HyperAIHyperAI
AccueilPlateformeDocsActualitésArticles de rechercheTutorielsEnsembles de donnéesWikiSOTAModèles LLMClassement GPUÉvénements
Recherche
À propos
HyperAIHyperAI

Command Palette

Search for a command to run...

Image Classification On Mini Webvision 1 0

Métriques

ImageNet Top-1 Accuracy
ImageNet Top-5 Accuracy
Top-1 Accuracy
Top-5 Accuracy

Résultats

Résultats de performance de divers modèles sur ce benchmark

Paper TitleRepository
LRA-diffusion (CLIP ViT)82.56-84.16-Label-Retrieval-Augmented Diffusion Models for Learning from Noisy Labels
Robust LR75.4893.7681.8494.12Two Wrongs Don't Make a Right: Combating Confirmation Bias in Learning with Label Noise-
PGDF (Inception-ResNet-v2)75.4593.1181.4794.03Sample Prior Guided Robust Model Learning to Suppress Noisy Labels
SSR75.7691.7680.9292.80SSR: An Efficient and Robust Framework for Learning with Unknown Label Noise
BtR75.9692.2080.8892.76Bootstrapping the Relationship Between Images and Their Clean and Noisy Labels
CoDiM-Sup (Inception-ResNet-v2)76.5291.9680.8892.48CoDiM: Learning with Noisy Labels via Contrastive Semi-Supervised Learning-
NCR+Mixup+DA (ResNet-50)--80.5-Learning with Neighbor Consistency for Noisy Labels
CMW-Net-SL+C2D77.3693.4880.4493.36CMW-Net: Learning a Class-Aware Sample Weighting Mapping for Robust Deep Learning
Dynamic Loss (Inception-ResNet-v2)74.7693.0880.1293.64Dynamic Loss For Robust Learning
CoDiM-Self (Inception-ResNet-v2)77.2492.4880.1293.52CoDiM: Learning with Noisy Labels via Contrastive Semi-Supervised Learning-
Sel-CL+ (ResNet-18)76.8493.0479.9692.64Selective-Supervised Contrastive Learning with Noisy Labels
CPC75.75±0.1493.49±0.2579.63±0.0893.46±0.10Class Prototype-based Cleaner for Label Noise Learning
PSSCL (130 epochs)79.6895.1679.5694.84PSSCL: A progressive sample selection framework with contrastive loss designed for noisy labels-
DivideMix with C2D (ResNet-50)78.57 ± 0.3793.04 ± 0.1079.42 ± 0.3492.32 ± 0.33Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy Labels
FaMUS7792.7679.492.80Faster Meta Update Strategy for Noise-Robust Deep Learning
NCR+Mixup (ResNet-50)--79.4-Learning with Neighbor Consistency for Noisy Labels
CC76.0893.8679.3693.64Centrality and Consistency: Two-Stage Clean Samples Identification for Learning with Instance-Dependent Noisy Labels
GJS (ResNet-50)75.5091.2779.2891.22Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labels
NGC (Inception-ResNet-v2)74.44 91.0479.1691.84 NGC: A Unified Framework for Learning with Open-World Noisy Data-
TCL75.492.479.192.3Twin Contrastive Learning with Noisy Labels
0 of 47 row(s) selected.