Uncertainty quantification (UQ) methods play a pivotal role in reducing the impact of uncertainties during both optimization and decision making processes. They have been …
Over the last decade, neural networks have reached almost every field of science and become a crucial part of various real world applications. Due to the increasing spread …
For future learning systems, incremental learning is desirable because it allows for: efficient resource usage by eliminating the need to retrain from scratch at the arrival of new data; …
JS Smith, L Karlinsky, V Gutta… - Proceedings of the …, 2023 - openaccess.thecvf.com
Computer vision models suffer from a phenomenon known as catastrophic forgetting when learning novel concepts from continuously shifting training data. Typical solutions for this …
Active learning aims to develop label-efficient algorithms by sampling the most representative queries to be labeled by an oracle. We describe a pool-based semi …
G Saha, I Garg, K Roy - arXiv preprint arXiv:2103.09762, 2021 - arxiv.org
The ability to learn continually without forgetting the past tasks is a desired attribute for artificial learning systems. Existing approaches to enable such learning in artificial neural …
Accurate automated medical image recognition, including classification and segmentation, is one of the most challenging tasks in medical image analysis. Recently, deep learning …
J Smith, YC Hsu, J Balloch, Y Shen… - Proceedings of the …, 2021 - openaccess.thecvf.com
Modern computer vision applications suffer from catastrophic forgetting when incrementally learning new concepts over time. The most successful approaches to alleviate this forgetting …
Continual learning (CL) aims to enable information systems to learn from a continuous data stream across time. However, it is difficult for existing deep learning architectures to learn a …