Large deep learning models are impressive, but they struggle when real-time data is not available. Few-shot class-incremental learning (FSCIL) poses a significant challenge for …
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 …
J Dong, D Zhang, Y Cong, W Cong… - Proceedings of the …, 2023 - openaccess.thecvf.com
Federated learning-based semantic segmentation (FSS) has drawn widespread attention via decentralized training on local clients. However, most FSS models assume categories …
New classes arise frequently in our ever-changing world, eg, emerging topics in social media and new types of products in e-commerce. A model should recognize new classes …
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 …
Incremental object detection (IOD) aims to train an object detector in phases, each with annotations for new object categories. As other incremental settings, IOD is subject to …
The incremental learning paradigm in machine learning has consistently been a focus of academic research. It is similar to the way in which biological systems learn, and reduces …
DW Zhou, HL Sun, HJ Ye… - Proceedings of the IEEE …, 2024 - openaccess.thecvf.com
Abstract Class-Incremental Learning (CIL) requires a learning system to continually learn new classes without forgetting. Despite the strong performance of Pre-Trained Models …
Z Hu, Y Li, J Lyu, D Gao… - Proceedings of the …, 2023 - openaccess.thecvf.com
The problem of class incremental learning (CIL) is considered. State-of-the-art approaches use a dynamic architecture based on network expansion (NE), in which a task expert is …