9 citations · 12 across the 11 of their papers we have counts for
11 papers
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…
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…
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…
A Step Towards Worldwide Biodiversity Assessment: The BIOSCAN-1M Insect Dataset
Zahra Gharaee, ZeMing Gong, Nicholas Pellegrino +13
In an effort to catalog insect biodiversity, we propose a new large dataset of hand-labelled insect images, the BIOSCAN-Insect Dataset. Each record is taxonomically classified by a…
Machine Learning Challenges of Biological Factors in Insect Image Data
Nicholas Pellegrino, Zahra Gharaee, Paul Fieguth
The BIOSCAN project, led by the International Barcode of Life Consortium, seeks to study changes in biodiversity on a global scale. One component of the project is focused on study…
Time-domain feature extraction for target-specificity in Photoacoustic Remote Sensing Microscopy
Nicholas Pellegrino, Benjamin R. Ecclestone, Paul Fieguth +1
Photoacoustic Remote Sensing (PARS) microscopy is an emerging label-free optical absorption imaging modality. PARS operates by capturing nanosecond-scale optical perturbations gene…
K-Means for Noise-Insensitive Multi-Dimensional Feature Learning
Nicholas Pellegrino, Paul Fieguth, Parsin Haji Reza
Many measurement modalities which perform imaging by probing an object pixel-by-pixel, such as via Photoacoustic Microscopy, produce a multi-dimensional feature (typically a time-d…
In vivo functional and structural retina imaging using multimodal photoacoustic remote sensing microscopy and optical coherence tomography
Zohreh Hosseinaee, Nicholas Pellegrino, Nima Abbasi +4
We have developed a multimodal photoacoustic remote sensing (PARS) microscope combined with swept source optical coherence tomography for in vivo, non-contact retinal imaging. Buil…
Non-contact, in-vivo, functional, and structural ophthalmic imaging using multimodal photoacoustic remote sensing (PARS) microscopy and optical coherence tomography (OCT)
Zohreh Hosseinaee, Nima Abbasi, Layla Khali +3
Early diagnosis of ocular diseases improves the understanding of pathophysiology and helps with accurate monitoring and effective treatment. Advanced multimodal ocular imaging plat…