Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
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…
cs.CV2025
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…
cs.CV2024
Image-to-Lidar Relational Distillation for Autonomous Driving Data
Anas Mahmoud, Ali Harakeh, Steven Waslander
Pre-trained on extensive and diverse multi-modal datasets, 2D foundation models excel at addressing 2D tasks with little or no downstream supervision, owing to their robust represe…