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

Metric: Average Incremental Accuracy (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Sort:

#	Model↕	Average Incremental Accuracy▼	Augmentations	Paper	Date↕	Code
1	FOSTER	80.22	No	FOSTER: Feature Boosting and Compression for Cla...	2022-04-10	Code
2	RMM (ResNet-18)	79.52	No	RMM: Reinforced Memory Management for Class-Incr...	2023-01-14	Code
3	CCIL-SD	79.44	No	Essentials for Class Incremental Learning	2021-02-18	Code
4	PODNet	75.82	No	PODNet: Pooled Outputs Distillation for Small-Ta...	2020-04-28	Code
5	iCaRL*	65.56	No	iCaRL: Incremental Classifier and Representation...	2016-11-23	Code

#1FOSTERSOTA
80.22
Average Incremental Accuracy· 2022-04-10
FOSTER: Feature Boosting and Compression for Class-Incremental Learning Code
#2RMM (ResNet-18)
79.52
Average Incremental Accuracy· 2023-01-14
RMM: Reinforced Memory Management for Class-Incremental Learning Code
#3CCIL-SDSOTA
79.44
Average Incremental Accuracy· 2021-02-18
Essentials for Class Incremental Learning Code
#4PODNetSOTA
75.82
Average Incremental Accuracy· 2020-04-28
PODNet: Pooled Outputs Distillation for Small-Tasks Incremental Learning Code
#5iCaRL*SOTA
65.56
Average Incremental Accuracy· 2016-11-23
iCaRL: Incremental Classifier and Representation Learning Code