HyperAIHyperAI超神经

Command Palette

Search for a command to run...

算力平台

Fine Grained Image Classification On Caltech

评估指标

Top-1 Error Rate

评测结果

各个模型在此基准测试上的表现结果

Paper Title
ResNet-101 (ideal number of groups)22.247%On the Ideal Number of Groups for Isometric Gradient Propagation
SE-ResNet-101 (SAP)15.949%Stochastic Subsampling With Average Pooling
PreResNet-10115.8036%How to Use Dropout Correctly on Residual Networks with Batch Normalization
AutoAugment13.07%AutoAugment: Learning Augmentation Policies from Data
ViT-S/16 (RPE w/ GAB)9.798%Understanding Gaussian Attention Bias of Vision Transformers Using Effective Receptive Fields
SEER (RegNet10B - linear eval)9.0%Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision
NNCLR8.7%With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations
µ2Net (ViT-L/16)7%An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems
VGG-19bn (Spinal FC)6.84%SpinalNet: Deep Neural Network with Gradual Input
TWIST (ResNet-50 )6.5%Self-Supervised Learning by Estimating Twin Class Distributions
ResNeXt-101-32x8d4.42%Dead Pixel Test Using Effective Receptive Field
µ2Net+ (ViT-L/16)4.06%A Continual Development Methodology for Large-scale Multitask Dynamic ML Systems
Wide-ResNet-1012.89%SpinalNet: Deep Neural Network with Gradual Input
Wide-ResNet-101 (Spinal FC)2.68%SpinalNet: Deep Neural Network with Gradual Input
VIT-L/161.98%Reduction of Class Activation Uncertainty with Background Information
Bamboo (ViT-B/16)-Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy
Pre trained wide-resnet-101-ProgressiveSpinalNet architecture for FC layers
UL-Hopfield (ULH)-Unsupervised Learning using Pretrained CNN and Associative Memory Bank
0 of 18 row(s) selected.
Fine Grained Image Classification On Caltech | SOTA | HyperAI超神经