Rate My Professor Gustavo Carneiro

Professor Carneiro specializes in machine learning, computer vision, and medical image analysis, with key interests in noisy label learning, meta-learning, semi-supervised learning, multi-modal learning, anomaly detection, domain adaptation, few-shot learning, image segmentation for left ventricle, polyps, and femoral cartilage, and classification for chest X-rays, endometriosis, and colonoscopy. His work applies to endometriosis classification, chest X-ray analysis, colonoscopy video analysis, ultrasound and MRI processing, nanoparticle pharmacokinetics, and photoacoustic imaging. He has authored more than 50 publications spanning 2002 to 2025. Notable works include "CPM: Class-Conditional Prompting Machine for Audio-Visual Segmentation" (ECCV 2024), "ItTakesTwo: Leveraging Peer Representations for Semi-supervised LiDAR Semantic Segmentation" (ECCV 2024), "Instance-Dependent Noisy-Label Learning with Graphical Model Based Noise-Rate Estimation" (ECCV 2024), "PAC-Bayes Meta-Learning With Implicit Task-Specific Posteriors" (IEEE TPAMI 2023), "Learning Support and Trivial Prototypes for Interpretable Image Classification" (ICCV 2023), "Self-supervised Monocular Trained Depth Estimation using Self-Attention" (2020), and "Combining deep learning and level set for the automated segmentation of the left ventricle of the heart from cardiac cine magnetic resonance" (2017). Awards include PAI Fellow, ARC Future Fellow, Humboldt Fellowships (2014, 2019), Marie Curie IIF Fellow, and NSERC Post-doctoral Fellow.