no code implementations • 29 Nov 2022 • Heeseung Kwon, Francisco M. Castro, Manuel J. Marin-Jimenez, Nicolas Guil, Karteek Alahari
Vision Transformers (ViTs) have become a dominant paradigm for visual representation learning with self-attention operators.
no code implementations • 31 Aug 2020 • Zihao Mu, Francisco M. Castro, Manuel J. Marin-Jimenez, Nicolas Guil, Yan-ran Li, Shiqi Yu
In this paper, we propose iLGaCo, the first incremental learning approach of covariate factors for gait recognition, where the deep model can be updated with new information without re-training it from scratch by using the whole dataset.
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)