HyperAI초신경
홈
뉴스
최신 연구 논문
튜토리얼
데이터셋
백과사전
SOTA
LLM 모델
GPU 랭킹
컨퍼런스
전체 검색
소개
한국어
HyperAI초신경
Toggle sidebar
전체 사이트 검색...
⌘
K
홈
SOTA
Image Classification
Image Classification On Cifar 100
Image Classification On Cifar 100
평가 지표
Percentage correct
평가 결과
이 벤치마크에서 각 모델의 성능 결과
Columns
모델 이름
Percentage correct
Paper Title
Repository
Stochastic Pooling
57.5
Stochastic Pooling for Regularization of Deep Convolutional Neural Networks
WRN-28-10 with reSGHMC
84.38
Non-convex Learning via Replica Exchange Stochastic Gradient MCMC
MIM
70.8
On the Importance of Normalisation Layers in Deep Learning with Piecewise Linear Activation Units
-
ViT-L (attn fine-tune)
93.0
Three things everyone should know about Vision Transformers
CoPaNet-R-164
81.10
Deep Competitive Pathway Networks
PyramidNet+ShakeDrop
89.3
AutoAugment: Learning Augmentation Policies from Data
DIANet
76.98
DIANet: Dense-and-Implicit Attention Network
WRN-28-8 (PuzzleMix+DM)
85.25
-
-
Dspike (ResNet-18)
74.24
Differentiable Spike: Rethinking Gradient-Descent for Training Spiking Neural Networks
-
Res2NeXt-29
83.44
Res2Net: A New Multi-scale Backbone Architecture
WideResNet 28-10 + CutMix (OneCycleLR scheduler)
83.97
Expeditious Saliency-guided Mix-up through Random Gradient Thresholding
ViT (lightweight, MAE pre-trained)
78.27
Pre-training of Lightweight Vision Transformers on Small Datasets with Minimally Scaled Images
-
RL-Mix (PreActResNet-18)
80.75
Expeditious Saliency-guided Mix-up through Random Gradient Thresholding
PDO-eConv (p6m,0.37M)
73
PDO-eConvs: Partial Differential Operator Based Equivariant Convolutions
ResNet-9
75.59
CNN Filter DB: An Empirical Investigation of Trained Convolutional Filters
BiT-M (ResNet)
92.17
Big Transfer (BiT): General Visual Representation Learning
Residual Gates + WRN
81.73
Learning Identity Mappings with Residual Gates
-
PyramidNet (SAM)
89.7
Sharpness-Aware Minimization for Efficiently Improving Generalization
ResMLP-24
89.5
ResMLP: Feedforward networks for image classification with data-efficient training
ABNet-2G-R1
78.792
ANDHRA Bandersnatch: Training Neural Networks to Predict Parallel Realities
0 of 210 row(s) selected.
Previous
Next