1 citations · 1 across the 4 of their papers we have counts for
5 papers
CLIP Is Shortsighted: Paying Attention Beyond the First Sentence
Marc-Antoine Lavoie, Anas Mahmoud, Aldo Zaimi +2
CLIP models learn transferable multi-modal features via image-text contrastive learning on internet-scale data. They are widely used in zero-shot classification, multi-modal retrie…
Trends in Motion Prediction Toward Deployable and Generalizable Autonomy: A Revisit and Perspectives
Letian Wang, Marc-Antoine Lavoie, Sandro Papais +13
Motion prediction, recently popularized as world models, refers to the anticipation of future agent states or scene evolution, which is rooted in human cognition, bridging percepti…
Large Self-Supervised Models Bridge the Gap in Domain Adaptive Object Detection
Marc-Antoine Lavoie, Anas Mahmoud, Steven L. Waslander
The current state-of-the-art methods in domain adaptive object detection (DAOD) use Mean Teacher self-labelling, where a teacher model, directly derived as an exponential moving av…
Feature Density Estimation for Out-of-Distribution Detection via Normalizing Flows
Evan D. Cook, Marc-Antoine Lavoie, Steven L. Waslander
Out-of-distribution (OOD) detection is a critical task for safe deployment of learning systems in the open world setting. In this work, we investigate the use of feature density es…
Class Instance Balanced Learning for Long-Tailed Classification
Marc-Antoine Lavoie, Steven Waslander
The long-tailed image classification task remains important in the development of deep neural networks as it explicitly deals with large imbalances in the class frequencies of the…