Online continual learning (CL) aims to learn new knowledge and consolida...
Pseudo-labeling has proven to be a promising semi-supervised learning (S...
Continual learning requires models to learn new tasks while maintaining
...
Hierarchical classification aims to sort the object into a hierarchy of
...
Contrastive representation learning is an effective unsupervised method ...
Location information is proven to benefit the deep learning models on
ca...
Local discriminative representation is needed in many medical image anal...
Deep neural networks often degrade significantly when training data suff...
We introduce a one-shot segmentation method to alleviate the burden of m...