Image Classification On Clothing1M

评估指标

Accuracy

评测结果

各个模型在此基准测试上的表现结果

		Paper Title	Repository
LRA-diffusion (CC)	75.7%	Label-Retrieval-Augmented Diffusion Models for Learning from Noisy Labels
SANM (DivideMix)	75.63%	Learning with Noisy labels via Self-supervised Adversarial Noisy Masking
CC	75.4%	Centrality and Consistency: Two-Stage Clean Samples Identification for Learning with Instance-Dependent Noisy Labels
Jigsaw-ViT+NCT	75.4%	Jigsaw-ViT: Learning Jigsaw Puzzles in Vision Transformer
CPC	75.40±0.10%	Class Prototype-based Cleaner for Label Noise Learning
MFRW	75.35%	Learning advisor networks for noisy image classification
Knockoffs-SPR	75.20%	Knockoffs-SPR: Clean Sample Selection in Learning with Noisy Labels
PGDF	75.19%	Sample Prior Guided Robust Model Learning to Suppress Noisy Labels
AugDesc	75.11%	Augmentation Strategies for Learning with Noisy Labels
Nested+Co-teaching (ResNet-50)	75%	Compressing Features for Learning with Noisy Labels
SSR	74.91	SSR: An Efficient and Robust Framework for Learning with Unknown Label Noise
NestedCoTeaching	74.9%	Boosting Co-teaching with Compression Regularization for Label Noise
ELR+	74.81%	Early-Learning Regularization Prevents Memorization of Noisy Labels
DivideMix	74.76%	DivideMix: Learning with Noisy Labels as Semi-supervised Learning
C2MT	74.61%	Cross-to-merge training with class balance strategy for learning with noisy labels	-
ELR+ with C2D (ResNet-50)	74.58 ± 0.15%	Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy Labels
InstanceGM	74.40%	Instance-Dependent Noisy Label Learning via Graphical Modelling
LongReMix	74.38%	LongReMix: Robust Learning with High Confidence Samples in a Noisy Label Environment
FINE + DivideMix	74.37%	FINE Samples for Learning with Noisy Labels
Negative Label Smoothing (NLS)	74.24%	To Smooth or Not? When Label Smoothing Meets Noisy Labels

0 of 50 row(s) selected.