Search Results for author:
Found 14 papers, 6 papers with code
Unsupervised Task Design to Meta-Train Medical Image Classifiers
Meta-training has been empirically demonstrated to be the most effective pre-training method for few-shot learning of medical image classifiers (i. e., classifiers modeled with small training sets).
Similarity of Classification Tasks
Recent advances in meta-learning has led to remarkable performances on several few-shot learning benchmarks.
Semi-supervised classification of radiology images with NoTeacher: A Teacher that is not Mean
Specifically, we describe adaptations for scenarios with 2D and 3D inputs, uni and multi-label classification, and class distribution mismatch between labeled and unlabeled portions of the training data.
Maximising the Utility of Validation Sets for Imbalanced Noisy-label Meta-learning
In this paper, we analyse the meta-learning algorithm and propose new criteria to characterise the utility of the validation set, based on: 1) the informativeness of the validation set; 2) the class distribution balance of the set; and 3) the correctness of the labels of the set.
Task Weighting in Meta-learning with Trajectory Optimisation
Developing meta-learning algorithms that are un-biased toward a subset of training tasks often requires hand-designed criteria to weight tasks, potentially resulting in sub-optimal solutions.
Towards the Identifiability in Noisy Label Learning: A Multinomial Mixture Approach
To meet this requirement without relying on additional $2C - 2$ manual annotations per instance, we propose a method that automatically generates additional noisy labels by estimating the noisy label distribution based on nearest neighbours.
PASS: Peer-Agreement based Sample Selection for training with Noisy Labels
The prevalence of noisy-label samples poses a significant challenge in deep learning, inducing overfitting effects.
Instance-dependent Noisy-label Learning with Graphical Model Based Noise-rate Estimation
To address IDN, Label Noise Learning (LNL) incorporates a sample selection stage to differentiate clean and noisy-label samples.
Learning to Complement with Multiple Humans
The ill-posedness of the LNL task requires the adoption of strong assumptions or the use of multiple noisy labels per training image, resulting in accurate models that work well in isolation but fail to optimise human-AI collaborative classification (HAI-CC).
Approximate Bayesian Computation for an Explicit-Duration Hidden Markov Model of COVID-19 Hospital Trajectories
We develop an Approximate Bayesian Computation approach that draws samples from the posterior distribution over the model's transition and duration parameters given aggregate counts from a specific location, thus adapting the model to a region or individual hospital site of interest.
Multi-omics Prediction from High-content Cellular Imaging with Deep Learning
High-content cellular imaging, transcriptomics, and proteomics data provide rich and complementary views on the molecular layers of biology that influence cellular states and function.
Instance-Dependent Noisy Label Learning via Graphical Modelling
Noisy labels are unavoidable yet troublesome in the ecosystem of deep learning because models can easily overfit them.
Ranked #1 on
Learning with noisy labels
on CIFAR-100
Uncertainty in Model-Agnostic Meta-Learning using Variational Inference
We introduce a new, rigorously-formulated Bayesian meta-learning algorithm that learns a probability distribution of model parameter prior for few-shot learning.
PAC-Bayes meta-learning with implicit task-specific posteriors
We introduce a new and rigorously-formulated PAC-Bayes meta-learning algorithm that solves few-shot learning.
