution Patches
By analysing the cross-resolution features and the attention weights, this paper interprets how the DBAT learns from image patches.
Rotation-Scale Equivariant Steerable Filters
When conventional CNNs are applied to histopathology image analysis, the generalization performance of models is limited because 1) a part of the parameters of filters are trained to fit rotation transformation, thus decreasing the capability of learning other discriminative features; 2) fixed-size filters trained on images at a given scale fail to generalize to those at different scales.
Scale-Equivariant UNet for Histopathology Image Segmentation
Digital histopathology slides are scanned and viewed under different magnifications and stored as images at different resolutions.
ADS_UNet: A Nested UNet for Histopathology Image Segmentation
Nested arrangements of these encoder and decoder maps give rise to extensions of the UNet model, such as UNete and UNet++.
Weight Fixing Networks
Rather than a channel or layer-wise encoding, we look to lossless whole-network quantisation to minimise the entropy and number of unique parameters in a network.
Optimising 2D Pose Representation: Improve Accuracy, Stability and Generalisability Within Unsupervised 2D-3D Human Pose Estimation
With a maximum architecture capacity of 6 residual blocks, we evaluate the performance of 5 models which each represent a 2D pose differently during the adversarial unsupervised 2D-3D HPE process.
"Teaching Independent Parts Separately" (TIPSy-GAN) : Improving Accuracy and Stability in Unsupervised Adversarial 2D to 3D Pose Estimation
We show that for two independent generators training adversarially has improved stability than that of a solo generator which collapses.
Ranked #46 on
3D Human Pose Estimation
on MPI-INF-3DHP
(AUC metric)
Low Entropy Deep Networks
We design the approach to realise four model outcome objectives: i) very few unique weights, ii) low-entropy weight encodings, iii) unique weight values which are amenable to energy-saving versions of hardware multiplication, and iv) lossless task-performance.
Can Super Resolution be used to improve Human Pose Estimation in Low Resolution Scenarios?
Second, the keypoint detection performance gained is dependent on that persons pixel count in the original image prior to any application of SR; keypoint detection performance was improved when SR was applied to people with a small initial segmentation area, but degrades as this becomes larger.
Generalisation and the Geometry of Class Separability
Recent results in deep learning show that considering only the capacity of machines does not adequately explain the generalisation performance we can observe.
A phenomenological cluster-based model of Ca2+ waves and oscillations for Inositol 1,4,5-trisphosphate receptor (IP3R) channels
Clusters of IP3 receptor channels in the membranes of the endoplasmic reticulum (ER) of many non-excitable cells release calcium ions in a cooperative manner giving rise to dynamical patterns such as Ca2+ puffs, waves, and oscillations that occur on multiple spatial and temporal scales.
Fast Approximate Bayesian Computation for Estimating Parameters in Differential Equations
Approximate Bayesian computation (ABC) using a sequential Monte Carlo method provides a comprehensive platform for parameter estimation, model selection and sensitivity analysis in differential equations.
