|
efficient adaptive ensembling
|
Efficient Adaptive Ensembling for Image Classific…
|
99.61
|
2022-06-15
|
|
|
ViT-H/14
|
An Image is Worth 16x16 Words: Transformers for I…
|
99.50
|
2020-10-22
|
|
|
DINOv2 (ViT-g/14, frozen model, linear eval)
|
DINOv2: Learning Robust Visual Features without S…
|
99.50
|
2023-04-14
|
|
|
µ2Net (ViT-L/16)
|
An Evolutionary Approach to Dynamic Introduction …
|
99.49
|
2022-05-25
|
|
|
ViT-L/16
|
An Image is Worth 16x16 Words: Transformers for I…
|
99.42
|
2020-10-22
|
|
|
CaiT-M-36 U 224
|
Going deeper with Image Transformers
|
99.40
|
2021-03-31
|
|
|
CvT-W24
|
CvT: Introducing Convolutions to Vision Transform…
|
99.39
|
2021-03-29
|
|
|
BiT-L (ResNet)
|
Big Transfer (BiT): General Visual Representation…
|
99.37
|
2019-12-24
|
|
|
RDNet-L (224 res, IN-1K pretrained)
|
DenseNets Reloaded: Paradigm Shift Beyond ResNets…
|
99.31
|
2024-03-28
|
|
|
RDNet-B (224 res, IN-1K pretrained)
|
DenseNets Reloaded: Paradigm Shift Beyond ResNets…
|
99.31
|
2024-03-28
|
|
|
ViT-B (attn fine-tune)
|
Three things everyone should know about Vision Tr…
|
99.30
|
2022-03-18
|
|
|
Heinsen Routing + BEiT-large 16 224
|
An Algorithm for Routing Vectors in Sequences
|
99.20
|
2022-11-20
|
|
|
ViT-B/16 (PUGD)
|
Perturbated Gradients Updating within Unit Space …
|
99.13
|
2021-10-01
|
|
|
Astroformer
|
Astroformer: More Data Might not be all you need …
|
99.12
|
2023-04-03
|
|
|
DeiT-B
|
Training data-efficient image transformers & dist…
|
99.10
|
2020-12-23
|
|
|
TNT-B
|
Transformer in Transformer
|
99.10
|
2021-02-27
|
|
|
CeiT-S (384 finetune resolution)
|
Incorporating Convolution Designs into Visual Tra…
|
99.10
|
2021-03-22
|
|
|
EfficientNetV2-L
|
EfficientNetV2: Smaller Models and Faster Training
|
99.10
|
2021-04-01
|
|
|
AutoFormer-S | 384
|
AutoFormer: Searching Transformers for Visual Rec…
|
99.10
|
2021-07-01
|
|
|
VIT-L/16 (Spinal FC, Background)
|
Reduction of Class Activation Uncertainty with Ba…
|
99.05
|
2023-05-05
|
|
|
GPIPE + transfer learning
|
GPipe: Efficient Training of Giant Neural Network…
|
99.00
|
2018-11-16
|
|
|
TResNet-XL
|
TResNet: High Performance GPU-Dedicated Architect…
|
99.00
|
2020-03-30
|
|
|
CeiT-S
|
Incorporating Convolution Designs into Visual Tra…
|
99.00
|
2021-03-22
|
|
|
EfficientNetV2-M
|
EfficientNetV2: Smaller Models and Faster Training
|
99.00
|
2021-04-01
|
|
|
GFNet-H-B
|
Global Filter Networks for Image Classification
|
99.00
|
2021-07-01
|
|
|
BiT-M (ResNet)
|
Big Transfer (BiT): General Visual Representation…
|
98.91
|
2019-12-24
|
|
|
EfficientNet-B7
|
EfficientNet: Rethinking Model Scaling for Convol…
|
98.90
|
2019-05-28
|
|
|
RDNet-T (224 res, IN-1K pretrained)
|
DenseNets Reloaded: Paradigm Shift Beyond ResNets…
|
98.88
|
2024-03-28
|
|
|
DGMMC-S
|
Performance of Gaussian Mixture Model Classifiers…
|
98.80
|
2024-10-17
|
|
|
PyramidNet-272, S=4
|
Towards Better Accuracy-efficiency Trade-offs: Di…
|
98.71
|
2020-11-30
|
|
|
EfficientNetV2-S
|
EfficientNetV2: Smaller Models and Faster Training
|
98.70
|
2021-04-01
|
|
|
ASF-former-S
|
Adaptive Split-Fusion Transformer
|
98.70
|
2022-04-26
|
|
|
PyramidNet-272 (ASAM)
|
ASAM: Adaptive Sharpness-Aware Minimization for S…
|
98.68
|
2021-02-23
|
|
|
PyramidNet + ShakeDrop + Fast AA + FMix
|
FMix: Enhancing Mixed Sample Data Augmentation
|
98.64
|
2020-02-27
|
|
|
ViT-B/16- SAM
|
When Vision Transformers Outperform ResNets witho…
|
98.60
|
2021-06-03
|
|
|
ConvMLP-M
|
ConvMLP: Hierarchical Convolutional MLPs for Visi…
|
98.60
|
2021-09-09
|
|
|
ConvMLP-L
|
ConvMLP: Hierarchical Convolutional MLPs for Visi…
|
98.60
|
2021-09-09
|
|
|
DVT (T2T-ViT-24)
|
Not All Images are Worth 16x16 Words: Dynamic Tra…
|
98.53
|
2021-05-31
|
|
|
E2E-3M
|
Rethinking Recurrent Neural Networks and Other Im…
|
98.52
|
2020-07-30
|
|
|
CeiT-T
|
Incorporating Convolution Designs into Visual Tra…
|
98.50
|
2021-03-22
|
|
|
NAT-M4
|
Neural Architecture Transfer
|
98.40
|
2020-05-12
|
|
|
WRN-40-10, S=4
|
Towards Better Accuracy-efficiency Trade-offs: Di…
|
98.38
|
2020-11-30
|
|
|
WRN-28-10, S=4
|
Towards Better Accuracy-efficiency Trade-offs: Di…
|
98.32
|
2020-11-30
|
|
|
Shake-Shake 26 2x96d, S=4
|
Towards Better Accuracy-efficiency Trade-offs: Di…
|
98.31
|
2020-11-30
|
|
|
Dynamics 2
|
PSO-Convolutional Neural Networks with Heterogene…
|
98.31
|
2022-05-20
|
|
|
PyramidNet+ShakeDrop (Fast AA)
|
Fast AutoAugment
|
98.30
|
2019-05-01
|
|
|
ResNet50 (A1)
|
ResNet strikes back: An improved training procedu…
|
98.30
|
2021-10-01
|
|
|
NoisyDARTS-A-t
|
Noisy Differentiable Architecture Search
|
98.28
|
2020-05-07
|
|
|
NAT-M3
|
Neural Architecture Transfer
|
98.20
|
2020-05-12
|
|
|
LeViT-192
|
LeViT: a Vision Transformer in ConvNet's Clothing…
|
98.20
|
2021-04-02
|
|
|
ResNet-152-SAM
|
When Vision Transformers Outperform ResNets witho…
|
98.20
|
2021-06-03
|
|
|
ViT-S/16- SAM
|
When Vision Transformers Outperform ResNets witho…
|
98.20
|
2021-06-03
|
|
|
Bamboo (ViT-B/16)
|
Bamboo: Building Mega-Scale Vision Dataset Contin…
|
98.20
|
2022-03-15
|
|
|
DE ELBo (ViT-B/16)
|
Learning Hyperparameters via a Data-Emphasized Va…
|
98.20
|
2025-02-03
|
|
|
LeViT-256
|
LeViT: a Vision Transformer in ConvNet's Clothing…
|
98.10
|
2021-04-02
|
|
|
PyramidNet + AA (AMP)
|
Regularizing Neural Networks via Adversarial Mode…
|
98.02
|
2020-10-10
|
|
|
EnAET
|
EnAET: A Self-Trained framework for Semi-Supervis…
|
98.01
|
2019-11-21
|
|
|
MUXNet-m
|
MUXConv: Information Multiplexing in Convolutiona…
|
98.00
|
2020-03-31
|
|
|
LeViT-384
|
LeViT: a Vision Transformer in ConvNet's Clothing…
|
98.00
|
2021-04-02
|
|
|
CCT-7/3x1*
|
Escaping the Big Data Paradigm with Compact Trans…
|
98.00
|
2021-04-12
|
|
|
ConvMLP-S
|
ConvMLP: Hierarchical Convolutional MLPs for Visi…
|
98.00
|
2021-09-09
|
|
|
Proxyless-G + c/o
|
ProxylessNAS: Direct Neural Architecture Search o…
|
97.92
|
2018-12-02
|
|
|
NAT-M2
|
Neural Architecture Transfer
|
97.90
|
2020-05-12
|
|
|
WRN-28-10+AutoDropout+RandAugment
|
AutoDropout: Learning Dropout Patterns to Regular…
|
97.90
|
2021-01-05
|
|
|
SENet + ShakeShake + Cutout
|
Squeeze-and-Excitation Networks
|
97.88
|
2017-09-05
|
|
|
HCGNet-A3
|
Gated Convolutional Networks with Hybrid Connecti…
|
97.86
|
2019-08-26
|
|
|
Wide-ResNet-28-10
|
Automatic Data Augmentation via Invariance-Constr…
|
97.85
|
2022-09-29
|
|
|
ResNeXt-50 (AutoMix)
|
AutoMix: Unveiling the Power of Mixup for Stronge…
|
97.84
|
2021-03-24
|
|
|
ResNet-152x4-AGC (ImageNet-21K)
|
Effect of Pre-Training Scale on Intra- and Inter-…
|
97.82
|
2021-05-31
|
|
|
Mixer-B/16- SAM
|
When Vision Transformers Outperform ResNets witho…
|
97.80
|
2021-06-03
|
|
|
CCT-7/3x1+VTM
|
TokenMixup: Efficient Attention-guided Token-leve…
|
97.78
|
2022-10-14
|
|
|
WRN-28-10
|
MixMo: Mixing Multiple Inputs for Multiple Output…
|
97.73
|
2021-03-10
|
|
|
HCGNet-A2
|
Gated Convolutional Networks with Hybrid Connecti…
|
97.71
|
2019-08-26
|
|
|
WRN + fixup init + mixup + cutout
|
Fixup Initialization: Residual Learning Without N…
|
97.70
|
2019-01-27
|
|
|
NoisyDARTS-a
|
Noisy Differentiable Architecture Search
|
97.61
|
2020-05-07
|
|
|
TransBoost-ResNet50
|
TransBoost: Improving the Best ImageNet Performan…
|
97.61
|
2022-05-26
|
|
|
LeViT-128
|
LeViT: a Vision Transformer in ConvNet's Clothing…
|
97.60
|
2021-04-02
|
|
|
DenseNet-BC-190 + batchboost
|
batchboost: regularization for stabilizing traini…
|
97.54
|
2020-01-21
|
|
|
LeViT-128S
|
LeViT: a Vision Transformer in ConvNet's Clothing…
|
97.50
|
2021-04-02
|
|
|
Shared WRN
|
Learning Implicitly Recurrent CNNs Through Parame…
|
97.47
|
2019-02-26
|
|
|
Manifold Mixup WRN 28-10
|
Manifold Mixup: Better Representations by Interpo…
|
97.45
|
2018-06-13
|
|
|
WRN 28-14
|
Neural networks with late-phase weights
|
97.45
|
2020-07-25
|
|
|
SparseSwin
|
SparseSwin: Swin Transformer with Sparse Transfor…
|
97.43
|
2023-09-11
|
|
|
WRN-28-10 with reSGHMC
|
Non-convex Learning via Replica Exchange Stochast…
|
97.42
|
2020-08-12
|
|
|
NAT-M1
|
Neural Architecture Transfer
|
97.40
|
2020-05-12
|
|
|
ResNet-50-SAM
|
When Vision Transformers Outperform ResNets witho…
|
97.40
|
2021-06-03
|
|
|
DenseNet-BC-190 + Mixup
|
mixup: Beyond Empirical Risk Minimization
|
97.30
|
2017-10-25
|
|
|
kNN-CLIP
|
Revisiting a kNN-based Image Classification Syste…
|
97.30
|
2022-04-03
|
|
|
WaveMixLite-144/7
|
WaveMix: A Resource-efficient Neural Network for …
|
97.29
|
2022-05-28
|
|
|
Transformer local-attention (NesT-B)
|
Nested Hierarchical Transformer: Towards Accurate…
|
97.20
|
2021-05-26
|
|
|
ShakeShake-2x64d + SWA
|
Averaging Weights Leads to Wider Optima and Bette…
|
97.12
|
2018-03-14
|
|
|
PyramidNet-200 + CutMix
|
CutMix: Regularization Strategy to Train Strong C…
|
97.12
|
2019-05-13
|
|
|
Wide-ResNet-40-2
|
Automatic Data Augmentation via Invariance-Constr…
|
97.05
|
2022-09-29
|
|
|
ORN
|
Oriented Response Networks
|
97.02
|
2017-01-07
|
|
|
WRN-16-8 with reSGHMC
|
Non-convex Learning via Replica Exchange Stochast…
|
96.87
|
2020-08-12
|
|
|
ResNet_XnIDR
|
XnODR and XnIDR: Two Accurate and Fast Fully Conn…
|
96.87
|
2021-11-21
|
|
|
HCGNet-A1
|
Gated Convolutional Networks with Hybrid Connecti…
|
96.85
|
2019-08-26
|
|
|
WRN 28-10
|
Neural networks with late-phase weights
|
96.81
|
2020-07-25
|
|
|
AutoDropout
|
AutoDropout: Learning Dropout Patterns to Regular…
|
96.80
|
2021-01-05
|
|
|
WRN-28-10 + SWA
|
Averaging Weights Leads to Wider Optima and Bette…
|
96.79
|
2018-03-14
|
|
|
ConvMixer-256/16
|
Patches Are All You Need?
|
96.74
|
2022-01-24
|
|
|
EXACT (WRN-28-10)
|
EXACT: How to Train Your Accuracy
|
96.73
|
2022-05-19
|
|
|
Wide ResNet+cutout
|
Single-bit-per-weight deep convolutional neural n…
|
96.71
|
2019-07-16
|
|
|
Deep pyramidal residual network
|
Deep Pyramidal Residual Networks
|
96.69
|
2016-10-10
|
|
|
CoPaNet-R-164
|
Deep Competitive Pathway Networks
|
96.62
|
2017-09-29
|
|
|
DenseNet (DenseNet-BC-190)
|
Densely Connected Convolutional Networks
|
96.54
|
2016-08-25
|
|
|
SKNet-29 (ResNeXt-29, 16×32d)
|
Selective Kernel Networks
|
96.53
|
2019-03-15
|
|
|
Fractional MP
|
Fractional Max-Pooling
|
96.50
|
2014-12-18
|
|
|
PDO-eConv (p8, 4.6M)
|
PDO-eConvs: Partial Differential Operator Based E…
|
96.50
|
2020-07-20
|
|
|
UPANets
|
UPANets: Learning from the Universal Pixel Attent…
|
96.47
|
2021-03-15
|
|
|
GAC-SNN
|
Gated Attention Coding for Training High-performa…
|
96.46
|
2023-08-12
|
|
|
ViT (lightweight, MAE pretrained)
|
Pre-training of Lightweight Vision Transformers o…
|
96.41
|
2024-02-06
|
|
|
NAS-RL
|
Neural Architecture Search with Reinforcement Lea…
|
96.40
|
2016-11-05
|
|
|
VGG11B(2x) + LocalLearning + CO
|
Training Neural Networks with Local Error Signals
|
96.40
|
2019-01-20
|
|
|
ABNet-2G-R3-Combined
|
ANDHRA Bandersnatch: Training Neural Networks to …
|
96.38
|
2024-11-28
|
|
|
Residual Gates + WRN
|
Learning Identity Mappings with Residual Gates
|
96.35
|
2016-11-04
|
|
|
PDO-eConv (p8, 2.62M)
|
PDO-eConvs: Partial Differential Operator Based E…
|
96.32
|
2020-07-20
|
|
|
SimpleNetv2
|
Towards Principled Design of Deep Convolutional N…
|
96.29
|
2018-02-17
|
|
|
ResNet56 with reSGHMC
|
Non-convex Learning via Replica Exchange Stochast…
|
96.12
|
2020-08-12
|
|
|
Mixer-S/16- SAM
|
When Vision Transformers Outperform ResNets witho…
|
96.10
|
2021-06-03
|
|
|
ABNet-2G-R3
|
ANDHRA Bandersnatch: Training Neural Networks to …
|
96.09
|
2024-11-28
|
|
|
PreActResNet18 (AMP)
|
Regularizing Neural Networks via Adversarial Mode…
|
96.03
|
2020-10-10
|
|
|
ConvMixer-256/8
|
Patches Are All You Need?
|
96.03
|
2022-01-24
|
|
|
Local Mixup Resnet18
|
Preventing Manifold Intrusion with Locality: Loca…
|
95.97
|
2022-01-12
|
|
|
ABNet-2G-R2
|
ANDHRA Bandersnatch: Training Neural Networks to …
|
95.90
|
2024-11-28
|
|
|
ResNet-50x1-ACG (ImageNet-21K)
|
Effect of Pre-Training Scale on Intra- and Inter-…
|
95.78
|
2021-05-31
|
|
|
SAG-ViT
|
SAG-ViT: A Scale-Aware, High-Fidelity Patching Ap…
|
95.74
|
2024-11-14
|
|
|
ResNet18 (FSGDM)
|
On the Performance Analysis of Momentum Method: A…
|
95.66
|
2024-11-29
|
|
|
ACN
|
Striving for Simplicity: The All Convolutional Net
|
95.60
|
2014-12-21
|
|
|
Evolution ensemble
|
Large-Scale Evolution of Image Classifiers
|
95.60
|
2017-03-03
|
|
|
ResNet-18
|
Benchopt: Reproducible, efficient and collaborati…
|
95.55
|
2022-06-27
|
|
|
ABNet-2G-R1
|
ANDHRA Bandersnatch: Training Neural Networks to …
|
95.54
|
2024-11-28
|
|
|
SimpleNetv1
|
Lets keep it simple, Using simple architectures t…
|
95.51
|
2016-08-22
|
|
|
Mobile Net_Sam
|
MobileNetV2: Inverted Residuals and Linear Bottle…
|
95.50
|
2018-01-13
|
|
|
ResNet-1001
|
Identity Mappings in Deep Residual Networks
|
95.40
|
2016-03-16
|
|
|
ResNet32 with reSGHMC
|
Non-convex Learning via Replica Exchange Stochast…
|
95.35
|
2020-08-12
|
|
|
ResNet-18+MM+FRL
|
Learning Class Unique Features in Fine-Grained Vi…
|
95.33
|
2020-11-22
|
|
|
CCT-6/3x1
|
Escaping the Big Data Paradigm with Compact Trans…
|
95.29
|
2021-04-12
|
|
|
MomentumNet
|
Momentum Residual Neural Networks
|
95.18
|
2021-02-15
|
|
|
SRM-ResNet-56
|
SRM : A Style-based Recalibration Module for Conv…
|
95.05
|
2019-03-26
|
|
|
MixMatch
|
MixMatch: A Holistic Approach to Semi-Supervised …
|
95.05
|
2019-05-06
|
|
|
WRN-22-8 (Sparse Momentum)
|
Sparse Networks from Scratch: Faster Training wit…
|
95.04
|
2019-07-10
|
|
|
LP-BNN (ours) + cutout
|
Encoding the latent posterior of Bayesian Neural …
|
95.02
|
2020-12-04
|
|
|
Prodpoly
|
Deep Polynomial Neural Networks
|
94.90
|
2020-06-20
|
|
|
ResNet-9
|
CNN Filter DB: An Empirical Investigation of Trai…
|
94.79
|
2022-03-29
|
|
|
Stochastic Depth
|
Deep Networks with Stochastic Depth
|
94.77
|
2016-03-30
|
|
|
VGG-19 with GradInit
|
GradInit: Learning to Initialize Neural Networks …
|
94.71
|
2021-02-16
|
|
|
ResNet20 with reSGHMC
|
Non-convex Learning via Replica Exchange Stochast…
|
94.62
|
2020-08-12
|
|
|
PDO-eConv (p6m,0.37M)
|
PDO-eConvs: Partial Differential Operator Based E…
|
94.62
|
2020-07-20
|
|
|
Evolution
|
Large-Scale Evolution of Image Classifiers
|
94.60
|
2017-03-03
|
|
|
RL+NT
|
Efficient Architecture Search by Network Transfor…
|
94.60
|
2017-07-16
|
|
|
Convolutional Performer for Vision (CPV)
|
Convolutional Xformers for Vision
|
94.46
|
2022-01-25
|
|
|
PreResNet-110
|
How to Use Dropout Correctly on Residual Networks…
|
94.44
|
2023-02-13
|
|
|
ResNet+ELU
|
Deep Residual Networks with Exponential Linear Un…
|
94.40
|
2016-04-14
|
|
|
Deep Complex
|
Deep Complex Networks
|
94.40
|
2017-05-27
|
|
|
PDO-eConv (p6,0.36M)
|
PDO-eConvs: Partial Differential Operator Based E…
|
94.35
|
2020-07-20
|
|
|
Stochastic Optimization of Plain Convolutional Neural Networks with Simple methods
|
Stochastic Optimization of Plain Convolutional Ne…
|
94.29
|
2020-01-24
|
|
|
Fitnet4-LSUV
|
All you need is a good init
|
94.20
|
2015-11-19
|
|
|
R-ExplaiNet-26
|
Learning local discrete features in explainable-b…
|
94.15
|
2024-10-31
|
|
|
ABNet-2G-R0
|
ANDHRA Bandersnatch: Training Neural Networks to …
|
94.12
|
2024-11-28
|
|
|
ResNet 9 + Mish
|
Mish: A Self Regularized Non-Monotonic Activation…
|
94.05
|
2019-08-23
|
|
|
Tree+Max-Avg pooling
|
Generalizing Pooling Functions in Convolutional N…
|
94.00
|
2015-09-30
|
|
|
Beta-Rank
|
Beta-Rank: A Robust Convolutional Filter Pruning …
|
93.97
|
2023-04-15
|
|
|
ResNet-110 (SAP)
|
Stochastic Subsampling With Average Pooling
|
93.86
|
2024-09-25
|
|
|
SA quadratic embedding
|
On the Relationship between Self-Attention and Co…
|
93.80
|
2019-11-08
|
|
|
OTTT
|
Online Training Through Time for Spiking Neural N…
|
93.73
|
2022-10-09
|
|
|
SSCNN
|
Spatially-sparse convolutional neural networks
|
93.70
|
2014-09-22
|
|
|
NNCLR
|
With a Little Help from My Friends: Nearest-Neigh…
|
93.70
|
2021-04-29
|
|
|
Tuned CNN
|
Scalable Bayesian Optimization Using Deep Neural …
|
93.60
|
2015-02-19
|
|
|
Exponential Linear Units
|
Fast and Accurate Deep Network Learning by Expone…
|
93.50
|
2015-11-23
|
|
|
BNM NiN
|
Batch-normalized Maxout Network in Network
|
93.30
|
2015-11-09
|
|
|
Universum Prescription
|
Universum Prescription: Regularization using Unla…
|
93.30
|
2015-11-11
|
|
|
CMsC
|
Competitive Multi-scale Convolution
|
93.10
|
2015-11-18
|
|
|
NiN+APL
|
Learning Activation Functions to Improve Deep Neu…
|
92.50
|
2014-12-21
|
|
|
VDN
|
Training Very Deep Networks
|
92.40
|
2015-07-22
|
|
|
ResNet
|
A Bregman Learning Framework for Sparse Neural Ne…
|
92.30
|
2021-05-10
|
|
|
SWWAE
|
Stacked What-Where Auto-encoders
|
92.20
|
2015-06-08
|
|
|
FlexTCN-7
|
FlexConv: Continuous Kernel Convolutions with Dif…
|
92.20
|
2021-10-15
|
|
|
ReActNet-18
|
"BNN - BN = ?": Training Binary Neural Networks w…
|
92.08
|
2021-04-16
|
|
|
ResNet v2-20 (Mish activation)
|
Mish: A Self Regularized Non-Monotonic Activation…
|
92.02
|
2019-08-23
|
|
|
DSN
|
Deeply-Supervised Nets
|
91.80
|
2014-09-18
|
|
|
BinaryConnect
|
BinaryConnect: Training Deep Neural Networks with…
|
91.70
|
2015-11-02
|
|
|
CLS-GAN
|
Loss-Sensitive Generative Adversarial Networks on…
|
91.70
|
2017-01-23
|
|
|
MIM
|
On the Importance of Normalisation Layers in Deep…
|
91.50
|
2015-08-03
|
|
|
Spectral Representations for Convolutional Neural Networks
|
Spectral Representations for Convolutional Neural…
|
91.40
|
2015-06-11
|
|
|
DLME (ResNet-18, linear)
|
DLME: Deep Local-flatness Manifold Embedding
|
91.30
|
2022-07-07
|
|
|
RMDL (30 RDLs)
|
RMDL: Random Multimodel Deep Learning for Classif…
|
91.21
|
2018-05-03
|
|
|
Network in Network
|
Network In Network
|
91.20
|
2013-12-16
|
|
|
Deep Networks with Internal Selective Attention through Feedback Connections
|
Deep Networks with Internal Selective Attention t…
|
90.80
|
2014-07-11
|
|
|
Maxout Network (k=2)
|
Maxout Networks
|
90.65
|
2013-02-18
|
|
|
ResNet-18
|
Knowledge Representing: Efficient, Sparse Represe…
|
90.65
|
2019-11-13
|
|
|
DNN+Probabilistic Maxout
|
Improving Deep Neural Networks with Probabilistic…
|
90.60
|
2013-12-20
|
|
|
GP EI
|
Practical Bayesian Optimization of Machine Learni…
|
90.50
|
2012-06-13
|
|
|
SEER (RegNet10B)
|
Vision Models Are More Robust And Fair When Pretr…
|
90.00
|
2022-02-16
|
|
|
APAC
|
APAC: Augmented PAttern Classification with Neura…
|
89.70
|
2015-05-13
|
|
|
ensemble of 7 models
|
Dynamic Routing Between Capsules
|
89.40
|
2017-10-26
|
|
|
DCNN+GFE
|
Deep Convolutional Neural Networks as Generic Fea…
|
89.10
|
2017-10-06
|
|
|
MCDNN
|
Multi-column Deep Neural Networks for Image Class…
|
88.80
|
2012-02-13
|
|
|
RReLU
|
Empirical Evaluation of Rectified Activations in …
|
88.80
|
2015-05-05
|
|
|
F-DENSER++
|
Fast-DENSER++: Evolving Fully-Trained Deep Artifi…
|
88.73
|
2019-05-08
|
|
|
Diffusion Classifier (zero-shot)
|
Your Diffusion Model is Secretly a Zero-Shot Clas…
|
88.50
|
2023-03-28
|
|
|
ReNet
|
ReNet: A Recurrent Neural Network Based Alternati…
|
87.70
|
2015-05-03
|
|
|
OnDev-LCT-8/3
|
OnDev-LCT: On-Device Lightweight Convolutional Tr…
|
87.65
|
2024-01-22
|
|
|
OnDev-LCT-4/3
|
OnDev-LCT: On-Device Lightweight Convolutional Tr…
|
87.03
|
2024-01-22
|
|
|
TripleNet-B
|
Efficient Convolutional Neural Networks on Raspbe…
|
87.03
|
2022-04-02
|
|
|
An Analysis of Unsupervised Pre-training in Light of Recent Advances
|
An Analysis of Unsupervised Pre-training in Light…
|
86.70
|
2014-12-20
|
|
|
ThreshNet95
|
ThreshNet: An Efficient DenseNet Using Threshold …
|
86.69
|
2022-01-09
|
|
|
OnDev-LCT-8/1
|
OnDev-LCT: On-Device Lightweight Convolutional Tr…
|
86.64
|
2024-01-22
|
|
|
ShortNet1-53
|
Connection Reduction of DenseNet for Image Recogn…
|
86.64
|
2022-08-02
|
|
|
OnDev-LCT-4/1
|
OnDev-LCT: On-Device Lightweight Convolutional Tr…
|
86.61
|
2024-01-22
|
|
|
CNN+ Wilson-Cowan model RNN
|
Learning in Wilson-Cowan model for metapopulation
|
86.59
|
2024-06-24
|
|
|
ThresholdNet
|
New Pruning Method Based on DenseNet Network for …
|
86.34
|
2021-08-28
|
|
|
OnDev-LCT-2/1
|
OnDev-LCT: On-Device Lightweight Convolutional Tr…
|
86.27
|
2024-01-22
|
|
|
OnDev-LCT-2/3
|
OnDev-LCT: On-Device Lightweight Convolutional Tr…
|
86.04
|
2024-01-22
|
|
|
OnDev-LCT-1/3
|
OnDev-LCT: On-Device Lightweight Convolutional Tr…
|
85.73
|
2024-01-22
|
|
|
cvpr_class
|
ResNet strikes back: An improved training procedu…
|
85.28
|
2021-10-01
|
|
|
Stochastic Pooling
|
Stochastic Pooling for Regularization of Deep Con…
|
84.90
|
2013-01-16
|
|
|
OnDev-LCT-1/1
|
OnDev-LCT: On-Device Lightweight Convolutional Tr…
|
84.55
|
2024-01-22
|
|
|
Improving neural networks by preventing co-adaptation of feature detectors
|
Improving neural networks by preventing co-adapta…
|
84.40
|
2012-07-03
|
|
|
CCN
|
Vision Xformers: Efficient Attention for Image Cl…
|
83.36
|
2021-07-05
|
|
|
CvN
|
Vision Xformers: Efficient Attention for Image Cl…
|
83.26
|
2021-07-05
|
|
|
UL-Hopfield (ULH)
|
Unsupervised Learning using Pretrained CNN and As…
|
83.10
|
2018-05-02
|
|
|
DCGAN
|
Unsupervised Representation Learning with Deep Co…
|
82.80
|
2015-11-19
|
|
|
TM Composites Toolbox
|
An Optimized Toolbox for Advanced Image Processin…
|
82.80
|
2024-06-02
|
|
|
CKN
|
Convolutional Kernel Networks
|
82.20
|
2014-06-12
|
|
|
Sign-symmetry
|
How Important is Weight Symmetry in Backpropagati…
|
80.98
|
2015-10-17
|
|
|
pFedBreD_ns_mg
|
Personalized Federated Learning with Hidden Infor…
|
80.63
|
2022-11-19
|
|
|
1 Layer K-means
|
Unsupervised Representation Learning with Deep Co…
|
80.60
|
2015-11-19
|
|
|
APVT
|
Aggregated Pyramid Vision Transformer: Split-tran…
|
80.45
|
2022-03-02
|
|
|
LeViP
|
Vision Xformers: Efficient Attention for Image Cl…
|
79.50
|
2021-07-05
|
|
|
PCANet
|
PCANet: A Simple Deep Learning Baseline for Image…
|
78.70
|
2014-04-14
|
|
|
Hybrid ViT+RoPE
|
Vision Xformers: Efficient Attention for Image Cl…
|
76.90
|
2021-07-05
|
|
|
FLSCNN
|
Enhanced Image Classification With a Fast-Learnin…
|
75.90
|
2015-03-16
|
|
|
Hybrid Vision Nystromformer (ViN)
|
Vision Xformers: Efficient Attention for Image Cl…
|
75.26
|
2021-07-05
|
|
|
CTM Drop Clause
|
Drop Clause: Enhancing Performance, Interpretabil…
|
75.10
|
2021-05-30
|
|
|
Hybrid PiN
|
Vision Xformers: Efficient Attention for Image Cl…
|
74.00
|
2021-07-05
|
|
|
SmoothNetV1
|
SmoothNets: Optimizing CNN architecture design fo…
|
73.50
|
2022-05-09
|
|
|
SNN
|
Sneaky Spikes: Uncovering Stealthy Backdoor Attac…
|
68.30
|
2023-02-13
|
|
|
Vision Nystromformer (ViN)
|
Vision Xformers: Efficient Attention for Image Cl…
|
65.06
|
2021-07-05
|
|
|
ANODE
|
Augmented Neural ODEs
|
60.60
|
2019-04-02
|
|
|
ASF-former-B
|
Adaptive Split-Fusion Transformer
|
|
2022-04-26
|
|