5 papers · 1 filter
Action-Guided Attention for Video Action Anticipation
Tsung-Ming Tai, Sofia Casarin, Andrea Pilzer +2
Anticipating future actions in videos is challenging, as the observed frames provide only evidence of past activities, requiring the inference of latent intentions to predict upcom…
L-SWAG: Layer-Sample Wise Activation with Gradients information for Zero-Shot NAS on Vision Transformers
Sofia Casarin, Sergio Escalera, Oswald Lanz
Training-free Neural Architecture Search (NAS) efficiently identifies high-performing neural networks using zero-cost (ZC) proxies. Unlike multi-shot and one-shot NAS approaches, Z…
GRASP-GCN: Graph-Shape Prioritization for Neural Architecture Search under Distribution Shifts
Sofia Casarin, Oswald Lanz, Sergio Escalera
Neural Architecture Search (NAS) methods have shown to output networks that largely outperform human-designed networks. However, conventional NAS methods have mostly tackled the si…
Fractals as Pre-training Datasets for Anomaly Detection and Localization
C. I. Ugwu, S. Casarin, O. Lanz
Anomaly detection is crucial in large-scale industrial manufacturing as it helps detect and localise defective parts. Pre-training feature extractors on large-scale datasets is a p…
Your Image is My Video: Reshaping the Receptive Field via Image-To-Video Differentiable AutoAugmentation and Fusion
Sofia Casarin, Cynthia I. Ugwu, Sergio Escalera +1
The landscape of deep learning research is moving towards innovative strategies to harness the true potential of data. Traditionally, emphasis has been on scaling model architectur…