OpenCodePapers

continual-learning-on-visual-domain-decathlon

Continual Learning
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodedecathlon discipline (Score)Avg. AccuracyModelNameReleaseDate
NetTailor: Tuning the Architecture, Not Just the Weights✓ Link374479.64NetTailor2019-06-29
Depthwise Convolution is All You Need for Learning Multiple Visual Domains✓ Link3507Depthwise Soft Sharing2019-02-03
Efficient parametrization of multi-domain deep neural networks✓ Link341278.07Parallel Res. adapt.2018-03-27
Depthwise Convolution is All You Need for Learning Multiple Visual Domains✓ Link3234Depthwise Sharing2019-02-03
Efficient parametrization of multi-domain deep neural networks✓ Link3159Series Res. adapt.2018-03-27
Learning multiple visual domains with residual adapters✓ Link3131Res. adapt. (large)2017-05-22
Incremental Learning Through Deep Adaptation285177.01DAN2017-05-11
Piggyback: Adapting a Single Network to Multiple Tasks by Learning to Mask Weights✓ Link283876.60Piggyback2018-01-19
Learning multiple visual domains with residual adapters✓ Link2643Res. adapt. finetune all2017-05-22
Learning multiple visual domains with residual adapters✓ Link2621Res. adapt. decay2017-05-22
Learning without Forgetting✓ Link251576.93LwF2016-06-29
Learning multiple visual domains with residual adapters✓ Link2503Res. adapt. dom-pred2017-05-22
Learning multiple visual domains with residual adapters✓ Link2118Res. adapt.2017-05-22
Universal representations:The missing link between faces, text, planktons, and cat breeds1363BN adapt.2017-01-25
Check out how to contribute new results. Then edit this file.