Sökning: L773:0893 6080 >
A survey on few-sho...
A survey on few-shot class-incremental learning
-
- Tian, Songsong (författare)
- Chinese Academy of Sciences, Beijing, China; University of Chinese Academy of Sciences, Beijing, China; Beijing Key Laboratory of Semiconductor Neural Network Intelligent Sensing and Computing Technology, Beijing, China
-
- Li, Lusi (författare)
- Old Dominion University, Norfolk, United States
-
- Li, Weijun (författare)
- Chinese Academy of Sciences, Beijing, China; University of Chinese Academy Of Sciences, Beijing, China; Beijing Key Laboratory Of Semiconductor Neural Network Intelligent Sensing and Computing Technology, Beijing, China
-
visa fler...
-
- Ran, Hang (författare)
- Chinese Academy of Sciences, Beijing, China; Beijing Key Laboratory Of Semiconductor Neural Network Intelligent Sensing and Computing Technology, Beijing, China
-
- Ning, Xin (författare)
- Chinese Academy of Sciences, Beijing, China; University of Chinese Academy Of Sciences, Beijing, China; Beijing Key Laboratory Of Semiconductor Neural Network Intelligent Sensing and Computing Technology, Beijing, China
-
- Tiwari, Prayag, 1991- (författare)
- Högskolan i Halmstad,Akademin för informationsteknologi
-
visa färre...
-
(creator_code:org_t)
- Oxford : Elsevier, 2024
- 2024
- Engelska.
-
Ingår i: Neural Networks. - Oxford : Elsevier. - 0893-6080 .- 1879-2782. ; 169, s. 307-324
- Relaterad länk:
-
https://doi.org/10.1...
-
visa fler...
-
https://urn.kb.se/re...
-
https://doi.org/10.1...
-
visa färre...
Abstract
Ämnesord
Stäng
- 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 neural networks to learn new tasks from just a few labeled samples without forgetting the previously learned ones. This setup can easily leads to catastrophic forgetting and overfitting problems, severely affecting model performance. Studying FSCIL helps overcome deep learning model limitations on data volume and acquisition time, while improving practicality and adaptability of machine learning models. This paper provides a comprehensive survey on FSCIL. Unlike previous surveys, we aim to synthesize few-shot learning and incremental learning, focusing on introducing FSCIL from two perspectives, while reviewing over 30 theoretical research studies and more than 20 applied research studies. From the theoretical perspective, we provide a novel categorization approach that divides the field into five subcategories, including traditional machine learning methods, meta learning-based methods, feature and feature space-based methods, replay-based methods, and dynamic network structure-based methods. We also evaluate the performance of recent theoretical research on benchmark datasets of FSCIL. From the application perspective, FSCIL has achieved impressive achievements in various fields of computer vision such as image classification, object detection, and image segmentation, as well as in natural language processing and graph. We summarize the important applications. Finally, we point out potential future research directions, including applications, problem setups, and theory development. Overall, this paper offers a comprehensive analysis of the latest advances in FSCIL from a methodological, performance, and application perspective. © 2023 The Author(s)
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datorseende och robotik (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Vision and Robotics (hsv//eng)
Nyckelord
- Catastrophic forgetting
- Class-incremental learning
- Few-shot learning
- Overfitting
- Performance evaluation
Publikations- och innehållstyp
- ref (ämneskategori)
- for (ämneskategori)
Hitta via bibliotek
Till lärosätets databas