iCaRL*

Reported on 3 benchmarks across 1 task · 1 paper · 3 SOTA

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

Methodology3 results

Incremental LearningonCIFAR-100 - 50 classes + 10 steps of 5 classes
Average Incremental Accuracy· 2016-11-23
52.57
best: 73.72 (TCIL)
SOTA
iCaRL: Incremental Classifier and Representation Learning arXiv:1611.07725
Incremental LearningonCIFAR-100 - 50 classes + 5 steps of 10 classes
Average Incremental Accuracy· 2016-11-23
57.17
best: 74.88 (TCIL)
SOTA
iCaRL: Incremental Classifier and Representation Learning arXiv:1611.07725
Incremental LearningonImageNet-100 - 50 classes + 5 steps of 10 classes
Average Incremental Accuracy· 2016-11-23
65.56
best: 80.22 (FOSTER)
SOTA
iCaRL: Incremental Classifier and Representation Learning arXiv:1611.07725