Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/iCaRL

iCaRL

Reported on 12 benchmarks across 3 tasks · 1 paper · 12 SOTA

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

Methodology12 results

Continual Learningoncifar100
10-stage average accuracy· 2016-11-23
63.24
best: 68.18 (S&B)
SOTA
iCaRL: Incremental Classifier and Representation Learning arXiv:1611.07725
Incremental LearningonCIFAR-100-B0(5steps of 20 classes)
Average Incremental Accuracy· 2016-11-23
71.14
best: 79.23 (View-Batch(TCIL))
SOTA
iCaRL: Incremental Classifier and Representation Learning arXiv:1611.07725
Incremental LearningonImageNet - 10 steps
# M Params· 2016-11-23
11.68
best: 116.89 (DER w/o Pruning)
SOTA
iCaRL: Incremental Classifier and Representation Learning arXiv:1611.07725
Incremental LearningonImageNet - 10 steps
Average Incremental Accuracy· 2016-11-23
38.4
best: 85.5 (kNN-CLIP)
SOTA
iCaRL: Incremental Classifier and Representation Learning arXiv:1611.07725
Incremental LearningonImageNet - 10 steps
Average Incremental Accuracy Top-5· 2016-11-23
63.7
best: 88.59 (DyTox)
SOTA
iCaRL: Incremental Classifier and Representation Learning arXiv:1611.07725
Incremental LearningonImageNet - 10 steps
Final Accuracy· 2016-11-23
22.7
best: 63.34 (DyTox)
SOTA
iCaRL: Incremental Classifier and Representation Learning arXiv:1611.07725
Incremental LearningonImageNet - 10 steps
Final Accuracy Top-5· 2016-11-23
44
best: 84.49 (DyTox)
SOTA
iCaRL: Incremental Classifier and Representation Learning arXiv:1611.07725
Incremental LearningonImageNet100 - 10 steps
# M Params· 2016-11-23
11.22
best: 116.54 (TCIL)
SOTA
iCaRL: Incremental Classifier and Representation Learning arXiv:1611.07725
Incremental LearningonImageNet100 - 10 steps
Average Incremental Accuracy Top-5· 2016-11-23
83.6
best: 94.17 (TCIL)
SOTA
iCaRL: Incremental Classifier and Representation Learning arXiv:1611.07725
Incremental LearningonImageNet100 - 10 steps
Final Accuracy Top-5· 2016-11-23
63.8
best: 88.84 (TCIL)
SOTA
iCaRL: Incremental Classifier and Representation Learning arXiv:1611.07725
Incremental LearningonCIFAR-100 - 50 classes + 2 steps of 25 classes
Average Incremental Accuracy· 2016-11-23
71.33
best: 76.42 (TCIL)
SOTA
iCaRL: Incremental Classifier and Representation Learning arXiv:1611.07725
Class Incremental Learningoncifar100
10-stage average accuracy· 2016-11-23
63.24
best: 68.18 (S&B)
SOTA
iCaRL: Incremental Classifier and Representation Learning arXiv:1611.07725