Long Tail Learning On Cifar 10 Lt R 10

평가 지표

Error Rate

평가 결과

이 벤치마크에서 각 모델의 성능 결과

		Paper Title
RISDA	20.11	Imagine by Reasoning: A Reasoning-Based Implicit Semantic Data Augmentation for Long-Tailed Classification
Empirical Risk Minimization (ERM, CE)	13.61	Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss
Class-balanced Reweighting	13.46	Class-Balanced Loss Based on Effective Number of Samples
Class-balanced Resampling	13.21	Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss
IBLLoss	12.93	Influence-Balanced Loss for Imbalanced Visual Classification
Class-balanced Focal Loss	12.90	Class-Balanced Loss Based on Effective Number of Samples
DecTDE	12.63	Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect
M2m	12.5	M2m: Imbalanced Classification via Major-to-minor Translation
Prior-LT	12.20	Towards Calibrated Model for Long-Tailed Visual Recognition from Prior Perspective
KCL	12.00	Exploring Balanced Feature Spaces for Representation Learning
ELF&LDAM+DRW	12.00	ELF: An Early-Exiting Framework for Long-Tailed Classification
smDRAGON	11.84	From Generalized zero-shot learning to long-tail with class descriptors
LDAM-DRW	11.84	Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss
BBN	11.7	BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition
Causal Norm	11.5	Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect
LDAM-DRW + SSP	11.47	Rethinking the Value of Labels for Improving Class-Imbalanced Learning
ViT-B + LDAM	11.4	Learning Imbalanced Data with Vision Transformers
ELP	11.3	A Simple Episodic Linear Probe Improves Visual Recognition in the Wild
TSC	11.3	Targeted Supervised Contrastive Learning for Long-Tailed Recognition
LADE	11.22	Disentangling Label Distribution for Long-tailed Visual Recognition

0 of 50 row(s) selected.

Command Palette

Long Tail Learning On Cifar 10 Lt R 10

평가 지표

평가 결과