PriViLege (ViT-L)

Reported on 4 benchmarks across 2 tasks · 1 paper · 4 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Methodology4 results

Continual Learningon CUB-200-2011
Average Accuracy· 2024-04-02
79.2
SOTA
Pre-trained Vision and Language Transformers Are Few-Shot Incremental Learners arXiv:2404.02117
Continual Learningon CUB-200-2011
Last Accuracy · 2024-04-02
76.43
best: 81.19 (CoACT)
SOTA
Pre-trained Vision and Language Transformers Are Few-Shot Incremental Learners arXiv:2404.02117
Class Incremental Learningon CUB-200-2011
Average Accuracy· 2024-04-02
79.2
SOTA
Pre-trained Vision and Language Transformers Are Few-Shot Incremental Learners arXiv:2404.02117
Class Incremental Learningon CUB-200-2011
Last Accuracy · 2024-04-02
76.43
best: 81.19 (CoACT)
SOTA
Pre-trained Vision and Language Transformers Are Few-Shot Incremental Learners arXiv:2404.02117