TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

SotA/Methodology/Incremental Learning

Incremental Learning

33 benchmarks1371 papers

Incremental learning aims to develop artificially intelligent systems that can continuously learn to address new tasks from new data while preserving knowledge learned from previously learned tasks.

Benchmarks

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

Average Incremental Accuracy

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

Average Incremental AccuracyFinal Accuracy

Incremental Learning on CIFAR-100-B0(5steps of 20 classes)

Average Incremental Accuracy

Incremental Learning on ImageNet100 - 10 steps

Average Incremental Accuracy Top-5Final Accuracy Top-5Average Incremental Accuracy# M ParamsFinal Accuracy

Incremental Learning on ImageNet - 10 steps

Average Incremental AccuracyAverage Incremental Accuracy Top-5Final Accuracy Top-5# M ParamsFinal Accuracy

Incremental Learning on CIFAR100-B0(10steps of 10 classes)

Average Incremental Accuracy

Incremental Learning on CIFAR-100 - 50 classes + 25 steps of 2 classes

Average Incremental Accuracy

Incremental Learning on CIFAR100B020Step(5ClassesPerStep)

Average Incremental Accuracy

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

Average Incremental Accuracy

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

Average Incremental Accuracy

Incremental Learning on CIFAR-100 - 50 classes + 2 steps of 25 classes

Average Incremental Accuracy

Incremental Learning on ImageNet - 500 classes + 10 steps of 50 classes

Average Incremental AccuracyFinal Accuracy

Incremental Learning on ImageNet - 500 classes + 5 steps of 100 classes

Average Incremental AccuracyFinal Accuracy

Incremental Learning on ImageNet-100 - 50 classes + 25 steps of 2 classes

Average Incremental Accuracy

Incremental Learning on CIFAR-100 - 50 classes + 50 steps of 1 class

Average Incremental Accuracy

Incremental Learning on ImageNet-100 - 50 classes + 50 steps of 1 class

Average Incremental Accuracy

Incremental Learning on CIFAR-100 - 40 classes + 60 steps of 1 class (Exemplar-free)

Average Incremental Accuracy

Incremental Learning on CIFAR100B050S(2ClassesPerStep)

Average Incremental Accuracy

Incremental Learning on ImageNet - 500 classes + 25 steps of 20 classes

Average Incremental Accuracy

Incremental Learning on ImageNet-10k - 5225 classes + 5 steps of 1045 classes

Final Accuracy

Incremental Learning on ImageNet100 - 20 steps

Average Incremental Accuracy

Incremental Learning on MLT17

Acc