DER(ResNet-18)

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 LearningonCIFAR100-B0(10steps of 10 classes)
Average Incremental Accuracy· 2021-03-31
74.64
best: 78.12 (View-Batch(DER))
SOTA
DER: Dynamically Expandable Representation for Class Incremental Learning arXiv:2103.16788
Incremental LearningonCIFAR100B020Step(5ClassesPerStep)
Average Incremental Accuracy· 2021-03-31
73.98
best: 76.95 (View-Batch(DER))
SOTA
DER: Dynamically Expandable Representation for Class Incremental Learning arXiv:2103.16788
Incremental LearningonCIFAR100B050S(2ClassesPerStep)
Average Incremental Accuracy· 2021-03-31
72.05
SOTA
DER: Dynamically Expandable Representation for Class Incremental Learning arXiv:2103.16788