Learning With Noisy Labels On Animal

Metriken

Accuracy

ImageNet Pretrained

Network

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

				Paper Title
Jigsaw-ViT	89.0	NO	DeiT-S	Jigsaw-ViT: Learning Jigsaw Puzzles in Vision Transformer
SURE	89.0	NO	Vgg19-BN	SURE: SUrvey REcipes for building reliable and robust deep networks
PSSCL	88.74	NO	Vgg19-BN	PSSCL: A progressive sample selection framework with contrastive loss designed for noisy labels
SSR	88.5	NO	Vgg19-BN	SSR: An Efficient and Robust Framework for Learning with Unknown Label Noise
BtR	88.5	NO	Vgg19-BN	Bootstrapping the Relationship Between Images and Their Clean and Noisy Labels
SPR	86.8	NO	VGG19-BN	Scalable Penalized Regression for Noise Detection in Learning with Noisy Labels
Dynamic Loss	86.5	NO	Vgg19-BN	Dynamic Loss For Robust Learning
C2MT	85.9	NO	Vgg-19-BN	Cross-to-merge training with class balance strategy for learning with noisy labels
GNL	85.9	NO	Vgg-19-BN	Partial Label Supervision for Agnostic Generative Noisy Label Learning
InstanceGM with ConvNeXt	84.7	NO	ConvNeXt	Instance-Dependent Noisy Label Learning via Graphical Modelling
InstanceGM	84.6	NO	Vgg19-BN	Instance-Dependent Noisy Label Learning via Graphical Modelling
Nested+Co-teaching (NCT)	84.1	NO	Vgg19-BN	Compressing Features for Learning with Noisy Labels
PLC	83.4	NO	Vgg19-BN	Learning with Feature-Dependent Label Noise: A Progressive Approach
InstanceGM with ResNet	82.3	NO	ResNet	Instance-Dependent Noisy Label Learning via Graphical Modelling
SELFIE	81.8	NO	Vgg19-BN	SELFIE: Refurbishing Unclean Samples for Robust Deep Learning
Nested Dropout	81.3	NO	Vgg19-BN	Boosting Co-teaching with Compression Regularization for Label Noise
CE + Dropout	81.3	NO	Vgg19-BN	Boosting Co-teaching with Compression Regularization for Label Noise
Cross Entropy	79.4	NO	Vgg19-BN	Learning with Feature-Dependent Label Noise: A Progressive Approach

0 of 18 row(s) selected.