{"task":"Incremental Learning","dataset":"ImageNet-100 - 50 classes + 10 steps of 5 classes","metric_names":["Average Incremental Accuracy"],"rows":[{"id":106419,"task":"Incremental Learning","parent_task":null,"dataset":"ImageNet-100 - 50 classes + 10 steps of 5 classes","model_name":"RMM (ResNet-18)","metrics":{"Average Incremental Accuracy":"78.47"},"paper_url":"https://arxiv.org/abs/2301.05792v1","paper_title":"RMM: Reinforced Memory Management for Class-Incremental Learning","paper_date":"2023-01-14","code_links":[{"title":"g-u-n/pycil","url":"https://github.com/g-u-n/pycil"},{"title":"aimagelab/mammoth","url":"https://github.com/aimagelab/mammoth"},{"title":"yaoyaoliu/rmm","url":"https://gitlab.mpi-klsb.mpg.de/yaoyaoliu/rmm"},{"title":"yaoyaoliu/rmm","url":"https://gitlab.mpi-klsb.mpg.de/yaoyaoliu/rmm/"}],"metrics_order":"[\"Average Incremental Accuracy\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":106420,"task":"Incremental Learning","parent_task":null,"dataset":"ImageNet-100 - 50 classes + 10 steps of 5 classes","model_name":"DER","metrics":{"Average Incremental Accuracy":"77.73"},"paper_url":"https://arxiv.org/abs/2103.16788v1","paper_title":"DER: Dynamically Expandable Representation for Class Incremental Learning","paper_date":"2021-03-31","code_links":[{"title":"g-u-n/pycil","url":"https://github.com/g-u-n/pycil"},{"title":"Rhyssiyan/DER-ClassIL.pytorch","url":"https://github.com/Rhyssiyan/DER-ClassIL.pytorch"}],"metrics_order":"[\"Average Incremental Accuracy\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":106421,"task":"Incremental Learning","parent_task":null,"dataset":"ImageNet-100 - 50 classes + 10 steps of 5 classes","model_name":"FOSTER","metrics":{"Average Incremental Accuracy":"77.54"},"paper_url":"https://arxiv.org/abs/2204.04662v2","paper_title":"FOSTER: Feature Boosting and Compression for Class-Incremental Learning","paper_date":"2022-04-10","code_links":[{"title":"g-u-n/pycil","url":"https://github.com/g-u-n/pycil"},{"title":"G-U-N/ECCV22-FOSTER","url":"https://github.com/G-U-N/ECCV22-FOSTER"}],"metrics_order":"[\"Average Incremental Accuracy\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":106422,"task":"Incremental Learning","parent_task":null,"dataset":"ImageNet-100 - 50 classes + 10 steps of 5 classes","model_name":"CCIL-SD","metrics":{"Average Incremental Accuracy":"76.77"},"paper_url":"https://arxiv.org/abs/2102.09517v1","paper_title":"Essentials for Class Incremental Learning","paper_date":"2021-02-18","code_links":[{"title":"sud0301/essentials_for_CIL","url":"https://github.com/sud0301/essentials_for_CIL"}],"metrics_order":"[\"Average Incremental Accuracy\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":106423,"task":"Incremental Learning","parent_task":null,"dataset":"ImageNet-100 - 50 classes + 10 steps of 5 classes","model_name":"PODNet","metrics":{"Average Incremental Accuracy":"73.14"},"paper_url":"https://arxiv.org/abs/2004.13513v3","paper_title":"PODNet: Pooled Outputs Distillation for Small-Tasks Incremental Learning","paper_date":"2020-04-28","code_links":[{"title":"g-u-n/pycil","url":"https://github.com/g-u-n/pycil"},{"title":"arthurdouillard/incremental_learning.pytorch","url":"https://github.com/arthurdouillard/incremental_learning.pytorch"}],"metrics_order":"[\"Average Incremental Accuracy\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]}]}