2 papers
cs.CV2026
Evolving Layer-Specific Scalar Functions for Hardware-Aware Transformer Adaptation
Kieran Carrigg, Sigur de Vries, Amirhossein Sadough +1
Vision Transformers (ViTs) achieve state-of-the-art performance on challenging vision tasks, but their deployment on edge devices is severely hindered by the computational complexi…
cs.CV2026
Decorrelation Speeds Up Vision Transformers
Kieran Carrigg, Rob van Gastel, Melda Yeghaian +3
Masked Autoencoder (MAE) pre-training of vision transformers (ViTs) yields strong performance in low-label data regimes but comes with substantial computational costs, making it im…