Results 311 to 320 of about 842,651 (374)

CASP: Few-Shot Class-Incremental Learning with CLS Token Attention Steering Prompts [PDF]

Shuai Huang, Xuhan Lin, Yuwu Lu
openalex  

Class-Incremental Learning: A Survey

IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023
Deep models, e.g., 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 our ever-changing world, requiring a learning system to acquire new ...
Da-Wei Zhou, Qiwen Wang, Zhiyuan Qi, Han-Jia Ye, De-chuan Zhan, Ziwei Liu   +5 more
semanticscholar   +4 more sources

Compositional Few-Shot Class-Incremental Learning

CoRR
Few-shot class-incremental learning (FSCIL) is proposed to continually learn from novel classes with only a few samples after the (pre-)training on base classes with sufficient data. However, this remains a challenge.
Yixiong Zou, Shanghang Zhang, Haichen Zhou, Yuhua Li, Ruixuan Li   +4 more
semanticscholar   +4 more sources

Some of the next articles are maybe not open access.

Related searches:

Generalized Class Incremental Learning

2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2020
Many real-world machine learning systems require the ability to continually learn new knowledge. Class incremental learning receives increasing attention recently as a solution towards this goal. However, existing methods often introduce some assumptions to simplify the problem setting, which rarely holds in real-world scenarios.
Fei Mi, Lingjing Kong 0001, Tao Lin 0004, Kaicheng Yu, Boi Faltings   +4 more
openaire   +1 more source

Few-Shot Class-Incremental Learning via Training-Free Prototype Calibration

Neural Information Processing Systems, 2023
Real-world scenarios are usually accompanied by continuously appearing classes with scare labeled samples, which require the machine learning model to incrementally learn new classes and maintain the knowledge of base classes.
Qiwen Wang, Da-Wei Zhou, Yi-Kai Zhang, De-chuan Zhan, Han-Jia Ye   +4 more
semanticscholar   +1 more source

Broad Learning System for Class Incremental Learning

2018 International Conference on Security, Pattern Analysis, and Cybernetics (SPAC), 2018
The large-scale image datasets such as ImageNet and open-ended photo websites are revealing new challenges to image classification that were not apparent in smaller and fixed sets. In particular, how to handle the dynamically growing datasets efficiently, where not only the amount of training data but also the number of classes increases over time ...
Ruizhi Han, C. L. Philip Chen, Shuang Feng 0001   +2 more
openaire   +1 more source

A survey on few-shot class-incremental learning

Neural Networks
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.
, Lusi Li, Hang Ran
exaly   +5 more sources

Few-Shot Class-Incremental Learning for System-Level Fault Diagnosis of Wind Turbine

IEEE/ASME transactions on mechatronics
As a complex industrial system, wind turbine (WT) will inevitably experience new faults during long-term operation. Incremental fault diagnosis can continuously accumulate new fault knowledge from data streams, thereby expanding the model's diagnostic ...
Shen Yan, Haidong Shao, Xudong Wang, Jie Wang   +3 more
semanticscholar   +1 more source