6 papers
Risk-Aware Decision Policies for Agents Under Noisy Perception
David Szczecina
Perception in biological systems is inherently noisy, requiring organisms to make decisions under uncertainty where misclassification can be costly or fatal. We present an Artifici…
Sparse Data Tree Canopy Segmentation: Fine-Tuning Leading Pretrained Models on Only 150 Images
David Szczecina, Hudson Sun, Anthony Bertnyk +3
Tree canopy detection from aerial imagery is an important task for environmental monitoring, urban planning, and ecosystem analysis. Simulating real-life data annotation scarcity,…
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…
Copyright Detection in Large Language Models: An Ethical Approach to Generative AI Development
David Szczecina, Senan Gaffori, Edmond Li
The widespread use of Large Language Models (LLMs) raises critical concerns regarding the unauthorized inclusion of copyrighted content in training data. Existing detection framewo…
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…