6 papers
Rethinking the Teacher-Student Framework for Test-Time Adaptation
Damian Sójka, Marc Masana, Bartłomiej Twardowski +1
Test-Time Adaptation (TTA) has recently emerged as a promising strategy that allows the adaptation of pre-trained models to changing data distributions at deployment time, without…
FedADAS: Communication-Efficient Federated Distillation for On-Device Driver Yawn Recognition in Vehicular Networks
Ahmed Mujtaba, Gleb Radchenko, Marc Masana +1
Driver fatigue is a critical safety concern in advanced driver assistance systems. Driver monitoring models trained off-site on static datasets adapt poorly to real-world condition…
Ranked Activation Shift for Post-Hoc Out-of-Distribution Detection
Gianluca Guglielmo, Marc Masana
State-of-the-art post-hoc out-of-distribution detection methods rely on intermediate layer activation editing. However, they exhibit inconsistent performance across datasets and mo…
Subspace Optimization for Backpropagation-Free Continual Test-Time Adaptation
Damian Sójka, Sebastian Cygert, Marc Masana
We introduce PACE, a backpropagation-free continual test-time adaptation system that directly optimizes the affine parameters of normalization layers. Existing derivative-free appr…
YawDD+: Frame-level Annotations for Accurate Yawn Prediction
Ahmed Mujtaba, Gleb Radchenko, Marc Masana +1
Driver fatigue remains a leading cause of road accidents, responsible for 24% of crashes. While yawning serves as an early behavioral indicator of fatigue, existing approaches face…
Federated Distillation on Edge Devices: Efficient Client-Side Filtering for Non-IID Data
Ahmed Mujtaba, Gleb Radchenko, Radu Prodan +1
Federated distillation has emerged as a promising collaborative machine learning approach, offering enhanced privacy protection and reduced communication compared to traditional fe…