Incremental Learning on CIFAR-100 - 50 classes + 2 steps of 25 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	TCIL	76.42	No	Resolving Task Confusion in Dynamic Expansion Ar...	2022-12-29	Code
2	TCIL-Lite	74.95	No	Resolving Task Confusion in Dynamic Expansion Ar...	2022-12-29	Code
3	DER (w/o P)	74.61	No	DER: Dynamically Expandable Representation for C...	2021-03-31	Code
4	iCaRL	71.33	No	iCaRL: Incremental Classifier and Representation...	2016-11-23	Code

#1TCILSOTA
76.42
Average Incremental Accuracy· 2022-12-29
Resolving Task Confusion in Dynamic Expansion Architectures for Class Incremental Learning Code
#2TCIL-Lite
74.95
Average Incremental Accuracy· 2022-12-29
Resolving Task Confusion in Dynamic Expansion Architectures for Class Incremental Learning Code
#3DER (w/o P)SOTA
74.61
Average Incremental Accuracy· 2021-03-31
DER: Dynamically Expandable Representation for Class Incremental Learning Code
#4iCaRLSOTA
71.33
Average Incremental Accuracy· 2016-11-23
iCaRL: Incremental Classifier and Representation Learning Code