Test-time adaptation provides an effective means of tackling the potential distribution shift between model training and inference, by dynamically updating the model at test time. This …
Y Wang, Z Huang, X Hong - Advances in Neural …, 2022 - proceedings.neurips.cc
State-of-the-art deep neural networks are still struggling to address the catastrophic forgetting problem in continual learning. In this paper, we propose one simple paradigm …
Deep learning systems typically suffer from catastrophic forgetting of past knowledge when acquiring new skills continually. In this paper, we emphasize two dilemmas, representation …
The staple of human intelligence is the capability of acquiring knowledge in a continuous fashion. In stark contrast, Deep Networks forget catastrophically and, for this reason, the sub …
Abstract Class Incremental Learning (CIL) aims at learning a classifier in a phase-by-phase manner, in which only data of a subset of the classes are provided at each phase. Previous …
Both generalized and incremental few-shot learning have to deal with three major challenges: learning novel classes from only few samples per class, preventing catastrophic …
J Zhang, C Chen, W Zhuang… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
This paper focuses on an under-explored yet important problem: Federated Class-Continual Learning (FCCL), where new classes are dynamically added in federated learning. Existing …
R Mohandas, M Southern, E O'Connell… - Big Data and Cognitive …, 2024 - mdpi.com
Deep learning based visual cognition has greatly improved the accuracy of defect detection, reducing processing times and increasing product throughput across a variety of …
Y Guo, B Liu, D Zhao - … of the IEEE/CVF Conference on …, 2023 - openaccess.thecvf.com
Existing continual learning (CL) research regards catastrophic forgetting (CF) as almost the only challenge. This paper argues for another challenge in class-incremental learning (CIL) …