Few-shot class-incremental learning (FSCIL) aims to design machine learn...
Rehearsal, retraining on a stored small data subset of old tasks, has be...
Multi-Label Continual Learning (MLCL) builds a class-incremental framewo...
Existing class-incremental lifelong learning studies only the data is wi...
The Lifelong Multi-Label (LML) image recognition builds an online
class-...
Sentence-based Image Editing (SIE) aims to deploy natural language to ed...
Using generative models to synthesize visual features from semantic
dist...
In our daily life, the scenes around us are always with multiple labels
...
Rehearsal, seeking to remind the model by storing old knowledge in lifel...
Extracting and fusing part features have become the key of fined-grained...
The existing Zero-Shot learning (ZSL) methods may suffer from the vague ...