natural-language-processing-7

unsupervised class-incremental learning

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in unsupervised-class-incremental-learning-21

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find unsupervised-class-incremental-learning-21 models and implementations

Datasets

No datasets available.

Subtasks

No subtasks available.

Most implemented papers

Proxy Anchor-based Unsupervised Learning for Continuous Generalized Category Discovery

Junmo Kim, Hyungmin Kim, Sungho Suh, Daehwan Kim, Daun Jeong, Hansang Cho•Wed Jul 19 2023

This paper proposes a novel unsupervised class incremental learning approach for discovering novel categories on unlabeled sets without prior knowledge that outperforms the state-of-the-art methods on fine-grained datasets under real-world scenarios.

26

Content

0

Paper Graph

Plasticity-Optimized Complementary Networks for Unsupervised Continual Learning

Joost van de Weijer, Bartłomiej Twardowski, Alex Gomez-Villa, Kai Wang•Mon Sep 11 2023

This work proposes to train an expert network that is relieved of the duty of keeping the previous knowledge and can focus on performing optimally on the new tasks (optimizing plasticity), and shows that this approach outperforms other CURL exemplar-free methods in few- and many-task split settings.

14 0

Paper Graph

Adding a benchmark result helps the community track progress.