|
efficient adaptive ensembling
|
Efficient Adaptive Ensembling for Image Classific…
|
96.81
|
2022-06-15
|
|
|
EffNet-L2 (SAM)
|
Sharpness-Aware Minimization for Efficiently Impr…
|
96.08
|
2020-10-03
|
|
|
Swin-L + ML-Decoder
|
ML-Decoder: Scalable and Versatile Classification…
|
95.10
|
2021-11-25
|
|
|
µ2Net (ViT-L/16)
|
An Evolutionary Approach to Dynamic Introduction …
|
94.95
|
2022-05-25
|
|
|
ViT-B-16 (ImageNet-21K-P pretrain)
|
ImageNet-21K Pretraining for the Masses
|
94.20
|
2021-04-22
|
|
|
CvT-W24
|
CvT: Introducing Convolutions to Vision Transform…
|
94.09
|
2021-03-29
|
|
|
ViT-B/16 (PUGD)
|
Perturbated Gradients Updating within Unit Space …
|
93.95
|
2021-10-01
|
|
|
Heinsen Routing + BEiT-large 16 224
|
An Algorithm for Routing Vectors in Sequences
|
93.80
|
2022-11-20
|
|
|
BiT-L (ResNet)
|
Big Transfer (BiT): General Visual Representation…
|
93.51
|
2019-12-24
|
|
|
VIT-L/16 (Spinal FC, Background)
|
Reduction of Class Activation Uncertainty with Ba…
|
93.31
|
2023-05-05
|
|
|
CaiT-M-36 U 224
|
Going deeper with Image Transformers
|
93.10
|
2021-03-31
|
|
|
ViT-L (attn fine-tune)
|
Three things everyone should know about Vision Tr…
|
93.00
|
2022-03-18
|
|
|
TResNet-L-V2
|
TResNet: High Performance GPU-Dedicated Architect…
|
92.60
|
2020-03-30
|
|
|
EfficientNetV2-L
|
EfficientNetV2: Smaller Models and Faster Training
|
92.30
|
2021-04-01
|
|
|
EfficientNetV2-M
|
EfficientNetV2: Smaller Models and Faster Training
|
92.20
|
2021-04-01
|
|
|
BiT-M (ResNet)
|
Big Transfer (BiT): General Visual Representation…
|
92.17
|
2019-12-24
|
|
|
CeiT-S
|
Incorporating Convolution Designs into Visual Tra…
|
91.80
|
2021-03-22
|
|
|
CeiT-S (384 finetune resolution)
|
Incorporating Convolution Designs into Visual Tra…
|
91.80
|
2021-03-22
|
|
|
EfficientNet-B7
|
EfficientNet: Rethinking Model Scaling for Convol…
|
91.70
|
2019-05-28
|
|
|
EfficientNetV2-S
|
EfficientNetV2: Smaller Models and Faster Training
|
91.50
|
2021-04-01
|
|
|
GPIPE
|
GPipe: Efficient Training of Giant Neural Network…
|
91.30
|
2018-11-16
|
|
|
DGMMC-S
|
Performance of Gaussian Mixture Model Classifiers…
|
91.20
|
2024-10-17
|
|
|
TNT-B
|
Transformer in Transformer
|
91.10
|
2021-02-27
|
|
|
DeiT-B
|
Training data-efficient image transformers & dist…
|
90.80
|
2020-12-23
|
|
|
GFNet-H-B
|
Global Filter Networks for Image Classification
|
90.30
|
2021-07-01
|
|
|
E2E-3M
|
Rethinking Recurrent Neural Networks and Other Im…
|
90.27
|
2020-07-30
|
|
|
Bamboo (ViT-B/16)
|
Bamboo: Building Mega-Scale Vision Dataset Contin…
|
90.20
|
2022-03-15
|
|
|
PyramidNet-272 (ASAM)
|
ASAM: Adaptive Sharpness-Aware Minimization for S…
|
89.90
|
2021-02-23
|
|
|
PyramidNet (SAM)
|
Sharpness-Aware Minimization for Efficiently Impr…
|
89.70
|
2020-10-03
|
|
|
DVT (T2T-ViT-24)
|
Not All Images are Worth 16x16 Words: Dynamic Tra…
|
89.63
|
2021-05-31
|
|
|
ResMLP-24
|
ResMLP: Feedforward networks for image classifica…
|
89.50
|
2021-05-07
|
|
|
PyramidNet-272, S=4
|
Towards Better Accuracy-efficiency Trade-offs: Di…
|
89.46
|
2020-11-30
|
|
|
CeiT-T
|
Incorporating Convolution Designs into Visual Tra…
|
89.40
|
2021-03-22
|
|
|
PyramidNet+ShakeDrop
|
AutoAugment: Learning Augmentation Policies from …
|
89.30
|
2018-05-24
|
|
|
ViT-B/16- SAM
|
When Vision Transformers Outperform ResNets witho…
|
89.10
|
2021-06-03
|
|
|
ConvMLP-M
|
ConvMLP: Hierarchical Convolutional MLPs for Visi…
|
89.10
|
2021-09-09
|
|
|
ConvMLP-L
|
ConvMLP: Hierarchical Convolutional MLPs for Visi…
|
88.60
|
2021-09-09
|
|
|
ResNet-152x4-AGC (ImageNet-21K)
|
Effect of Pre-Training Scale on Intra- and Inter-…
|
88.54
|
2021-05-31
|
|
|
ColorNet
|
ColorNet: Investigating the importance of color s…
|
88.40
|
2019-02-01
|
|
|
PyramidNet+ShakeDrop (Fast AA)
|
Fast AutoAugment
|
88.30
|
2019-05-01
|
|
|
NAT-M4
|
Neural Architecture Transfer
|
88.30
|
2020-05-12
|
|
|
CeiT-T (384 finetune resolution)
|
Incorporating Convolution Designs into Visual Tra…
|
88.00
|
2021-03-22
|
|
|
NAT-M3
|
Neural Architecture Transfer
|
87.70
|
2020-05-12
|
|
|
ViT-S/16- SAM
|
When Vision Transformers Outperform ResNets witho…
|
87.60
|
2021-06-03
|
|
|
NAT-M2
|
Neural Architecture Transfer
|
87.50
|
2020-05-12
|
|
|
Dynamics 1
|
PSO-Convolutional Neural Networks with Heterogene…
|
87.48
|
2022-05-20
|
|
|
DenseNet-BC-190, S=4
|
Towards Better Accuracy-efficiency Trade-offs: Di…
|
87.44
|
2020-11-30
|
|
|
ConvMLP-S
|
ConvMLP: Hierarchical Convolutional MLPs for Visi…
|
87.40
|
2021-09-09
|
|
|
ResMLP-12
|
ResMLP: Feedforward networks for image classifica…
|
87.00
|
2021-05-07
|
|
|
WRN-40-10, S=4
|
Towards Better Accuracy-efficiency Trade-offs: Di…
|
86.90
|
2020-11-30
|
|
|
ResNet50 (A1)
|
ResNet strikes back: An improved training procedu…
|
86.90
|
2021-10-01
|
|
|
WRN-28-10 * 3
|
MixMo: Mixing Multiple Inputs for Multiple Output…
|
86.81
|
2021-03-10
|
|
|
PyramidNet + AA (AMP)
|
Regularizing Neural Networks via Adversarial Mode…
|
86.64
|
2020-10-10
|
|
|
PyramidNet-200 + Shakedrop + Cutmix + PS-KD
|
Self-Knowledge Distillation with Progressive Refi…
|
86.41
|
2020-06-22
|
|
|
Mixer-B/16- SAM
|
When Vision Transformers Outperform ResNets witho…
|
86.40
|
2021-06-03
|
|
|
ResCNet-50
|
Deep Feature Response Discriminative Calibration
|
86.31
|
2024-11-16
|
|
|
PyramidNet-200 + Shakedrop + Cutmix
|
CutMix: Regularization Strategy to Train Strong C…
|
86.19
|
2019-05-13
|
|
|
MUXNet-m
|
MUXConv: Information Multiplexing in Convolutiona…
|
86.10
|
2020-03-31
|
|
|
NAT-M1
|
Neural Architecture Transfer
|
86.00
|
2020-05-12
|
|
|
WRN-28-10
|
MixMo: Mixing Multiple Inputs for Multiple Output…
|
85.77
|
2021-03-10
|
|
|
WRN-28-10, S=4
|
Towards Better Accuracy-efficiency Trade-offs: Di…
|
85.74
|
2020-11-30
|
|
|
WRN-28-8 +SAMix
|
Boosting Discriminative Visual Representation Lea…
|
85.50
|
2021-11-30
|
|
|
ASANas
|
Improving Neural Architecture Search Image Classi…
|
85.42
|
2019-03-14
|
|
|
SparseSwin
|
SparseSwin: Swin Transformer with Sparse Transfor…
|
85.35
|
2023-09-11
|
|
|
ResNet-50-SAM
|
When Vision Transformers Outperform ResNets witho…
|
85.20
|
2021-06-03
|
|
|
WRN-28-8 +AutoMix
|
AutoMix: Unveiling the Power of Mixup for Stronge…
|
85.16
|
2021-03-24
|
|
|
WaveMixLite-256/7
|
WaveMix: A Resource-efficient Neural Network for …
|
85.09
|
2022-05-28
|
|
|
MANO-tiny
|
Linear Attention with Global Context: A Multipole…
|
85.08
|
2025-07-03
|
|
|
WRN 28-14
|
Neural networks with late-phase weights
|
85.00
|
2020-07-25
|
|
|
R-Mix (WideResNet 28-10)
|
Expeditious Saliency-guided Mix-up through Random…
|
85.00
|
2022-12-09
|
|
|
EEEA-Net-C (b=5)+ CO
|
EEEA-Net: An Early Exit Evolutionary Neural Archi…
|
84.98
|
2021-08-13
|
|
|
RL-Mix (WideResNet 28-10)
|
Expeditious Saliency-guided Mix-up through Random…
|
84.90
|
2022-12-09
|
|
|
Wide-ResNet-28-10
|
Automatic Data Augmentation via Invariance-Constr…
|
84.89
|
2022-09-29
|
|
|
SENet + ShakeEven + Cutout
|
Squeeze-and-Excitation Networks
|
84.59
|
2017-09-05
|
|
|
ResNeXt-50(32x4d) + SAMix
|
Boosting Discriminative Visual Representation Lea…
|
84.42
|
2021-11-30
|
|
|
WRN-28-10 with reSGHMC
|
Non-convex Learning via Replica Exchange Stochast…
|
84.38
|
2020-08-12
|
|
|
PyramidNet-272 + SWA
|
Averaging Weights Leads to Wider Optima and Bette…
|
84.16
|
2018-03-14
|
|
|
WRN28-10
|
Puzzle Mix: Exploiting Saliency and Local Statist…
|
84.05
|
2020-09-15
|
|
|
HCGNet-A3
|
Gated Convolutional Networks with Hybrid Connecti…
|
84.04
|
2019-08-26
|
|
|
WideResNet 28-10 + CutMix (OneCycleLR scheduler)
|
Expeditious Saliency-guided Mix-up through Random…
|
83.97
|
2022-12-09
|
|
|
DenseNet-BC-190 + FMix
|
FMix: Enhancing Mixed Sample Data Augmentation
|
83.95
|
2020-02-27
|
|
|
ORN
|
Oriented Response Networks
|
83.85
|
2017-01-07
|
|
|
Grafit (ResNet-50)
|
Grafit: Learning fine-grained image representatio…
|
83.70
|
2020-11-25
|
|
|
ResNeXt-50(32x4d) + AutoMix
|
AutoMix: Unveiling the Power of Mixup for Stronge…
|
83.64
|
2021-03-24
|
|
|
CCT-7/3x1+HTM+VTM
|
TokenMixup: Efficient Attention-guided Token-leve…
|
83.57
|
2022-10-14
|
|
|
HCGNet-A2
|
Gated Convolutional Networks with Hybrid Connecti…
|
83.46
|
2019-08-26
|
|
|
Res2NeXt-29
|
Res2Net: A New Multi-scale Backbone Architecture
|
83.44
|
2019-04-02
|
|
|
DenseNet-BC-190 + Mixup
|
mixup: Beyond Empirical Risk Minimization
|
83.20
|
2017-10-25
|
|
|
SSAL-DenseNet 190-40
|
Contextual Classification Using Self-Supervised A…
|
83.20
|
2021-01-07
|
|
|
EnAET
|
EnAET: A Self-Trained framework for Semi-Supervis…
|
83.13
|
2019-11-21
|
|
|
WRN 28-10
|
Neural networks with late-phase weights
|
83.06
|
2020-07-25
|
|
|
R-Mix (ResNeXt 29-4-24)
|
Expeditious Saliency-guided Mix-up through Random…
|
83.02
|
2022-12-09
|
|
|
Wide ResNet+Cutout+no BN scale/offset learning
|
Single-bit-per-weight deep convolutional neural n…
|
82.95
|
2019-07-16
|
|
|
WRN-16-8 with reSGHMC
|
Non-convex Learning via Replica Exchange Stochast…
|
82.95
|
2020-08-12
|
|
|
DenseNet-BC
|
Densely Connected Convolutional Networks
|
82.82
|
2016-08-25
|
|
|
ABNet-2G-R3-Combined
|
ANDHRA Bandersnatch: Training Neural Networks to …
|
82.78
|
2024-11-28
|
|
|
CCT-7/3x1*
|
Escaping the Big Data Paradigm with Compact Trans…
|
82.72
|
2021-04-12
|
|
|
EXACT (WRN-28-10)
|
EXACT: How to Train Your Accuracy
|
82.68
|
2022-05-19
|
|
|
SKNet-29 (ResNeXt-29, 16×32d)
|
Selective Kernel Networks
|
82.67
|
2019-03-15
|
|
|
DenseNet
|
Densely Connected Convolutional Networks
|
82.62
|
2016-08-25
|
|
|
Shared WRN
|
Learning Implicitly Recurrent CNNs Through Parame…
|
82.57
|
2019-02-26
|
|
|
Transformer local-attention (NesT-B)
|
Nested Hierarchical Transformer: Towards Accurate…
|
82.56
|
2021-05-26
|
|
|
RL-Mix (ResNeXt 29-4-24)
|
Expeditious Saliency-guided Mix-up through Random…
|
82.43
|
2022-12-09
|
|
|
Mixer-S/16- SAM
|
When Vision Transformers Outperform ResNets witho…
|
82.40
|
2021-06-03
|
|
|
R-Mix (WideResNet 16-8)
|
Expeditious Saliency-guided Mix-up through Random…
|
82.32
|
2022-12-09
|
|
|
ResNeXt 29-4-24 + CutMix (OneCycleLR scheduler)
|
Expeditious Saliency-guided Mix-up through Random…
|
82.30
|
2022-12-09
|
|
|
WARN
|
Attend and Rectify: a Gated Attention Mechanism f…
|
82.18
|
2018-07-19
|
|
|
RL-Mix (WideResNet 16-8)
|
Expeditious Saliency-guided Mix-up through Random…
|
82.16
|
2022-12-09
|
|
|
WRN+SWA
|
Averaging Weights Leads to Wider Optima and Bette…
|
82.15
|
2018-03-14
|
|
|
Manifold Mixup
|
Manifold Mixup: Better Representations by Interpo…
|
81.96
|
2018-06-13
|
|
|
HCGNet-A1
|
Gated Convolutional Networks with Hybrid Connecti…
|
81.87
|
2019-08-26
|
|
|
WideResNet 16-8 + CutMix (OneCycleLR scheduler)
|
Expeditious Saliency-guided Mix-up through Random…
|
81.79
|
2022-12-09
|
|
|
Residual Gates + WRN
|
Learning Identity Mappings with Residual Gates
|
81.73
|
2016-11-04
|
|
|
kNN-CLIP
|
Revisiting a kNN-based Image Classification Syste…
|
81.70
|
2022-04-03
|
|
|
AA-Wide-ResNet
|
Attention Augmented Convolutional Networks
|
81.60
|
2019-04-22
|
|
|
PDO-eConv (p8, 4.6M)
|
PDO-eConvs: Partial Differential Operator Based E…
|
81.60
|
2020-07-20
|
|
|
SEER (RegNet10B)
|
Vision Models Are More Robust And Fair When Pretr…
|
81.53
|
2022-02-16
|
|
|
R-Mix (PreActResNet-18)
|
Expeditious Saliency-guided Mix-up through Random…
|
81.49
|
2022-12-09
|
|
|
ResNet50 (FSGDM)
|
On the Performance Analysis of Momentum Method: A…
|
81.44
|
2024-11-29
|
|
|
Wide-ResNet-40-2
|
Automatic Data Augmentation via Invariance-Constr…
|
81.19
|
2022-09-29
|
|
|
Wide ResNet
|
Wide Residual Networks
|
81.15
|
2016-05-23
|
|
|
CoPaNet-R-164
|
Deep Competitive Pathway Networks
|
81.10
|
2017-09-29
|
|
|
ABNet-2G-R3
|
ANDHRA Bandersnatch: Training Neural Networks to …
|
80.83
|
2024-11-28
|
|
|
RL-Mix (PreActResNet-18)
|
Expeditious Saliency-guided Mix-up through Random…
|
80.75
|
2022-12-09
|
|
|
PreActResNet-18 + CutMix (OneCycleLR scheduler)
|
Expeditious Saliency-guided Mix-up through Random…
|
80.60
|
2022-12-09
|
|
|
GAC-SNN
|
Gated Attention Coding for Training High-performa…
|
80.45
|
2023-08-12
|
|
|
ABNet-2G-R2
|
ANDHRA Bandersnatch: Training Neural Networks to …
|
80.35
|
2024-11-28
|
|
|
SimpleNetv2
|
Towards Principled Design of Deep Convolutional N…
|
80.29
|
2018-02-17
|
|
|
UPANets
|
UPANets: Learning from the Universal Pixel Attent…
|
80.29
|
2021-03-15
|
|
|
PreActResNet-18 + SageMix
|
SageMix: Saliency-Guided Mixup for Point Clouds
|
80.16
|
2022-10-13
|
|
|
ResNet56 with reSGHMC
|
Non-convex Learning via Replica Exchange Stochast…
|
80.14
|
2020-08-12
|
|
|
PDO-eConv (p8, 2.62M)
|
PDO-eConvs: Partial Differential Operator Based E…
|
79.99
|
2020-07-20
|
|
|
VGG11B(3x) + LocalLearning
|
Training Neural Networks with Local Error Signals
|
79.90
|
2019-01-20
|
|
|
NNCLR
|
With a Little Help from My Friends: Nearest-Neigh…
|
79.00
|
2021-04-29
|
|
|
ABNet-2G-R1
|
ANDHRA Bandersnatch: Training Neural Networks to …
|
78.79
|
2024-11-28
|
|
|
PreActResNet18 (AMP)
|
Regularizing Neural Networks via Adversarial Mode…
|
78.49
|
2020-10-10
|
|
|
SimpleNetv1
|
Lets keep it simple, Using simple architectures t…
|
78.37
|
2016-08-22
|
|
|
ViT (lightweight, MAE pre-trained)
|
Pre-training of Lightweight Vision Transformers o…
|
78.27
|
2024-02-06
|
|
|
PDC
|
Augmenting Deep Classifiers with Polynomial Neura…
|
77.90
|
2021-04-16
|
|
|
MobileNetV3-large x1.0 (BSConv-U)
|
Rethinking Depthwise Separable Convolutions: How …
|
77.70
|
2020-03-30
|
|
|
CCT-6/3x1
|
Escaping the Big Data Paradigm with Compact Trans…
|
77.31
|
2021-04-12
|
|
|
ResNet-1001
|
Identity Mappings in Deep Residual Networks
|
77.30
|
2016-03-16
|
|
|
Evolution
|
Large-Scale Evolution of Image Classifiers
|
77.00
|
2017-03-03
|
|
|
DIANet
|
DIANet: Dense-and-Implicit Attention Network
|
76.98
|
2019-05-25
|
|
|
LP-BNN (ours) + cutout
|
Encoding the latent posterior of Bayesian Neural …
|
76.85
|
2020-12-04
|
|
|
ResNet-18+MM+FRL
|
Learning Class Unique Features in Fine-Grained Vi…
|
76.64
|
2020-11-22
|
|
|
ResNet32 with reSGHMC
|
Non-convex Learning via Replica Exchange Stochast…
|
76.55
|
2020-08-12
|
|
|
MomentumNet
|
Momentum Residual Neural Networks
|
76.38
|
2021-02-15
|
|
|
SSCNN
|
Spatially-sparse convolutional neural networks
|
75.70
|
2014-09-22
|
|
|
Exponential Linear Units
|
Fast and Accurate Deep Network Learning by Expone…
|
75.70
|
2015-11-23
|
|
|
ResNet-9
|
CNN Filter DB: An Empirical Investigation of Trai…
|
75.59
|
2022-03-29
|
|
|
Stochastic Depth
|
Deep Networks with Stochastic Depth
|
75.42
|
2016-03-30
|
|
|
ResNet v2-110 (Mish activation)
|
Mish: A Self Regularized Non-Monotonic Activation…
|
74.41
|
2019-08-23
|
|
|
ResNet20 with reSGHMC
|
Non-convex Learning via Replica Exchange Stochast…
|
74.14
|
2020-08-12
|
|
|
MixMatch
|
MixMatch: A Holistic Approach to Semi-Supervised …
|
74.10
|
2019-05-06
|
|
|
Beta-Rank
|
Beta-Rank: A Robust Convolutional Filter Pruning …
|
74.01
|
2023-04-15
|
|
|
PreResNet-110
|
How to Use Dropout Correctly on Residual Networks…
|
73.98
|
2023-02-13
|
|
|
ABNet-2G-R0
|
ANDHRA Bandersnatch: Training Neural Networks to …
|
73.93
|
2024-11-28
|
|
|
Fractional MP
|
Fractional Max-Pooling
|
73.60
|
2014-12-18
|
|
|
ResNet+ELU
|
Deep Residual Networks with Exponential Linear Un…
|
73.50
|
2016-04-14
|
|
|
PDO-eConv (p6m,0.37M)
|
PDO-eConvs: Partial Differential Operator Based E…
|
73.00
|
2020-07-20
|
|
|
SOPCNN
|
Stochastic Optimization of Plain Convolutional Ne…
|
72.96
|
2020-01-24
|
|
|
PDO-eConv (p6,0.36M)
|
PDO-eConvs: Partial Differential Operator Based E…
|
72.87
|
2020-07-20
|
|
|
Tuned CNN
|
Scalable Bayesian Optimization Using Deep Neural …
|
72.60
|
2015-02-19
|
|
|
ResNet-110 (SAP)
|
Stochastic Subsampling With Average Pooling
|
72.54
|
2024-09-25
|
|
|
CMsC
|
Competitive Multi-scale Convolution
|
72.40
|
2015-11-18
|
|
|
Fitnet4-LSUV
|
All you need is a good init
|
72.30
|
2015-11-19
|
|
|
BNM NiN
|
Batch-normalized Maxout Network in Network
|
71.10
|
2015-11-09
|
|
|
OTTT
|
Online Training Through Time for Spiking Neural N…
|
71.05
|
2022-10-09
|
|
|
MIM
|
On the Importance of Normalisation Layers in Deep…
|
70.80
|
2015-08-03
|
|
|
WaveMix-Lite-256/7
|
WaveMix: A Resource-efficient Neural Network for …
|
70.20
|
2022-05-28
|
|
|
NiN+APL
|
Learning Activation Functions to Improve Deep Neu…
|
69.20
|
2014-12-21
|
|
|
SWWAE
|
Stacked What-Where Auto-encoders
|
69.10
|
2015-06-08
|
|
|
NiN+Superclass+CDJ
|
Deep Convolutional Decision Jungle for Image Clas…
|
69.00
|
2017-06-06
|
|
|
Spectral Representations for Convolutional Neural Networks
|
Spectral Representations for Convolutional Neural…
|
68.40
|
2015-06-11
|
|
|
ReActNet-18
|
"BNN - BN = ?": Training Binary Neural Networks w…
|
68.34
|
2021-04-16
|
|
|
VDN
|
Training Very Deep Networks
|
67.80
|
2015-07-22
|
|
|
DCNN+GFE
|
Deep Convolutional Neural Networks as Generic Fea…
|
67.70
|
2017-10-06
|
|
|
Tree+Max-Avg pooling
|
Generalizing Pooling Functions in Convolutional N…
|
67.60
|
2015-09-30
|
|
|
HD-CNN
|
HD-CNN: Hierarchical Deep Convolutional Neural Ne…
|
67.40
|
2014-10-03
|
|
|
Universum Prescription
|
Universum Prescription: Regularization using Unla…
|
67.20
|
2015-11-11
|
|
|
ACN
|
Striving for Simplicity: The All Convolutional Net
|
66.30
|
2014-12-21
|
|
|
DLME (ResNet-18, linear)
|
DLME: Deep Local-flatness Manifold Embedding
|
66.10
|
2022-07-07
|
|
|
ResNet-18 (modified)
|
FatNet: High Resolution Kernels for Classificatio…
|
66.00
|
2022-10-30
|
|
|
DSN
|
Deeply-Supervised Nets
|
65.40
|
2014-09-18
|
|
|
NiN
|
Network In Network
|
64.30
|
2013-12-16
|
|
|
DNN+Probabilistic Maxout
|
Improving Deep Neural Networks with Probabilistic…
|
61.90
|
2013-12-20
|
|
|
Maxout Network (k=2)
|
Maxout Networks
|
61.43
|
2013-02-18
|
|
|
Convolutional Linear Transformer for Vision (CLTV)
|
Convolutional Xformers for Vision
|
60.11
|
2022-01-25
|
|
|
FatNet of ResNet-18
|
FatNet: High Resolution Kernels for Classificatio…
|
60.00
|
2022-10-30
|
|
|
Optical Simulation of FatNet
|
FatNet: High Resolution Kernels for Classificatio…
|
60.00
|
2022-10-30
|
|
|
RReLU
|
Empirical Evaluation of Rectified Activations in …
|
59.80
|
2015-05-05
|
|
|
Stochastic Pooling
|
Stochastic Pooling for Regularization of Deep Con…
|
57.50
|
2013-01-16
|
|
|
Sign-symmetry
|
How Important is Weight Symmetry in Backpropagati…
|
48.75
|
2015-10-17
|
|
|
CNN39
|
Sharpness-Aware Minimization for Efficiently Impr…
|
42.64
|
2020-10-03
|
|
|
CNN36
|
Sharpness-Aware Minimization for Efficiently Impr…
|
36.07
|
2020-10-03
|
|
|
CNN37
|
Sharpness-aware Quantization for Deep Neural Netw…
|
35.05
|
2021-11-24
|
|