Continual Learning on visual domain decathlon (10 tasks)

Metric: Avg. Accuracy (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Sort:

#	Model↕	Avg. Accuracy▼	Augmentations	Paper	Date↕	Code
1	NetTailor	79.64	No	NetTailor: Tuning the Architecture, Not Just the...	2019-06-29	Code
2	Parallel Res. adapt.	78.07	No	Efficient parametrization of multi-domain deep n...	2018-03-27	Code
3	DAN	77.01	No	Incremental Learning Through Deep Adaptation	2017-05-11	-
4	LwF	76.93	No	Learning without Forgetting	2016-06-29	Code
5	Piggyback	76.6	No	Piggyback: Adapting a Single Network to Multiple...	2018-01-19	Code

#1NetTailorSOTA
79.64
Avg. Accuracy· 2019-06-29
NetTailor: Tuning the Architecture, Not Just the Weights Code
#2Parallel Res. adapt.SOTA
78.07
Avg. Accuracy· 2018-03-27
Efficient parametrization of multi-domain deep neural networks Code
#3DANSOTA
77.01
Avg. Accuracy· 2017-05-11
Incremental Learning Through Deep Adaptation
#4LwFSOTA
76.93
Avg. Accuracy· 2016-06-29
Learning without Forgetting Code
#5Piggyback
76.6
Avg. Accuracy· 2018-01-19
Piggyback: Adapting a Single Network to Multiple Tasks by Learning to Mask Weights Code