1 code implementation • 3 Nov 2020 • Rafael Berral-Soler, Francisco J. Madrid-Cuevas, Rafael Muñoz-Salinas, Manuel J. Marín-Jiménez
In this work, we address this problem, defined here as the estimation of both vertical (tilt/pitch) and horizontal (pan/yaw) angles, through the use of a single Convolutional Neural Network (ConvNet) model, trying to balance precision and inference speed in order to maximize its usability in real-world applications.
no code implementations • 1 Aug 2018 • Francisco M. Castro, Nicolás Guil, Manuel J. Marín-Jiménez, Jesús Pérez-Serrano, Manuel Ujaldón
Deep Learning (DL) applications are gaining momentum in the realm of Artificial Intelligence, particularly after GPUs have demonstrated remarkable skills for accelerating their challenging computational requirements.
5 code implementations • ECCV 2018 • Francisco M. Castro, Manuel J. Marín-Jiménez, Nicolás Guil, Cordelia Schmid, Karteek Alahari
Although deep learning approaches have stood out in recent years due to their state-of-the-art results, they continue to suffer from catastrophic forgetting, a dramatic decrease in overall performance when training with new classes added incrementally.
Ranked #2 on Incremental Learning on ImageNet100 - 10 steps (# M Params metric)