4 citations · 10 across the 10 of their papers we have counts for
7 papers · 1 filter
Pre-train to Gain: Robust Learning Without Clean Labels
David Szczecina, Nicholas Pellegrino, Paul Fieguth
Training deep networks with noisy labels leads to poor generalization and degraded accuracy due to overfitting to label noise. Existing approaches for learning with noisy labels of…
Effects of Initialization Biases on Deep Neural Network Training Dynamics
Nicholas Pellegrino, David Szczecina, Paul W. Fieguth
Untrained large neural networks, just after random initialization, tend to favour a small subset of classes, assigning high predicted probabilities to these few classes and approxi…
Hard Samples, Bad Labels: Robust Loss Functions That Know When to Back Off
Nicholas Pellegrino, David Szczecina, Paul Fieguth
Incorrectly labelled training data are frustratingly ubiquitous in both benchmark and specially curated datasets. Such mislabelling clearly adversely affects the performance and ge…
Self-Supervised Learning by Curvature Alignment
Benyamin Ghojogh, M. Hadi Sepanj, Paul Fieguth
Self-supervised learning (SSL) has recently advanced through non-contrastive methods that couple an invariance term with variance, covariance, or redundancy-reduction penalties. Wh…
Self-Supervised Learning Using Nonlinear Dependence
M. Hadi Sepanj, Benyamin Ghojogh, Paul Fieguth
Self-supervised learning has gained significant attention in contemporary applications, particularly due to the scarcity of labeled data. While existing SSL methodologies primarily…
BIOSCAN-5M: A Multimodal Dataset for Insect Biodiversity
Zahra Gharaee, Scott C. Lowe, ZeMing Gong +10
As part of an ongoing worldwide effort to comprehend and monitor insect biodiversity, this paper presents the BIOSCAN-5M Insect dataset to the machine learning community and establ…
Challenges for Predictive Modeling with Neural Network Techniques using Error-Prone Dietary Intake Data
Dylan Spicker, Amir Nazemi, Joy Hutchinson +4
Dietary intake data are routinely drawn upon to explore diet-health relationships. However, these data are often subject to measurement error, distorting the true relationships. Be…