Zobrazeno 1 - 10
of 26
pro vyhledávání: '"De Lange, Matthias"'
Autor:
Shen, Junxiao, De Lange, Matthias, Xu, Xuhai "Orson", Zhou, Enmin, Tan, Ran, Suda, Naveen, Lazarewicz, Maciej, Kristensson, Per Ola, Karlson, Amy, Strasnick, Evan
Providing users with accurate gestural interfaces, such as gesture recognition based on wrist-worn devices, is a key challenge in mixed reality. However, static machine learning processes in gesture recognition assume that training and test data come
Externí odkaz:
http://arxiv.org/abs/2401.11144
Autor:
Tan, Reuben, De Lange, Matthias, Iuzzolino, Michael, Plummer, Bryan A., Saenko, Kate, Ridgeway, Karl, Torresani, Lorenzo
Long-term activity forecasting is an especially challenging research problem because it requires understanding the temporal relationships between observed actions, as well as the variability and complexity of human activities. Despite relying on stro
Externí odkaz:
http://arxiv.org/abs/2307.12854
Autor:
De Lange, Matthias, Eghbalzadeh, Hamid, Tan, Reuben, Iuzzolino, Michael, Meier, Franziska, Ridgeway, Karl
In egocentric action recognition a single population model is typically trained and subsequently embodied on a head-mounted device, such as an augmented reality headset. While this model remains static for new users and environments, we introduce an
Externí odkaz:
http://arxiv.org/abs/2307.05784
Autor:
Pellegrini, Lorenzo, Zhu, Chenchen, Xiao, Fanyi, Yan, Zhicheng, Carta, Antonio, De Lange, Matthias, Lomonaco, Vincenzo, Sumbaly, Roshan, Rodriguez, Pau, Vazquez, David
Continual Learning, also known as Lifelong or Incremental Learning, has recently gained renewed interest among the Artificial Intelligence research community. Recent research efforts have quickly led to the design of novel algorithms able to reduce t
Externí odkaz:
http://arxiv.org/abs/2212.06833
Autor:
Verwimp, Eli, Yang, Kuo, Parisot, Sarah, Lanqing, Hong, McDonagh, Steven, Pérez-Pellitero, Eduardo, De Lange, Matthias, Tuytelaars, Tinne
In this paper we describe the design and the ideas motivating a new Continual Learning benchmark for Autonomous Driving (CLAD), that focuses on the problems of object classification and object detection. The benchmark utilises SODA10M, a recently rel
Externí odkaz:
http://arxiv.org/abs/2210.03482
Time-dependent data-generating distributions have proven to be difficult for gradient-based training of neural networks, as the greedy updates result in catastrophic forgetting of previously learned knowledge. Despite the progress in the field of con
Externí odkaz:
http://arxiv.org/abs/2205.13452
Autor:
Verwimp, Eli, Yang, Kuo, Parisot, Sarah, Lanqing, Hong, McDonagh, Steven, Pérez-Pellitero, Eduardo, De Lange, Matthias, Tuytelaars, Tinne
Training models continually to detect and classify objects, from new classes and new domains, remains an open problem. In this work, we conduct a thorough analysis of why and how object detection models forget catastrophically. We focus on distillati
Externí odkaz:
http://arxiv.org/abs/2204.01407
Publikováno v:
Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 9385-9394
Learning from non-stationary data streams and overcoming catastrophic forgetting still poses a serious challenge for machine learning research. Rather than aiming to improve state-of-the-art, in this work we provide insight into the limits and merits
Externí odkaz:
http://arxiv.org/abs/2104.07446
Autor:
Lomonaco, Vincenzo, Pellegrini, Lorenzo, Cossu, Andrea, Carta, Antonio, Graffieti, Gabriele, Hayes, Tyler L., De Lange, Matthias, Masana, Marc, Pomponi, Jary, van de Ven, Gido, Mundt, Martin, She, Qi, Cooper, Keiland, Forest, Jeremy, Belouadah, Eden, Calderara, Simone, Parisi, German I., Cuzzolin, Fabio, Tolias, Andreas, Scardapane, Simone, Antiga, Luca, Amhad, Subutai, Popescu, Adrian, Kanan, Christopher, van de Weijer, Joost, Tuytelaars, Tinne, Bacciu, Davide, Maltoni, Davide
Learning continually from non-stationary data streams is a long-standing goal and a challenging problem in machine learning. Recently, we have witnessed a renewed and fast-growing interest in continual learning, especially within the deep learning co
Externí odkaz:
http://arxiv.org/abs/2104.00405
Autor:
De Lange, Matthias, Tuytelaars, Tinne
Publikováno v:
Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 8250-8259
Attaining prototypical features to represent class distributions is well established in representation learning. However, learning prototypes online from streaming data proves a challenging endeavor as they rapidly become outdated, caused by an ever-
Externí odkaz:
http://arxiv.org/abs/2009.00919