Displaying 420 resources
Software resources Software resources

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.

Category
Technology methodologies and landscape
Target audience
ADR Experts and Associations, Researchers and Academic
Source
Adra-e
Software resources Software resources

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.

Category
Semantic knowledge
Target audience
ADR Experts and Associations, Researchers and Academic
Source
Adra-e
Software resources Software resources

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.

Category
Reasoning Techniques
Target audience
ADR Experts and Associations, Researchers and Academic
Source
Adra-e
Software resources Software resources

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.

Category
Semantic knowledge
Target audience
ADR Experts and Associations, Researchers and Academic
Source
Adra-e
Software resources Software resources

pygrank

pygrank is an open source framework to define, run and evaluate node ranking algorithms.

Category
Multi-modal interaction
Target audience
ADR Experts and Associations, Private Sector, Researchers and Academic
Source
Adra-e
Software resources Software resources

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.

Category
Multi-modal interaction
Target audience
ADR Experts and Associations, Private Sector, Researchers and Academic
Source
Adra-e