HyperAI
HomeNewsLatest PapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAI

Incremental Learning On Imagenet 10 Steps

Metrics

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

Results

Performance results of various models on this benchmark

Model Name
# M Params
Average Incremental Accuracy
Average Incremental Accuracy Top-5
Final Accuracy
Final Accuracy Top-5
Paper TitleRepository
DER w/o Pruning116.8968.8488.1760.1682.86DER: Dynamically Expandable Representation for Class Incremental Learning
DyTox11.3671.2988.5963.3484.49DyTox: Transformers for Continual Learning with DYnamic TOken eXpansion
E2E11.68-72.09-52.29End-to-End Incremental Learning
WA11.6865.6786.6055.6081.10Maintaining Discrimination and Fairness in Class Incremental Learning-
DER-66.7387.0858.6281.89DER: Dynamically Expandable Representation for Class Incremental Learning
RMM (ResNet-18)-67.45---RMM: Reinforced Memory Management for Class-Incremental Learning
BiC11.68-84.00-73.20Large Scale Incremental Learning
FOSTER-68.34---FOSTER: Feature Boosting and Compression for Class-Incremental Learning
kNN-CLIP-85.5---Revisiting a kNN-based Image Classification System with High-capacity Storage-
iCaRL11.6838.4063.7022.7044.00iCaRL: Incremental Classifier and Representation Learning
0 of 10 row(s) selected.