paper-with-me

Incremental Learning 벤치마크

Incremental Learning on ImageNet-100 - 50 classes + 5 steps of 10 classes

5개 결과 · ⬇ CSV · JSON

Average Incremental Accuracy

65.56 69.22 72.89 76.56 80.22 2016-11 2026-09 iCaRL* — 65.56 (2016-11-23) PODNet — 75.82 (2020-04-28) CCIL-SD — 79.44 (2021-02-18) FOSTER — 80.22 (2022-04-10) RMM (ResNet-18) — 79.52 (2023-01-14) iCaRL* — 65.56 (2016-11-23) PODNet — 75.82 (2020-04-28) CCIL-SD — 79.44 (2021-02-18) FOSTER — 80.22 (2022-04-10)
RankModel Average Incremental Accuracy PaperCodeYear
1 FOSTER 80.22 FOSTER: Feature Boosting and Compression for Class-Incremental Learning g-u-n/pycil · G-U-N/ECCV22-FOSTER 2022
2 RMM (ResNet-18) 79.52 RMM: Reinforced Memory Management for Class-Incremental Learning g-u-n/pycil · aimagelab/mammoth · yaoyaoliu/rmm · +1 2023
3 CCIL-SD 79.44 Essentials for Class Incremental Learning sud0301/essentials_for_CIL 2021
4 PODNet 75.82 PODNet: Pooled Outputs Distillation for Small-Tasks Incremental Learning g-u-n/pycil · arthurdouillard/incremental_learning.pytorch 2020
5 iCaRL* 65.56 iCaRL: Incremental Classifier and Representation Learning ContinualAI/avalanche · g-u-n/pycil · aimagelab/mammoth · +7 2016
1–5 / 5 페이지당 10 20 50 100