HyperAI超神经

首页资讯最新论文教程数据集百科 SOTA LLM 模型天梯 GPU 天梯顶会

中文

HyperAI超神经

Retinal Oct Disease Classification On Oct2017

评估指标

Acc

Sensitivity

评测结果

各个模型在此基准测试上的表现结果

模型名称	Acc	Sensitivity	Paper Title	Repository
InceptionV3 (limited)	93.4	96.6	Rethinking the Inception Architecture for Computer Vision
InceptionV3	96.6	97.8	Rethinking the Inception Architecture for Computer Vision
MobileNet-v2	99.4	99.4	Optic-Net: A Novel Convolutional Neural Network for Diagnosis of Retinal Diseases from Optical Tomography Images
Xception	99.7	99.7	Optic-Net: A Novel Convolutional Neural Network for Diagnosis of Retinal Diseases from Optical Tomography Images
WideResNet-50-2 (EMA-decay=0.999)	99.69	-	Matching the Clinical Reality: Accurate OCT-Based Diagnosis From Few Labels
MobileNet-v2	98.5	99.4	MobileNetV2: Inverted Residuals and Linear Bottlenecks
Joint-Attention-Network OpticNet-71	77.4	-	Improving Robustness using Joint Attention Network For Detecting Retinal Degeneration From Optical Coherence Tomography Images
ResNet50-v1	99.3	99.3	Optic-Net: A Novel Convolutional Neural Network for Diagnosis of Retinal Diseases from Optical Tomography Images
Joint-Attention-Network MobileNet-v2	95.6	-	Improving Robustness using Joint Attention Network For Detecting Retinal Degeneration From Optical Coherence Tomography Images
OpticNet-71	99.8	99.8	Optic-Net: A Novel Convolutional Neural Network for Diagnosis of Retinal Diseases from Optical Tomography Images
ResNet50-v1	99.3	99.3	Deep Residual Learning for Image Recognition
InceptionV3 (limited)	93.4	96.6	Optic-Net: A Novel Convolutional Neural Network for Diagnosis of Retinal Diseases from Optical Tomography Images
Xception	-	99.7	Xception: Deep Learning With Depthwise Separable Convolutions
InceptionV3	96.6	97.8	Optic-Net: A Novel Convolutional Neural Network for Diagnosis of Retinal Diseases from Optical Tomography Images
Joint-Attention-Network ResNet50-v1	92.4	-	Improving Robustness using Joint Attention Network For Detecting Retinal Degeneration From Optical Coherence Tomography Images

0 of 15 row(s) selected.