CCIL-SD

Reported on 5 benchmarks across 1 task · 1 paper · 5 SOTA

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

Methodology5 results

Incremental LearningonCIFAR-100 - 50 classes + 10 steps of 5 classes
Average Incremental Accuracy· 2021-02-18
65.86
best: 73.72 (TCIL)
SOTA
Essentials for Class Incremental Learning arXiv:2102.09517
Incremental LearningonCIFAR-100 - 50 classes + 5 steps of 10 classes
Average Incremental Accuracy· 2021-02-18
67.17
best: 74.88 (TCIL)
SOTA
Essentials for Class Incremental Learning arXiv:2102.09517
Incremental LearningonImageNet - 500 classes + 5 steps of 100 classes
Average Incremental Accuracy· 2021-02-18
68.04
best: 69.21 (RMM (ResNet-18))
SOTA
Essentials for Class Incremental Learning arXiv:2102.09517
Incremental LearningonImageNet-100 - 50 classes + 10 steps of 5 classes
Average Incremental Accuracy· 2021-02-18
76.77
best: 78.47 (RMM (ResNet-18))
SOTA
Essentials for Class Incremental Learning arXiv:2102.09517
Incremental LearningonImageNet-100 - 50 classes + 5 steps of 10 classes
Average Incremental Accuracy· 2021-02-18
79.44
best: 80.22 (FOSTER)
SOTA
Essentials for Class Incremental Learning arXiv:2102.09517