collaborators

5 papers

cs.LG2025

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…

cs.LG2025

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…

cs.LG2025

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…

cs.LG2025

Hyperbolic Multimodal Representation Learning for Biological Taxonomies

ZeMing Gong, Chuanqi Tang, Xiaoliang Huo +6

Taxonomic classification in biodiversity research involves organizing biological specimens into structured hierarchies based on evidence, which can come from multiple modalities su…

cs.CV2024

Particle-Filtering-based Latent Diffusion for Inverse Problems

Amir Nazemi, Mohammad Hadi Sepanj, Nicholas Pellegrino +2

Current strategies for solving image-based inverse problems apply latent diffusion models to perform posterior sampling.However, almost all approaches make no explicit attempt to e…