Image Classification On Stl 10

평가 지표

Percentage correct

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	Percentage correct	Paper Title	Repository
VGG8B + LocalLearning + CO	80.75	Training Neural Networks with Local Error Signals
IIC	88.80	MixMatch: A Holistic Approach to Semi-Supervised Learning
cosine function	84.38	Image Augmentation for Object Image Classification Based On Combination of PreTrained CNN and SVM	-
NAT-M3	97.8	Neural Architecture Transfer
AMDIM	93.80	A Framework For Contrastive Self-Supervised Learning And Designing A New Approach
MP*	93.19	Increasing Trustworthiness of Deep Neural Networks via Accuracy Monitoring	-
ReMixMatch	94.77	FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
Simulated Fixations	61	A Framework For Contrastive Self-Supervised Learning And Designing A New Approach
An Analysis of Unsupervised Pre-training in Light of Recent Advances	70.2	An Analysis of Unsupervised Pre-training in Light of Recent Advances
µ2Net+ (ViT-L/16)	99.64	A Continual Development Methodology for Large-scale Multitask Dynamic ML Systems
NSRL+CN(d=32)	98.34	Toward Understanding Supervised Representation Learning with RKHS and GAN	-
Exemplar CNN	75.7	Scaling the Scattering Transform: Deep Hybrid Networks
FixMatch (CTA)	94.83	FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
FixMatch (RA)	92.02	FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
NAT-M1	96.7	Neural Architecture Transfer
Accuracy Monitoring	68.62	Increasing Trustworthiness of Deep Neural Networks via Accuracy Monitoring	-
Stacked what-where AE	74.33	Scaling the Scattering Transform: Deep Hybrid Networks
Leapfrog	83.7	Reversible Architectures for Arbitrarily Deep Residual Neural Networks
wrn16/8* D1 D1 D1	88.95	General $E(2)$-Equivariant Steerable CNNs
ResNet18(BN, 4)	81.04	Extended Batch Normalization	-

0 of 117 row(s) selected.