Deep models, eg, CNNs and Vision Transformers, have achieved impressive achievements in many vision tasks in the closed world. However, novel classes emerge from time to time in …
Z Wang, E Yang, L Shen, H Huang - arXiv preprint arXiv:2307.09218, 2023 - arxiv.org
Forgetting refers to the loss or deterioration of previously acquired information or knowledge. While the existing surveys on forgetting have primarily focused on continual learning …
G Petit, A Popescu, H Schindler… - Proceedings of the …, 2023 - openaccess.thecvf.com
Exemplar-free class-incremental learning is very challenging due to the negative effect of catastrophic forgetting. A balance between stability and plasticity of the incremental process …
Y Zhu, T Wang, X Fu, X Yang, X Guo… - Proceedings of the …, 2023 - openaccess.thecvf.com
Image restoration under multiple adverse weather conditions aims to remove weather- related artifacts by using the single set of network parameters. In this paper, we find that …
Z Ji, D Guo, P Wang, K Yan, L Lu… - Proceedings of the …, 2023 - openaccess.thecvf.com
Deep learning empowers the mainstream medical image segmentation methods. Nevertheless, current deep segmentation approaches are not capable of efficiently and …
JW Xiao, CB Zhang, J Feng, X Liu… - Proceedings of the …, 2023 - openaccess.thecvf.com
Class incremental semantic segmentation (CISS) focuses on alleviating catastrophic forgetting to improve discrimination. Previous work mainly exploit regularization (eg …
Exemplar-free class-incremental learning (CIL) poses several challenges since it prohibits the rehearsal of data from previous tasks and thus suffers from catastrophic forgetting …
YM Tang, YX Peng, WS Zheng - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Incremental learning aims to overcome catastrophic forgetting when learning deep networks from sequential tasks. With impressive learning efficiency and performance, prompt-based …
TY Liu, S Soatto - … of the IEEE/CVF International Conference …, 2023 - openaccess.thecvf.com
Abstract Tangent Model Composition (TMC) is a method to combine component models independently fine-tuned around a pre-trained point. Component models are tangent …