2 papers
cs.LG2026
Soft Dice Confidence: A Near-Optimal Confidence Estimator for Selective Prediction in Semantic Segmentation
Bruno Laboissiere Camargos Borges, Bruno Machado Pacheco, Danilo Silva
In semantic segmentation, even state-of-the-art deep learning models fall short of the performance required in certain high-stakes applications such as medical image analysis. In t…
cs.LG2025
Benchmarking noisy label detection methods
Henrique Pickler, Jorge K. S. Kamassury, Danilo Silva
Label noise is a common problem in real-world datasets, affecting both model training and validation. Clean data are essential for achieving strong performance and ensuring reliabl…