paper-with-me

Image Classification 벤치마크

Image Classification on CIFAR-10

279개 결과 · ⬇ CSV · JSON

Percentage correct

48.45 61.21 73.97 86.74 99.5 2012-02 2026-09 MCDNN — 88.8 (2012-02-13) GP EI — 90.5 (2012-06-13) Improving neural networks by preventing co-adaptation of feature detectors — 84.4 (2012-07-03) DCNN — 89.0 (2012-12-01) Learning with Recursive Perceptual Representations — 79.7 (2012-12-01) Stochastic Pooling — 84.9 (2013-01-16) Maxout Network (k=2) — 90.65 (2013-02-18) Network in Network — 91.2 (2013-12-16) DNN+Probabilistic Maxout — 90.6 (2013-12-20) PCANet — 78.7 (2014-04-14) CKN — 82.2 (2014-06-12) Deep Networks with Internal Selective Attention through Feedback Connections — 90.8 (2014-07-11) DSN — 91.8 (2014-09-18) SSCNN — 93.7 (2014-09-22) Discriminative Unsupervised Feature Learning with Convolutional Neural Networks — 82.0 (2014-12-01) Fractional MP — 96.5 (2014-12-18) An Analysis of Unsupervised Pre-training in Light of Recent Advances — 86.7 (2014-12-20) ACN — 95.6 (2014-12-21) NiN+APL — 92.5 (2014-12-21) Tuned CNN — 93.6 (2015-02-19) FLSCNN — 75.9 (2015-03-16) ReNet — 87.7 (2015-05-03) RReLU — 88.8 (2015-05-05) APAC — 89.7 (2015-05-13) SWWAE — 92.2 (2015-06-08) Spectral Representations for Convolutional Neural Networks — 91.4 (2015-06-11) VDN — 92.4 (2015-07-22) MIM — 91.5 (2015-08-03) Tree+Max-Avg pooling — 94.0 (2015-09-30) Sign-symmetry — 80.98 (2015-10-17) BinaryConnect — 91.7 (2015-11-02) BNM NiN — 93.3 (2015-11-09) Universum Prescription — 93.3 (2015-11-11) CMsC — 93.1 (2015-11-18) Fitnet4-LSUV — 94.2 (2015-11-19) DCGAN — 82.8 (2015-11-19) 1 Layer K-means — 80.6 (2015-11-19) Exponential Linear Units — 93.5 (2015-11-23) ResNet-1001 — 95.4 (2016-03-16) Stochastic Depth — 94.77 (2016-03-30) ResNet+ELU — 94.4 (2016-04-14) SimpleNetv1 — 95.51 (2016-08-22) DenseNet (DenseNet-BC-190) — 96.54 (2016-08-25) Deep pyramidal residual network — 96.69 (2016-10-10) Residual Gates + WRN — 96.35 (2016-11-04) NAS-RL — 96.4 (2016-11-05) ORN — 97.02 (2017-01-07) CLS-GAN — 91.7 (2017-01-23) Evolution ensemble — 95.6 (2017-03-03) Evolution — 94.6 (2017-03-03) Deep Complex — 94.4 (2017-05-27) RL+NT — 94.6 (2017-07-16) SENet + ShakeShake + Cutout — 97.88 (2017-09-05) CoPaNet-R-164 — 96.62 (2017-09-29) DCNN+GFE — 89.1 (2017-10-06) DenseNet-BC-190 + Mixup — 97.3 (2017-10-25) ensemble of 7 models — 89.4 (2017-10-26) Mobile Net_Sam — 95.5 (2018-01-13) SimpleNetv2 — 96.29 (2018-02-17) ShakeShake-2x64d + SWA — 97.12 (2018-03-14) WRN-28-10 + SWA — 96.79 (2018-03-14) UL-Hopfield (ULH) — 83.1 (2018-05-02) RMDL (30 RDLs) — 91.21 (2018-05-03) Manifold Mixup WRN 28-10 — 97.45 (2018-06-13) GPIPE + transfer learning — 99.0 (2018-11-16) Proxyless-G + c/o — 97.92 (2018-12-02) LaNet — 99.03 (2019-01-01) VGG11B(2x) + LocalLearning + CO — 96.4 (2019-01-20) WRN + fixup init + mixup + cutout — 97.7 (2019-01-27) Shared WRN — 97.47 (2019-02-26) SKNet-29 (ResNeXt-29, 16×32d) — 96.53 (2019-03-15) SRM-ResNet-56 — 95.05 (2019-03-26) ANODE — 60.6 (2019-04-02) PyramidNet+ShakeDrop (Fast AA) — 98.3 (2019-05-01) MixMatch — 95.05 (2019-05-06) F-DENSER++ — 88.73 (2019-05-08) PyramidNet-200 + CutMix — 97.12 (2019-05-13) EfficientNet-B7 — 98.9 (2019-05-28) WRN-22-8 (Sparse Momentum) — 95.04 (2019-07-10) Wide ResNet+cutout — 96.71 (2019-07-16) ResNet 9 + Mish — 94.05 (2019-08-23) ResNet v2-20 (Mish activation) — 92.02 (2019-08-23) HCGNet-A3 — 97.86 (2019-08-26) HCGNet-A2 — 97.71 (2019-08-26) HCGNet-A1 — 96.85 (2019-08-26) SA quadratic embedding — 93.8 (2019-11-08) ResNet-18 — 90.65 (2019-11-13) EnAET — 98.01 (2019-11-21) BiT-L (ResNet) — 99.37 (2019-12-24) BiT-M (ResNet) — 98.91 (2019-12-24) DenseNet-BC-190 + batchboost — 97.54 (2020-01-21) Stochastic Optimization of Plain Convolutional Neural Networks with Simple methods — 94.29 (2020-01-24) PyramidNet + ShakeDrop + Fast AA + FMix — 98.64 (2020-02-27) TResNet-XL — 99.0 (2020-03-30) MUXNet-m — 98.0 (2020-03-31) NoisyDARTS-A-t — 98.28 (2020-05-07) NoisyDARTS-a — 97.61 (2020-05-07) NAT-M4 — 98.4 (2020-05-12) NAT-M3 — 98.2 (2020-05-12) NAT-M2 — 97.9 (2020-05-12) NAT-M1 — 97.4 (2020-05-12) Prodpoly — 94.9 (2020-06-20) PDO-eConv (p8, 4.6M) — 96.5 (2020-07-20) PDO-eConv (p8, 2.62M) — 96.32 (2020-07-20) PDO-eConv (p6m,0.37M) — 94.62 (2020-07-20) PDO-eConv (p6,0.36M) — 94.35 (2020-07-20) WRN 28-14 — 97.45 (2020-07-25) WRN 28-10 — 96.81 (2020-07-25) E2E-3M — 98.52 (2020-07-30) WRN-28-10 with reSGHMC — 97.42 (2020-08-12) WRN-16-8 with reSGHMC — 96.87 (2020-08-12) ResNet56 with reSGHMC — 96.12 (2020-08-12) ResNet32 with reSGHMC — 95.35 (2020-08-12) ResNet20 with reSGHMC — 94.62 (2020-08-12) PyramidNet + AA (AMP) — 98.02 (2020-10-10) PreActResNet18 (AMP) — 96.03 (2020-10-10) ViT-H/14 — 99.5 (2020-10-22) ViT-L/16 — 99.42 (2020-10-22) ResNet-18+MM+FRL — 95.33 (2020-11-22) Context-Aware DNN tree — 92.01 (2020-11-29) PyramidNet-272, S=4 — 98.71 (2020-11-30) WRN-40-10, S=4 — 98.38 (2020-11-30) WRN-28-10, S=4 — 98.32 (2020-11-30) Shake-Shake 26 2x96d, S=4 — 98.31 (2020-11-30) LP-BNN (ours) + cutout — 95.02 (2020-12-04) DeiT-B — 99.1 (2020-12-23) WRN-28-10+AutoDropout+RandAugment — 97.9 (2021-01-05) AutoDropout — 96.8 (2021-01-05) MomentumNet — 95.18 (2021-02-15) VGG-19 with GradInit — 94.71 (2021-02-16) PyramidNet-272 (ASAM) — 98.68 (2021-02-23) TNT-B — 99.1 (2021-02-27) WRN-28-10 — 97.73 (2021-03-10) UPANets — 96.47 (2021-03-15) CeiT-S (384 finetune resolution) — 99.1 (2021-03-22) CeiT-S — 99.0 (2021-03-22) CeiT-T — 98.5 (2021-03-22) ResNeXt-50 (AutoMix) — 97.84 (2021-03-24) CvT-W24 — 99.39 (2021-03-29) CaiT-M-36 U 224 — 99.4 (2021-03-31) EfficientNetV2-L — 99.1 (2021-04-01) EfficientNetV2-M — 99.0 (2021-04-01) EfficientNetV2-S — 98.7 (2021-04-01) LeViT-192 — 98.2 (2021-04-02) LeViT-256 — 98.1 (2021-04-02) LeViT-384 — 98.0 (2021-04-02) LeViT-128 — 97.6 (2021-04-02) LeViT-128S — 97.5 (2021-04-02) CCT-7/3x1* — 98.0 (2021-04-12) CCT-6/3x1 — 95.29 (2021-04-12) ReActNet-18 — 92.08 (2021-04-16) NNCLR — 93.7 (2021-04-29) ResNet — 92.3 (2021-05-10) Transformer local-attention (NesT-B) — 97.2 (2021-05-26) CTM Drop Clause — 75.1 (2021-05-30) DVT (T2T-ViT-24) — 98.53 (2021-05-31) ResNet-152x4-AGC (ImageNet-21K) — 97.82 (2021-05-31) ResNet-50x1-ACG (ImageNet-21K) — 95.78 (2021-05-31) ViT-B/16- SAM — 98.6 (2021-06-03) ResNet-152-SAM — 98.2 (2021-06-03) ViT-S/16- SAM — 98.2 (2021-06-03) Mixer-B/16- SAM — 97.8 (2021-06-03) ResNet-50-SAM — 97.4 (2021-06-03) Mixer-S/16- SAM — 96.1 (2021-06-03) AutoFormer-S | 384 — 99.1 (2021-07-01) GFNet-H-B — 99.0 (2021-07-01) CCN — 83.36 (2021-07-05) CvN — 83.26 (2021-07-05) LeViP — 79.5 (2021-07-05) Hybrid ViT+RoPE — 76.9 (2021-07-05) Hybrid Vision Nystromformer (ViN) — 75.26 (2021-07-05) Hybrid PiN — 74.0 (2021-07-05) Vision Nystromformer (ViN) — 65.06 (2021-07-05) ThresholdNet — 86.34 (2021-08-28) ConvMLP-M — 98.6 (2021-09-09) ConvMLP-L — 98.6 (2021-09-09) ConvMLP-S — 98.0 (2021-09-09) WaveMix — 85.21 (2021-09-29) ViT-B/16 (PUGD) — 99.13 (2021-10-01) ResNet50 (A1) — 98.3 (2021-10-01) cvpr_class — 85.28 (2021-10-01) FlexTCN-7 — 92.2 (2021-10-15) ResNet_XnIDR — 96.87 (2021-11-21) Context-Aware Pipeline — 95.16 (2021-12-30) ThreshNet95 — 86.69 (2022-01-09) Local Mixup Resnet18 — 95.97 (2022-01-12) ConvMixer-256/16 — 96.74 (2022-01-24) ConvMixer-256/8 — 96.03 (2022-01-24) Convolutional Performer for Vision (CPV) — 94.46 (2022-01-25) SEER (RegNet10B) — 90.0 (2022-02-16) APVT — 80.45 (2022-03-02) Bamboo (ViT-B/16) — 98.2 (2022-03-15) ViT-B (attn fine-tune) — 99.3 (2022-03-18) ResNet-9 — 94.79 (2022-03-29) TripleNet-B — 87.03 (2022-04-02) kNN-CLIP — 97.3 (2022-04-03) ASF-former-B — 98.8 (2022-04-26) ASF-former-S — 98.7 (2022-04-26) SmoothNetV1 — 73.5 (2022-05-09) EXACT (WRN-28-10) — 96.73 (2022-05-19) Dynamics 2 — 98.31 (2022-05-20) µ2Net (ViT-L/16) — 99.49 (2022-05-25) TransBoost-ResNet50 — 97.61 (2022-05-26) WaveMixLite-144/7 — 97.29 (2022-05-28) ResNet-18 — 95.55 (2022-06-27) kEffNet-B0 32ch — 93.75 (2022-06-30) kMobileNet V3 Large 16ch — 92.74 (2022-06-30) kDenseNet-BC L100 12ch — 90.83 (2022-06-30) kMobileNet 16ch — 89.81 (2022-06-30) DLME (ResNet-18, linear) — 91.3 (2022-07-07) ShortNet1-53 — 86.64 (2022-08-02) kEffNet-B0 V2 32ch + H Flip — 94.95 (2022-09-08) Wide-ResNet-28-10 — 97.85 (2022-09-29) Wide-ResNet-40-2 — 97.05 (2022-09-29) OTTT — 93.73 (2022-10-09) CCT-7/3x1+VTM — 97.78 (2022-10-14) IM-Loss (ResNet-19) — 95.49 (2022-10-31) pFedBreD_ns_mg — 80.63 (2022-11-19) Heinsen Routing + BEiT-large 16 224 — 99.2 (2022-11-20) ResNet-26 (Trainable Activations) — 91.1 (2023-01-26) ResNet-32 (Trainable Activations) — 90.9 (2023-01-26) ResNet-44 (Trainable Activations) — 90.5 (2023-01-26) ResNet-20 (Trainable Activations) — 90.4 (2023-01-26) ResNet-14 (Trainable Activations) — 89.0 (2023-01-26) ResNet-56 (Trainable Activations) — 88.8 (2023-01-26) ResNet-8 (Trainable Activations) — 86.5 (2023-01-26) PreResNet-110 — 94.4367 (2023-02-13) SNN — 68.3 (2023-02-13) Diffusion Classifier (zero-shot) — 88.5 (2023-03-28) Astroformer — 99.12 (2023-04-03) DINOv2 (ViT-g/14, frozen model, linear eval) — 99.5 (2023-04-14) Beta-Rank — 93.97 (2023-04-15) VIT-L/16 (Spinal FC, Background) — 99.05 (2023-05-05) GAC-SNN — 96.46 (2023-08-12) SparseSwin — 97.43 (2023-09-11) OnDev-LCT-8/3 — 87.65 (2024-01-22) OnDev-LCT-4/3 — 87.03 (2024-01-22) OnDev-LCT-8/1 — 86.64 (2024-01-22) OnDev-LCT-4/1 — 86.61 (2024-01-22) OnDev-LCT-2/1 — 86.27 (2024-01-22) OnDev-LCT-2/3 — 86.04 (2024-01-22) OnDev-LCT-1/3 — 85.73 (2024-01-22) OnDev-LCT-1/1 — 84.55 (2024-01-22) ViT (lightweight, MAE pretrained) — 96.41 (2024-02-06) DGPPF-ResNet18 — 92.9 (2024-02-15) RDNet-L (224 res, IN-1K pretrained) — 99.31 (2024-03-28) RDNet-B (224 res, IN-1K pretrained) — 99.31 (2024-03-28) RDNet-T (224 res, IN-1K pretrained) — 98.88 (2024-03-28) TM Composites Toolbox — 82.8 (2024-06-02) CNN+ Wilson-Cowan model RNN — 86.59 (2024-06-24) ResNet-110 (SAP) — 93.861 (2024-09-25) R-ExplaiNet-26 — 94.15 (2024-10-31) ABNet-2G-R3-Combined — 96.378 (2024-11-28) ABNet-2G-R3 — 96.088 (2024-11-28) ABNet-2G-R2 — 95.9 (2024-11-28) ABNet-2G-R1 — 95.536 (2024-11-28) ABNet-2G-R0 — 94.118 (2024-11-28) ResNet18 (FSGDM) — 95.66 (2024-11-29) DE ELBo (ViT-B/16) — 98.2 (2025-02-03) The Analog Activation Function — 82.06 (2025-02-13) Compositional — 96.24 (2025-07-28) Noisy Label Refinement with Semantically — 70.0 (2025-09-04) GhostNetV3-Small — 93.94 (2025-09-15) Knowledge Distillation Detection for Ope — 59.6 (2025-10-02) Exploring the Hierarchical Reasoning Mod — 91.5 (2025-10-04) Arc Gradient Descent — 50.7 (2025-12-07) Stylized Synthetic Augmentation further — 50.86 (2025-12-17) Enhancing Small Dataset Classification U — 90.0 (2026-01-06) Adversarial Vulnerability Transcends Com — 59.1 (2026-01-29) RAViT — 70.0 (2026-02-27) Empirical Ablation and Ensemble Optimiza — 89.23 (2026-04-26) Gated — 91.11 (2026-05-05) GC-ART — 48.45 (2026-05-08) Scaling Up Thermodynamic AI Models — 94.9 (2026-06-30) MCDNN — 88.8 (2012-02-13) GP EI — 90.5 (2012-06-13) Maxout Network (k=2) — 90.65 (2013-02-18) Network in Network — 91.2 (2013-12-16) DSN — 91.8 (2014-09-18) SSCNN — 93.7 (2014-09-22) Fractional MP — 96.5 (2014-12-18) DenseNet (DenseNet-BC-190) — 96.54 (2016-08-25) Deep pyramidal residual network — 96.69 (2016-10-10) ORN — 97.02 (2017-01-07) SENet + ShakeShake + Cutout — 97.88 (2017-09-05) GPIPE + transfer learning — 99.0 (2018-11-16) LaNet — 99.03 (2019-01-01) BiT-L (ResNet) — 99.37 (2019-12-24) ViT-H/14 — 99.5 (2020-10-22)
RankModel Percentage correctTop-1 AccuracyAccuracyParametersTop 1 AccuracyF1Cross Entropy Loss Extra Training Data PaperCodeYear
1 ViT-H/14 99.5 An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale huggingface/transformers · labmlai/annotated_deep_learning_paper_implementations · rwightman/pytorch-image-models · +155 2020
1 DINOv2 (ViT-g/14, frozen model, linear eval) 99.5 DINOv2: Learning Robust Visual Features without Supervision huggingface/transformers · facebookresearch/dinov2 · roboflow/rf-detr · +23 2023
3 µ2Net (ViT-L/16) 99.49 An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems google-research/google-research 2022
4 ViT-L/16 99.42 An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale huggingface/transformers · labmlai/annotated_deep_learning_paper_implementations · rwightman/pytorch-image-models · +155 2020
5 CaiT-M-36 U 224 99.4 Going deeper with Image Transformers rwightman/pytorch-image-models · lucidrains/vit-pytorch · facebookresearch/deit · +18 2021
6 CvT-W24 99.39 CvT: Introducing Convolutions to Vision Transformers huggingface/transformers · BR-IDL/PaddleViT · microsoft/CvT · +13 2021
7 BiT-L (ResNet) 99.37 Big Transfer (BiT): General Visual Representation Learning google-research/big_transfer · sayakpaul/FunMatch-Distillation · bethgelab/InDomainGeneralizationBenchmark · +6 2019
8 RDNet-L (224 res, IN-1K pretrained) 99.31 DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs huggingface/pytorch-image-models · naver-ai/rdnet · birder/birder 2024
8 RDNet-B (224 res, IN-1K pretrained) 99.31 DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs huggingface/pytorch-image-models · naver-ai/rdnet · birder/birder 2024
10 ViT-B (attn fine-tune) 99.3 Three things everyone should know about Vision Transformers rwightman/pytorch-image-models · lucidrains/vit-pytorch · facebookresearch/deit · +5 2022
11 Heinsen Routing + BEiT-large 16 224 99.2 An Algorithm for Routing Vectors in Sequences glassroom/heinsen_routing 2022
12 ViT-B/16 (PUGD) 99.13 Perturbated Gradients Updating within Unit Space for Deep Learning hanktseng131415go/pugd 2021
13 Astroformer 99.1299.12 Astroformer: More Data Might not be all you need for Classification Rishit-dagli/Astroformer 2023
14 DeiT-B 99.1 Training data-efficient image transformers & distillation through attention huggingface/transformers · rwightman/pytorch-image-models · PaddlePaddle/PaddleClas · +37 2020
14 TNT-B 99.1 Transformer in Transformer rwightman/pytorch-image-models · PaddlePaddle/PaddleClas · huawei-noah/CV-backbones · +9 2021
14 CeiT-S (384 finetune resolution) 99.1 Incorporating Convolution Designs into Visual Transformers rishikksh20/CeiT-pytorch · coeusguo/ceit · mindspore-courses/External-Attention-MindSpore 2021
14 EfficientNetV2-L 99.1 EfficientNetV2: Smaller Models and Faster Training rwightman/pytorch-image-models · pytorch/vision · lukemelas/EfficientNet-PyTorch · +23 2021
14 AutoFormer-S | 384 99.1 AutoFormer: Searching Transformers for Visual Recognition microsoft/AutoML · microsoft/cream 2021
19 VIT-L/16 (Spinal FC, Background) 99.05 Reduction of Class Activation Uncertainty with Background Information dipuk0506/SpinalNet · dipuk0506/uq 2023
20 LaNet 99.03 Sample-Efficient Neural Architecture Search by Learning Action Space for Monte Carlo Tree Search facebookresearch/LaMCTS 2019
21 GPIPE + transfer learning 99 GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism tensorflow/lingvo · qubvel/efficientnet · KakaoBrain/torchgpipe · +10 2018
21 TResNet-XL 99 TResNet: High Performance GPU-Dedicated Architecture rwightman/pytorch-image-models · mrT23/TResNet · Alibaba-MIIL/TResNet 2020
21 CeiT-S 99 Incorporating Convolution Designs into Visual Transformers rishikksh20/CeiT-pytorch · coeusguo/ceit · mindspore-courses/External-Attention-MindSpore 2021
21 EfficientNetV2-M 99.0 EfficientNetV2: Smaller Models and Faster Training rwightman/pytorch-image-models · pytorch/vision · lukemelas/EfficientNet-PyTorch · +23 2021
21 GFNet-H-B 99.0 Global Filter Networks for Image Classification raoyongming/GFNet · liuruiyang98/Jittor-MLP · mindspore-courses/External-Attention-MindSpore · +1 2021
26 BiT-M (ResNet) 98.91 Big Transfer (BiT): General Visual Representation Learning google-research/big_transfer · sayakpaul/FunMatch-Distillation · bethgelab/InDomainGeneralizationBenchmark · +6 2019
27 EfficientNet-B7 98.9 EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks ultralytics/yolov5 · rwightman/pytorch-image-models · open-mmlab/mmdetection · +141 2019
28 RDNet-T (224 res, IN-1K pretrained) 98.88 DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs huggingface/pytorch-image-models · naver-ai/rdnet · birder/birder 2024
29 ASF-former-B 98.8% Adaptive Split-Fusion Transformer szx503045266/asf-former 2022
30 PyramidNet-272, S=4 98.71 Towards Better Accuracy-efficiency Trade-offs: Divide and Co-training freeformrobotics/divide-and-co-training · mzhaoshuai/Divide-and-Co-training 2020
31 EfficientNetV2-S 98.7 EfficientNetV2: Smaller Models and Faster Training rwightman/pytorch-image-models · pytorch/vision · lukemelas/EfficientNet-PyTorch · +23 2021
31 ASF-former-S 98.7 Adaptive Split-Fusion Transformer szx503045266/asf-former 2022
33 PyramidNet-272 (ASAM) 98.68 ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks davda54/sam · borealisai/perturbed-forgetting 2021
34 PyramidNet + ShakeDrop + Fast AA + FMix 98.64 FMix: Enhancing Mixed Sample Data Augmentation PaddlePaddle/PaddleClas · Westlake-AI/openmixup · ecs-vlc/FMix · +2 2020
35 ViT-B/16- SAM 98.6 When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations google-research/vision_transformer · ttt496/VisionTransformer 2021
35 ConvMLP-M 98.6 ConvMLP: Hierarchical Convolutional MLPs for Vision BR-IDL/PaddleViT · shinya7y/UniverseNet · liuruiyang98/Jittor-MLP · +1 2021
35 ConvMLP-L 98.6 ConvMLP: Hierarchical Convolutional MLPs for Vision BR-IDL/PaddleViT · shinya7y/UniverseNet · liuruiyang98/Jittor-MLP · +1 2021
38 DVT (T2T-ViT-24) 98.53 Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognition blackfeather-wang/Dynamic-Vision-Transformer · blackfeather-wang/dynamic-vision-transformer-mindspore 2021
39 E2E-3M 98.52 Rethinking Recurrent Neural Networks and Other Improvements for Image Classification leonlha/e2e-3m 2020
40 CeiT-T 98.5 Incorporating Convolution Designs into Visual Transformers rishikksh20/CeiT-pytorch · coeusguo/ceit · mindspore-courses/External-Attention-MindSpore 2021
41 NAT-M4 98.498.46.9M Neural Architecture Transfer human-analysis/neural-architecture-transfer · awesomelemon/encas 2020
42 WRN-40-10, S=4 98.38 Towards Better Accuracy-efficiency Trade-offs: Divide and Co-training freeformrobotics/divide-and-co-training · mzhaoshuai/Divide-and-Co-training 2020
43 WRN-28-10, S=4 98.32 Towards Better Accuracy-efficiency Trade-offs: Divide and Co-training freeformrobotics/divide-and-co-training · mzhaoshuai/Divide-and-Co-training 2020
44 Shake-Shake 26 2x96d, S=4 98.31 Towards Better Accuracy-efficiency Trade-offs: Divide and Co-training freeformrobotics/divide-and-co-training · mzhaoshuai/Divide-and-Co-training 2020
44 Dynamics 2 98.31 PSO-Convolutional Neural Networks with Heterogeneous Learning Rate leonlha/pso-convnet-dynamics 2022
46 PyramidNet+ShakeDrop (Fast AA) 98.3 Fast AutoAugment kakaobrain/fast-autoaugment · ildoonet/pytorch-randaugment · philip-bachman/amdim-public · +8 2019
46 ResNet50 (A1) 98.3 ResNet strikes back: An improved training procedure in timm rwightman/pytorch-image-models · open-mmlab/mmdetection · open-mmlab/mmclassification · +11 2021
48 NoisyDARTS-A-t 98.28 Noisy Differentiable Architecture Search xiaomi-automl/NoisyDARTS 2020
49 NAT-M3 98.298.26.2M Neural Architecture Transfer human-analysis/neural-architecture-transfer · awesomelemon/encas 2020
49 LeViT-192 98.2 LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference huggingface/transformers · rwightman/pytorch-image-models · leondgarse/keras_cv_attention_models · +9 2021
49 ResNet-152-SAM 98.2 When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations google-research/vision_transformer · ttt496/VisionTransformer 2021
49 ViT-S/16- SAM 98.2 When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations google-research/vision_transformer · ttt496/VisionTransformer 2021
49 Bamboo (ViT-B/16) 98.2 Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy zhangyuanhan-ai/bamboo · davidzhangyuanhan/bamboo 2022
49 DE ELBo (ViT-B/16) 98.2 Learning Hyperparameters via a Data-Emphasized Variational Objective tufts-ml/data-emphasized-ELBo 2025
55 LeViT-256 98.1 LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference huggingface/transformers · rwightman/pytorch-image-models · leondgarse/keras_cv_attention_models · +9 2021
56 PyramidNet + AA (AMP) 98.02 Regularizing Neural Networks via Adversarial Model Perturbation hiyouga/AMP-Regularizer 2020
57 EnAET 98.01 EnAET: A Self-Trained framework for Semi-Supervised and Supervised Learning with Ensemble Transformations maple-research-lab/EnAET · wang3702/EnAET 2019
58 MUXNet-m 98.098.0 MUXConv: Information Multiplexing in Convolutional Neural Networks human-analysis/MUXConv 2020
58 LeViT-384 98 LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference huggingface/transformers · rwightman/pytorch-image-models · leondgarse/keras_cv_attention_models · +9 2021
58 CCT-7/3x1* 98 Escaping the Big Data Paradigm with Compact Transformers keras-team/keras-io · SHI-Labs/Compact-Transformers · brohrer/sharpened-cosine-similarity · +6 2021
58 ConvMLP-S 98 ConvMLP: Hierarchical Convolutional MLPs for Vision BR-IDL/PaddleViT · shinya7y/UniverseNet · liuruiyang98/Jittor-MLP · +1 2021
62 Proxyless-G + c/o 97.92 ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware osmr/imgclsmob · mit-han-lab/once-for-all · mit-han-lab/ProxylessNAS · +20 2018
63 NAT-M2 97.997.94.6M Neural Architecture Transfer human-analysis/neural-architecture-transfer · awesomelemon/encas 2020
63 WRN-28-10+AutoDropout+RandAugment 97.9 AutoDropout: Learning Dropout Patterns to Regularize Deep Networks google-research/google-research 2021
65 SENet + ShakeShake + Cutout 97.88 Squeeze-and-Excitation Networks PaddlePaddle/PaddleOCR · xmu-xiaoma666/External-Attention-pytorch · open-mmlab/mmpose · +82 2017
66 HCGNet-A3 97.86 Gated Convolutional Networks with Hybrid Connectivity for Image Classification winycg/HCGNet 2019
67 Wide-ResNet-28-10 97.85 Automatic Data Augmentation via Invariance-Constrained Learning ihounie/daug 2022
68 ResNeXt-50 (AutoMix) 97.84 AutoMix: Unveiling the Power of Mixup for Stronger Classifiers Westlake-AI/openmixup · zeyuanyin/tiny-imagenet · Westlake-AI/AutoMix 2021
69 ResNet-152x4-AGC (ImageNet-21K) 97.82 Effect of Pre-Training Scale on Intra- and Inter-Domain Full and Few-Shot Transfer Learning for Natural and Medical X-Ray Chest Images SLAMPAI/large-scale-pretraining-transfer 2021
70 Mixer-B/16- SAM 97.8 When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations google-research/vision_transformer · ttt496/VisionTransformer 2021
71 CCT-7/3x1+VTM 97.78 TokenMixup: Efficient Attention-guided Token-level Data Augmentation for Transformers mlvlab/tokenmixup 2022
72 WRN-28-10 97.73 MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks alexrame/mixmo-pytorch 2021
73 HCGNet-A2 97.71 Gated Convolutional Networks with Hybrid Connectivity for Image Classification winycg/HCGNet 2019
74 WRN + fixup init + mixup + cutout 97.7 Fixup Initialization: Residual Learning Without Normalization hongyi-zhang/Fixup · bzhangGo/zero · Zelgunn/CustomKerasLayers · +7 2019
75 NoisyDARTS-a 97.61 Noisy Differentiable Architecture Search xiaomi-automl/NoisyDARTS 2020
75 TransBoost-ResNet50 97.61 TransBoost: Improving the Best ImageNet Performance using Deep Transduction omerb01/transboost 2022
77 LeViT-128 97.6 LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference huggingface/transformers · rwightman/pytorch-image-models · leondgarse/keras_cv_attention_models · +9 2021
78 DenseNet-BC-190 + batchboost 97.54 batchboost: regularization for stabilizing training with resistance to underfitting & overfitting maciejczyzewski/batchboost 2020
79 LeViT-128S 97.5 LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference huggingface/transformers · rwightman/pytorch-image-models · leondgarse/keras_cv_attention_models · +9 2021
80 Shared WRN 97.47 Learning Implicitly Recurrent CNNs Through Parameter Sharing lolemacs/soft-sharing 2019
81 Manifold Mixup WRN 28-10 97.45 Manifold Mixup: Better Representations by Interpolating Hidden States Westlake-AI/openmixup · vikasverma1077/manifold_mixup · jankrepl/mildlyoverfitted · +9 2018
81 WRN 28-14 97.45 Neural networks with late-phase weights google/uncertainty-baselines · seijin-kobayashi/late-phase-weights 2020
83 SparseSwin 97.43 SparseSwin: Swin Transformer with Sparse Transformer Block krisnapinasthika/sparseswin 2023
84 WRN-28-10 with reSGHMC 97.42 Non-convex Learning via Replica Exchange Stochastic Gradient MCMC gaoliyao/Replica_Exchange_Stochastic_Gradient_MCMC · WayneDW/Variance_Reduced_Replica_Exchange_SGMCMC 2020
85 NAT-M1 97.497.44.3M Neural Architecture Transfer human-analysis/neural-architecture-transfer · awesomelemon/encas 2020
85 ResNet-50-SAM 97.4 When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations google-research/vision_transformer · ttt496/VisionTransformer 2021
87 DenseNet-BC-190 + Mixup 97.3 mixup: Beyond Empirical Risk Minimization rwightman/pytorch-image-models · pytorch/vision · PaddlePaddle/PaddleDetection · +68 2017
87 kNN-CLIP 97.3 Revisiting a kNN-based Image Classification System with High-capacity Storage 2022
89 WaveMixLite-144/7 97.29 WaveMix: A Resource-efficient Neural Network for Image Analysis pranavphoenix/WaveMix 2022
90 Transformer local-attention (NesT-B) 97.2 Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding rwightman/pytorch-image-models · google-research/nested-transformer · ttt496/vit-pytorch · +3 2021
91 ShakeShake-2x64d + SWA 97.12 Averaging Weights Leads to Wider Optima and Better Generalization timgaripov/swa · wjmaddox/swa_gaussian · ENSTA-U2IS-AI/torch-uncertainty · +14 2018
91 PyramidNet-200 + CutMix 97.12 CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features rwightman/pytorch-image-models · pytorch/vision · kornia/kornia · +27 2019
93 Wide-ResNet-40-2 97.05 Automatic Data Augmentation via Invariance-Constrained Learning ihounie/daug 2022
94 ORN 97.02 Oriented Response Networks ZhouYanzhao/ORN 2017
95 WRN-16-8 with reSGHMC 96.87 Non-convex Learning via Replica Exchange Stochastic Gradient MCMC gaoliyao/Replica_Exchange_Stochastic_Gradient_MCMC · WayneDW/Variance_Reduced_Replica_Exchange_SGMCMC 2020
95 ResNet_XnIDR 96.87 XnODR and XnIDR: Two Accurate and Fast Fully Connected Layers For Convolutional Neural Networks jiansfoggy/CODE-SHOW 2021
97 HCGNet-A1 96.85 Gated Convolutional Networks with Hybrid Connectivity for Image Classification winycg/HCGNet 2019
98 WRN 28-10 96.81 Neural networks with late-phase weights google/uncertainty-baselines · seijin-kobayashi/late-phase-weights 2020
99 AutoDropout 96.8 AutoDropout: Learning Dropout Patterns to Regularize Deep Networks google-research/google-research 2021
100 WRN-28-10 + SWA 96.79 Averaging Weights Leads to Wider Optima and Better Generalization timgaripov/swa · wjmaddox/swa_gaussian · ENSTA-U2IS-AI/torch-uncertainty · +14 2018
1–100 / 279 다음 → 페이지당 10 20 50 100