Papers with Code · CC BY-SA 4.0
Continual Learning
Continual Learning (also known as Incremental Learning, Life-long Learning) is a concept to learn a model for a large number of tasks sequentially without forgetting knowledge obtained from the preceding tasks, where the data in the old tasks are not available anymore during training new ones.
If not mentioned, the benchmarks here are Task-CL, where task-id is provided on validation.
Source:
Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation
Three scenarios for continual learning
Lifelong Machine Learning
Continual lifelong learning with neural networks: A review
데이터셋
62개TiRODPermuted MNISTCIFAR-100 - 50 classes + 10 steps of 5 classesCIFAR-100 - 50 classes + 5 steps of 10 classessplit CIFAR-1002010 i2b2/VA5-Datasets5-dataset - 1 epochAIDSCIFAR-100 AlexNet - 300 EpochCIFAR-100 ResNet-18 - 300 EpochsCIFAR100-B0(50 tasks)-no-exemplarsCUB-200-2011 (20 tasks) - 1 epochCifar100 (20 tasks) - 1 epochCifar100-B0(10 tasks)-no-exemplarsCifar100-B0(20 tasks)-no-exemplarsCityscapesCityscapesCoarse-CIFAR100ImageNetSubsetMLT17MiniImageNet ResNet-18 - 300 EpochsOntoNotes 5.0Rotated MNISTSplit CIFAR-10 (5 tasks)Split MNIST (5 tasks)TinyImageNetTinyImageNet ResNet-18 - 300 Epochscifar100conll2003