FeTrIL: Feature Translation for Exemplar-Free Class-Incremental Learning
Exemplar-free class-incremental learning is very challenging due to the negative effect of catastrophic forgetting.
Style-Hallucinated Dual Consistency Learning for Domain Generalized Semantic Segmentation
we study the task of synthetic-to-real domain generalized semantic segmentation, which aims to learn a model that is robust to unseen real-world scenes using only synthetic data.
Augmentation-free unsupervised approach for point clouds
Unsupervised learning on 3D point clouds has undergone a rapid evolution, especially thanks to data augmentation-based contrastive methods.
Novel Class Discovery in Semantic Segmentation (NCDSS)
We introduce a new setting of Novel Class Discovery in Semantic Segmentation (NCDSS), which aims at segmenting unlabeled images containing new classes given prior knowledge from a labeled set of disjoint classes.
InDistill
InDistill enchances the effectiveness of the Knowledge Distillation procedure by leveraging the properties of channel pruning to both reduce the capacity gap between the models and retain the information geometry.