IBM

Reported on 4 benchmarks across 1 task · 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 LearningonCIFAR-100 AlexNet - 300 Epoch
Accuracy· 2023-12-01
82.69
SOTA
Towards Redundancy-Free Sub-networks in Continual Learning arXiv:2312.00840
Continual LearningonTinyImageNet ResNet-18 - 300 Epochs
Accuracy· 2023-12-01
52.38
SOTA
Towards Redundancy-Free Sub-networks in Continual Learning arXiv:2312.00840
Continual LearningonCIFAR-100 ResNet-18 - 300 Epochs
Accuracy· 2023-12-01
88.15
SOTA
Towards Redundancy-Free Sub-networks in Continual Learning arXiv:2312.00840
Continual LearningonMiniImageNet ResNet-18 - 300 Epochs
Accuracy· 2023-12-01
53.9
SOTA
Towards Redundancy-Free Sub-networks in Continual Learning arXiv:2312.00840