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/CIFAR-100 - 50 classes + 5 steps of 10 classes

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

Metric: Average Incremental Accuracy (higher is better)

LeaderboardDataset
Loading chart...

Results

Submit a result
#Model↕Average Incremental Accuracy▼AugmentationsPaperDate↕Code
1TCIL74.88NoResolving Task Confusion in Dynamic Expansion Ar...2022-12-29Code
2TCIL-Lite74.3NoResolving Task Confusion in Dynamic Expansion Ar...2022-12-29Code
3DER(Standard ResNet-18)72.6NoDER: Dynamically Expandable Representation for C...2021-03-31Code
4D3Former72.23NoD3Former: Debiased Dual Distilled Transformer fo...2022-07-25Code
5FOSTER69.46NoFOSTER: Feature Boosting and Compression for Cla...2022-04-10Code
6RMM (Modified ResNet-32)68.86NoRMM: Reinforced Memory Management for Class-Incr...2023-01-14Code
7DER(Modified Res-32)67.6NoDER: Dynamically Expandable Representation for C...2021-03-31Code
8CCIL-SD67.17NoEssentials for Class Incremental Learning2021-02-18Code
9PODNet (CNN)64.83NoPODNet: Pooled Outputs Distillation for Small-Ta...2020-04-28Code
10UCIR (CNN)*63.42No--Code
11UCIR (NME)*63.12No--Code
12iCaRL*57.17NoiCaRL: Incremental Classifier and Representation...2016-11-23Code
13BiC56.86NoLarge Scale Incremental Learning2019-05-30Code