Image Classification On Tiny Imagenet 1

评估指标

Validation Acc

评测结果

各个模型在此基准测试上的表现结果

模型名称	Validation Acc	Paper Title	Repository
SwinV2-B + GradMatch	91.90	Data-Efficient Training of CNNs and Transformers with Coresets: A Stability Perspective
ViT-B/16 (PUGD)	90.74%	Perturbated Gradients Updating within Unit Space for Deep Learning
ResNeXt-50 (SAMix)	72.18%	Boosting Discriminative Visual Representation Learning with Scenario-Agnostic Mixup
UPANets	67.67	UPANets: Learning from the Universal Pixel Attention Networks	-
ResNeXt-50 (SAMix+DM)	72.39	-	-
DeiT-B/16 (PUGD)	91.02%	Perturbated Gradients Updating within Unit Space for Deep Learning
ResNeXt-50 (PuzzleMix+DM)	68.04	-	-
ResNet18 (AutoMix)	67.33%	AutoMix: Unveiling the Power of Mixup for Stronger Classifiers
ResNeXt-50 (AutoMix)	70.72%	AutoMix: Unveiling the Power of Mixup for Stronger Classifiers
DeiT-B/16-D + OCD	90.8%	OCD: Learning to Overfit with Conditional Diffusion Models
Convolutional Nystromformer for Vision (CNV)	49.56	Convolutional Xformers for Vision
WaveMixLite-160/13	54.76	WaveMix-Lite: A Resource-efficient Neural Network for Image Analysis
Swin-L	91.35%	Vision Transformers in 2022: An Update on Tiny ImageNet
ResNeXt-50 (AutoMix+DM)	71.56	-	-
EfficientNet-B1+DCL	84.39%	Direction Concentration Learning: Enhancing Congruency in Machine Learning
PreActResNet-18-3	70.24%	MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks
Context-Aware Pipeline	73.6%	Context-Aware Compilation of DNN Training Pipelines across Edge and Cloud
DenseNet + Residual Networks	60%	DenseNet Models for Tiny ImageNet Classification
Astroformer	92.98	Astroformer: More Data Might not be all you need for Classification
WaveMixLite-144/7	77.47%	WaveMix: A Resource-efficient Neural Network for Image Analysis

0 of 22 row(s) selected.