3 papers
cs.CV2026
DESA-TTA: Dynamic EMA and Source Anchoring for Test-Time Adaptation
Atif Belal, Lilian Hollard, Marco Pedersoli +1
Vision-language object detectors (VLODs) achieve strong zero-shot performance but remain vulnerable to distribution shifts during deployment. Mean-teacher methods for test-time ada…
cs.CV2025
Exploring Superposition and Interference in State-of-the-Art Low-Parameter Vision Models
Lilian Hollard, Lucas Mohimont, Nathalie Gaveau +1
The paper investigates the performance of state-of-the-art low-parameter deep neural networks for computer vision, focusing on bottleneck architectures and their behavior using sup…
cs.CV2024
LeYOLO, New Embedded Architecture for Object Detection
Lilian Hollard, Lucas Mohimont, Nathalie Gaveau +1
Efficient computation in deep neural networks is crucial for real-time object detection. However, recent advancements primarily result from improved high-performing hardware rather…