{"task":"Incremental Learning","dataset":"CIFAR100B020Step(5ClassesPerStep)","metric_names":["Average Incremental Accuracy"],"rows":[{"id":106399,"task":"Incremental Learning","parent_task":null,"dataset":"CIFAR100B020Step(5ClassesPerStep)","model_name":"View-Batch(DER)","metrics":{"Average Incremental Accuracy":"76.95"},"paper_url":"https://arxiv.org/abs/2503.18371v1","paper_title":"Do Your Best and Get Enough Rest for Continual Learning","paper_date":"2025-03-24","code_links":[{"title":"hankyul2/viewbatchmodel","url":"https://github.com/hankyul2/viewbatchmodel"}],"metrics_order":"[\"Average Incremental Accuracy\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":106400,"task":"Incremental Learning","parent_task":null,"dataset":"CIFAR100B020Step(5ClassesPerStep)","model_name":"TCIL-Lite","metrics":{"Average Incremental Accuracy":"75.47"},"paper_url":"https://arxiv.org/abs/2212.14284v2","paper_title":"Resolving Task Confusion in Dynamic Expansion Architectures for Class Incremental Learning","paper_date":"2022-12-29","code_links":[{"title":"yellowpancake/tcil","url":"https://github.com/yellowpancake/tcil"}],"metrics_order":"[\"Average Incremental Accuracy\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":106401,"task":"Incremental Learning","parent_task":null,"dataset":"CIFAR100B020Step(5ClassesPerStep)","model_name":"TCIL","metrics":{"Average Incremental Accuracy":"75.11"},"paper_url":"https://arxiv.org/abs/2212.14284v2","paper_title":"Resolving Task Confusion in Dynamic Expansion Architectures for Class Incremental Learning","paper_date":"2022-12-29","code_links":[{"title":"yellowpancake/tcil","url":"https://github.com/yellowpancake/tcil"}],"metrics_order":"[\"Average Incremental Accuracy\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":106402,"task":"Incremental Learning","parent_task":null,"dataset":"CIFAR100B020Step(5ClassesPerStep)","model_name":"DER(ResNet-18)","metrics":{"Average Incremental Accuracy":"73.98"},"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":106403,"task":"Incremental Learning","parent_task":null,"dataset":"CIFAR100B020Step(5ClassesPerStep)","model_name":"FOSTER","metrics":{"Average Incremental Accuracy":"70.65"},"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":[]}]}