Long Tail Learning On Cifar 10 Lt R 100

評価指標

Error Rate

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	Error Rate	Paper Title	Repository
VS + SAM	17.6	Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data
smDRAGON	20.37	From Generalized zero-shot learning to long-tail with class descriptors
LDAM-DRW + SSP	22.17	Rethinking the Value of Labels for Improving Class-Imbalanced Learning
GCL	17.32	Long-tailed Visual Recognition via Gaussian Clouded Logit Adjustment
CE+DRS+GIT	21.24	Do Deep Networks Transfer Invariances Across Classes?
ConCutMix	13.93	Enhanced Long-Tailed Recognition with Contrastive CutMix Augmentation
ETF Classifier + DR (Resnet)	23.5	Inducing Neural Collapse in Imbalanced Learning: Do We Really Need a Learnable Classifier at the End of Deep Neural Network?
LPT	10.9	LPT: Long-tailed Prompt Tuning for Image Classification
GLMC + SAM	10.82	Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data
FBL (ResNet-32)	17.54	Feature-Balanced Loss for Long-Tailed Visual Recognition
ACE (4 experts)	18.6	ACE: Ally Complementary Experts for Solving Long-Tailed Recognition in One-Shot	-
DeiT-LT	12.5	DeiT-LT Distillation Strikes Back for Vision Transformer Training on Long-Tailed Datasets
DirMixE	16.74	Harnessing Hierarchical Label Distribution Variations in Test Agnostic Long-tail Recognition
GLMC+MaxNorm (ResNet-34, channel x4)	10.42	Global and Local Mixture Consistency Cumulative Learning for Long-tailed Visual Recognitions
TADE	16.2	Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition	-
NCL* + WGCC (ensemble)	15.4	Weight-guided class complementing for long-tailed image recognition	-
TSC(ResNet-32)	21.3	Targeted Supervised Contrastive Learning for Long-Tailed Recognition
VS + ADRW + TLA	13.58	A Unified Generalization Analysis of Re-Weighting and Logit-Adjustment for Imbalanced Learning. paper with code
SimSiam+rwSAM	14.4	Self-supervised Learning is More Robust to Dataset Imbalance
GLMC (ResNet-34, channel x4)	11.50	Global and Local Mixture Consistency Cumulative Learning for Long-tailed Visual Recognitions

0 of 28 row(s) selected.