HyperAI超神経
ホームニュース最新論文チュートリアルデータセット百科事典SOTALLMモデルGPU ランキング学会
検索
サイトについて
HyperAI超神経

Incremental Learning On Imagenet100 10 Steps

評価指標

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

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

モデル名
# M Params
Average Incremental Accuracy
Average Incremental Accuracy Top-5
Final Accuracy
Final Accuracy Top-5
Paper TitleRepository
TCIL116.5477.6694.1767.3488.84Resolving Task Confusion in Dynamic Expansion Architectures for Class Incremental Learning
RPSNet--87.90-74.00An Adaptive Random Path Selection Approach for Incremental Learning
BiC11.22-90.60-84.40Large Scale Incremental Learning
WA11.22-91.00-84.10Maintaining Discrimination and Fairness in Class Incremental Learning-
E2E11.22-89.92-80.29End-to-End Incremental Learning
DyTox11.0177.1592.0469.1087.98DyTox: Transformers for Continual Learning with DYnamic TOken eXpansion
DER-76.1292.7966.0788.38DER: Dynamically Expandable Representation for Class Incremental Learning
iCaRL11.22-83.60-63.80iCaRL: Incremental Classifier and Representation Learning
DER w/o Pruning112.2777.1893.2366.7087.52DER: Dynamically Expandable Representation for Class Incremental Learning
FOSTER-77.75---FOSTER: Feature Boosting and Compression for Class-Incremental Learning
TCIL-Lite26.3677.5093.6067.3087.94Resolving Task Confusion in Dynamic Expansion Architectures for Class Incremental Learning
kNN-CLIP-85.1---Revisiting a kNN-based Image Classification System with High-capacity Storage-
RMM (ResNet-18)-78.47---RMM: Reinforced Memory Management for Class-Incremental Learning
0 of 13 row(s) selected.