Long Tail Learning On Cifar 100 Lt R 10

评估指标

Error Rate

评测结果

各个模型在此基准测试上的表现结果

模型名称	Error Rate	Paper Title	Repository
UniMix+Bayias (ResNet-32)	38.75	Towards Calibrated Model for Long-Tailed Visual Recognition from Prior Perspective
MiSLAS	36.8	Improving Calibration for Long-Tailed Recognition
SMC	37.5	Supervised Contrastive Learning on Blended Images for Long-tailed Recognition	-
DRO-LT	36.59	Distributional Robustness Loss for Long-tail Learning	-
LPT	9	LPT: Long-tailed Prompt Tuning for Image Classification
TADE	36.4	Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition	-
ELP	40.9	A Simple Episodic Linear Probe Improves Visual Recognition in the Wild
CDB-loss	41.26	Class-Wise Difficulty-Balanced Loss for Solving Class-Imbalance
LDAM-DRW	41.29	Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss
GLMC (ResNet-34, channel x4)	26.53	Global and Local Mixture Consistency Cumulative Learning for Long-tailed Visual Recognitions
VPT	10.4	Visual Prompt Tuning
SURE(ResNet-32)	26.76	SURE: SUrvey REcipes for building reliable and robust deep networks
PC	30.88	Learning Prototype Classifiers for Long-Tailed Recognition
CE-DRW-IC	41.4	Posterior Re-calibration for Imbalanced Datasets	-
MetaSAug-LDAM	38.72	MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognition
GLAG	35.5	Long-Tailed Classification with Gradual Balanced Loss and Adaptive Feature Generation	-
CBD+TailCalibX	38.87	Feature Generation for Long-tail Classification
GML (ResNet-32)	33.0	Long-Tailed Recognition by Mutual Information Maximization between Latent Features and Ground-Truth Labels
Difficulty-Net	34.78	Difficulty-Net: Learning to Predict Difficulty for Long-Tailed Recognition
VS + ADRW + TLA	34.41	A Unified Generalization Analysis of Re-Weighting and Logit-Adjustment for Imbalanced Learning. paper with code

0 of 31 row(s) selected.