Methods based on dynamic structures are effective in addressing catastrophic forgetting on
Class-incremental learning (CIL). However, they often isolate sub-networks and overlook the …

Existing deep learning algorithms for synthetic aperture radar (SAR) image recognition are
performed with offline data. These methods must use all data to retrain the entire model …

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 …

Owing to the superior performances, exemplar-based methods with knowledge distillation
(KD) are widely applied in class incremental learning (CIL). However, it suffers from two …

Few-shot class-incremental learning (FSCIL) aims to continually learn novel data with
limited samples. One of the major challenges is the catastrophic forgetting problem of old …

Most existing studies on continual learning (CL) consider the task-based setting, where task
boundaries are known to learners during training. However, they may be impractical for real …

Class incremental learning can solve the issue of catastrophic forgetting when the trained
model is used to learn a new task in which the model may forget part of previous knowledge …

Continual learning (CL) from infinite data streams has become a challenge for neural
network models in real-world scenarios. Catastrophic forgetting of previous knowledge …

Tibetan script possesses a distinctive artistic form of writing, intricate glyph structures, and
diverse stylistic variations. In the task of text recognition, effectively handling the recognition …

Deep learning systems are prone to catastrophic forgetting when learning from a sequence
of tasks, where old data from experienced tasks is unavailable when learning from a new …