10 citations · 30 across the 7 of their papers we have counts for
5 papers · 1 filter
Positive Pair Distillation Considered Harmful: Continual Meta Metric Learning for Lifelong Object Re-Identification
Kai Wang, Chenshen Wu, Andy Bagdanov +4
Lifelong object re-identification incrementally learns from a stream of re-identification tasks. The objective is to learn a representation that can be applied to all tasks and tha…
Generalized Source-free Domain Adaptation
Shiqi Yang, Yaxing Wang, Joost van de Weijer +2
Domain adaptation (DA) aims to transfer the knowledge learned from a source domain to an unlabeled target domain. Some recent works tackle source-free domain adaptation (SFDA) wher…
Generative Feature Replay For Class-Incremental Learning
Xialei Liu, Chenshen Wu, Mikel Menta +5
Humans are capable of learning new tasks without forgetting previous ones, while neural networks fail due to catastrophic forgetting between new and previously-learned tasks. We co…
Semantic Drift Compensation for Class-Incremental Learning
Lu Yu, Bartłomiej Twardowski, Xialei Liu +5
Class-incremental learning of deep networks sequentially increases the number of classes to be classified. During training, the network has only access to data of one task at a tim…
Deep Demosaicing for Edge Implementation
Ramchalam Kinattinkara Ramakrishnan, Shangling Jui, Vahid Patrovi Nia
Most digital cameras use sensors coated with a Color Filter Array (CFA) to capture channel components at every pixel location, resulting in a mosaic image that does not contain pix…