paper-with-me

Incremental Learning 벤치마크

Incremental Learning on CIFAR100B020Step(5ClassesPerStep)

5개 결과 · ⬇ CSV · JSON

Average Incremental Accuracy

70.65 72.23 73.8 75.38 76.95 2021-03 2026-09 DER(ResNet-18) — 73.98 (2021-03-31) FOSTER — 70.65 (2022-04-10) TCIL-Lite — 75.47 (2022-12-29) TCIL — 75.11 (2022-12-29) View-Batch(DER) — 76.95 (2025-03-24) DER(ResNet-18) — 73.98 (2021-03-31) TCIL-Lite — 75.47 (2022-12-29) View-Batch(DER) — 76.95 (2025-03-24)
RankModel Average Incremental Accuracy PaperCodeYear
1 View-Batch(DER) 76.95 Do Your Best and Get Enough Rest for Continual Learning hankyul2/viewbatchmodel 2025
2 TCIL-Lite 75.47 Resolving Task Confusion in Dynamic Expansion Architectures for Class Incremental Learning yellowpancake/tcil 2022
3 TCIL 75.11 Resolving Task Confusion in Dynamic Expansion Architectures for Class Incremental Learning yellowpancake/tcil 2022
4 DER(ResNet-18) 73.98 DER: Dynamically Expandable Representation for Class Incremental Learning g-u-n/pycil · Rhyssiyan/DER-ClassIL.pytorch 2021
5 FOSTER 70.65 FOSTER: Feature Boosting and Compression for Class-Incremental Learning g-u-n/pycil · G-U-N/ECCV22-FOSTER 2022
1–5 / 5 페이지당 10 20 50 100