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/FOSTER

FOSTER

Reported on 11 benchmarks across 1 task · 1 paper · 4 SOTA

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

Methodology11 results

Incremental LearningonImageNet-100 - 50 classes + 25 steps of 2 classes
Average Incremental Accuracy· 2022-04-10
69.34
best: 76.54 (RMM (ResNet-18))
SOTA
FOSTER: Feature Boosting and Compression for Class-Incremental Learning arXiv:2204.04662
Incremental LearningonImageNet100 - 20 steps
Average Incremental Accuracy· 2022-04-10
74.49
SOTA
FOSTER: Feature Boosting and Compression for Class-Incremental Learning arXiv:2204.04662
Incremental LearningonCIFAR-100 - 50 classes + 25 steps of 2 classes
Average Incremental Accuracy· 2022-04-10
63.83
best: 68.68 (D3Former)
SOTA
FOSTER: Feature Boosting and Compression for Class-Incremental Learning arXiv:2204.04662
Incremental LearningonImageNet-100 - 50 classes + 5 steps of 10 classes
Average Incremental Accuracy· 2022-04-10
80.22
SOTA
FOSTER: Feature Boosting and Compression for Class-Incremental Learning arXiv:2204.04662
Incremental LearningonCIFAR-100 - 50 classes + 10 steps of 5 classes
Average Incremental Accuracy· 2022-04-10
67.95
best: 73.72 (TCIL)
FOSTER: Feature Boosting and Compression for Class-Incremental Learning arXiv:2204.04662
Incremental LearningonCIFAR-100 - 50 classes + 5 steps of 10 classes
Average Incremental Accuracy· 2022-04-10
69.46
best: 74.88 (TCIL)
FOSTER: Feature Boosting and Compression for Class-Incremental Learning arXiv:2204.04662
Incremental LearningonCIFAR100-B0(10steps of 10 classes)
Average Incremental Accuracy· 2022-04-10
72.9
best: 78.12 (View-Batch(DER))
FOSTER: Feature Boosting and Compression for Class-Incremental Learning arXiv:2204.04662
Incremental LearningonImageNet - 10 steps
Average Incremental Accuracy· 2022-04-10
68.34
best: 85.5 (kNN-CLIP)
FOSTER: Feature Boosting and Compression for Class-Incremental Learning arXiv:2204.04662
Incremental LearningonImageNet100 - 10 steps
Average Incremental Accuracy· 2022-04-10
77.75
best: 85.1 (kNN-CLIP)
FOSTER: Feature Boosting and Compression for Class-Incremental Learning arXiv:2204.04662
Incremental LearningonCIFAR100B020Step(5ClassesPerStep)
Average Incremental Accuracy· 2022-04-10
70.65
best: 76.95 (View-Batch(DER))
FOSTER: Feature Boosting and Compression for Class-Incremental Learning arXiv:2204.04662
Incremental LearningonImageNet-100 - 50 classes + 10 steps of 5 classes
Average Incremental Accuracy· 2022-04-10
77.54
best: 78.47 (RMM (ResNet-18))
FOSTER: Feature Boosting and Compression for Class-Incremental Learning arXiv:2204.04662