IDLVQ-C

Reported on 4 benchmarks across 2 tasks

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

Methodology4 results

Continual Learningonmini-Imagenet
Average Accuracy
51.16
best: 95.27 (PriViLege)
Continual Learningonmini-Imagenet
Last Accuracy
41.84
best: 96.24 (CoACT)
Class Incremental Learningonmini-Imagenet
Average Accuracy
51.16
best: 95.27 (PriViLege)
Class Incremental Learningonmini-Imagenet
Last Accuracy
41.84
best: 96.24 (CoACT)