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

		Paper Title	Repository
CE-DRW-IC	41.4	Posterior Re-calibration for Imbalanced Datasets	-
LDAM-DRW	41.29	Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss
CDB-loss	41.26	Class-Wise Difficulty-Balanced Loss for Solving Class-Imbalance
smDRAGON	41.23	From Generalized zero-shot learning to long-tail with class descriptors
LDAM-DRW + SSP	41.09	Rethinking the Value of Labels for Improving Class-Imbalanced Learning
ELP	40.9	A Simple Episodic Linear Probe Improves Visual Recognition in the Wild	-
CBD+TailCalibX	38.87	Feature Generation for Long-tail Classification
UniMix+Bayias (ResNet-32)	38.75	Towards Calibrated Model for Long-Tailed Visual Recognition from Prior Perspective
MetaSAug-LDAM	38.72	MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognition
RIDE + CMO + Curvature Regularization	38.60	Predicting and Enhancing the Fairness of DNNs with the Curvature of Perceptual Manifolds
LADE	38.3	Disentangling Label Distribution for Long-tailed Visual Recognition
Hybrid-PSC	37.63	Contrastive Learning based Hybrid Networks for Long-Tailed Image Classification	-
SMC	37.5	Supervised Contrastive Learning on Blended Images for Long-tailed Recognition	-
MiSLAS	36.8	Improving Calibration for Long-Tailed Recognition
DRO-LT	36.59	Distributional Robustness Loss for Long-tail Learning	-
TADE	36.4	Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition
LCReg	35.8	Long-tailed Recognition by Learning from Latent Categories	-
GLAG	35.5	Long-Tailed Classification with Gradual Balanced Loss and Adaptive Feature Generation	-
BCL+CUDA	35.4	CUDA: Curriculum of Data Augmentation for Long-Tailed Recognition
Difficulty-Net	34.78	Difficulty-Net: Learning to Predict Difficulty for Long-Tailed Recognition

0 of 31 row(s) selected.