Long Tail Learning On Cifar 100 Lt R 50

Métriques

Error Rate

Résultats

Résultats de performance de divers modèles sur ce benchmark

		Paper Title
LDAM-DRW + SSP	52.89	Rethinking the Value of Labels for Improving Class-Imbalanced Learning
LDAM-DRW-RSG	51.5	RSG: A Simple but Effective Module for Learning Imbalanced Datasets
Hybrid-PSC	51.07	Contrastive Learning based Hybrid Networks for Long-Tailed Image Classification
CBD+TailCalibX	49.1	Feature Generation for Long-tail Classification
MetaSAug-LDAM	47.73	MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognition
MiSLAS	47.7	Improving Calibration for Long-Tailed Recognition
GCL	46.4	Long-tailed Visual Recognition via Gaussian Clouded Logit Adjustment
TADE	46.1	Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition
BCL(ResNet-32)	43.4	Balanced Contrastive Learning for Long-Tailed Visual Recognition
NCL(ResNet32)	43.2	Nested Collaborative Learning for Long-Tailed Visual Recognition
Difficulty-Net	43.1	Difficulty-Net: Learning to Predict Difficulty for Long-Tailed Recognition
LTR-weight-balancing	42.29	Long-Tailed Recognition via Weight Balancing
PC	42.25	Learning Prototype Classifiers for Long-Tailed Recognition
GML (ResNet-32)	41.9	Long-Tailed Recognition by Mutual Information Maximization between Latent Features and Ground-Truth Labels
OPeN (WideResNet-28-10)	40.2	Pure Noise to the Rescue of Insufficient Data: Improving Imbalanced Classification by Training on Random Noise Images
MDCS	39.9	MDCS: More Diverse Experts with Consistency Self-distillation for Long-tailed Recognition
DeiT-LT	39.5	DeiT-LT Distillation Strikes Back for Vision Transformer Training on Long-Tailed Datasets
SURE(ResNet-32)	36.87	SURE: SUrvey REcipes for building reliable and robust deep networks
GLMC (ResNet-34, channel x4)	36.15	Global and Local Mixture Consistency Cumulative Learning for Long-tailed Visual Recognitions
GLMC + SAM	34.72	Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data

0 of 25 row(s) selected.

Command Palette

Long Tail Learning On Cifar 100 Lt R 50

Métriques

Résultats