Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

Continual Learning on VTAB-2 benchmark leaderboard · SOTA2 Research

Research Benchmarks

Continual Learning on VTAB-2

86.76Avg Acc (A-bar)EASE

Updated 5mo ago

Evaluation Results

Method	Links
EASE2024.03		86.76	78.86
SEMA2024.03		85.99	80.06

SOTA Paper

EASE

Expandable Subspace Ensemble for Pre-Trained Model-Based Class-Incremental Learning

Dataset

VTAB

Follow for updates

Join SOTA2 Contact

Related Benchmarks

Continual Learning on CIFAR-100 (Training Time)Continual Learning on ImageNet A Training Time on VTAB (Continual Learning)Class-Incremental Learning on ImageNet-R 50 tasks (test)Class-Incremental Learning on ImageNet-A 50 tasks (test)