OpenCodePapers

image-classification-on-cifar-100

Image Classification
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodePercentage correctPARAMSAccuracyTop 1 AccuracyModelNameReleaseDate
Sharpness-Aware Minimization for Efficiently Improving Generalization✓ Link96.08EffNet-L2 (SAM)2020-10-03
ML-Decoder: Scalable and Versatile Classification Head✓ Link95.1Swin-L + ML-Decoder2021-11-25
An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems✓ Link94.95µ2Net (ViT-L/16)2022-05-25
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale✓ Link94.55Vision Transformer (ViT-H/14) (extra data)2020-10-22
Multimodal Autoregressive Pre-training of Large Vision Encoders✓ Link94.5AIMv2 ViT-3B/14 448px2024-11-21
DINOv2: Learning Robust Visual Features without Supervision✓ Link94.4DINOv2 (ViT-g/14)2023-04-14
ImageNet-21K Pretraining for the Masses✓ Link94.2ViT-B-16 (ImageNet-21K-P pretrain)2021-04-22
CvT: Introducing Convolutions to Vision Transformers✓ Link94.09CvT-W242021-03-29
Perturbated Gradients Updating within Unit Space for Deep Learning✓ Link93.95ViT-B/16 (PUGD)2021-10-01
PolyViT: Co-training Vision Transformers on Images, Videos and Audio93.9PolyViT-L2021-11-25
An Algorithm for Routing Vectors in Sequences✓ Link93.8309.8MHeinsen Routing + BEiT-large 16 2242022-11-20
Big Transfer (BiT): General Visual Representation Learning✓ Link93.51BiT-L (ResNet)2019-12-24
Reduction of Class Activation Uncertainty with Background Information✓ Link93.31VIT-L/16 (Spinal FC, Background)2023-05-05
ReFTA: Breaking the Weight Reconstruction Bottleneck in Tensorized Parameter-Efficient Fine-Tuning✓ Link93.26ReFTA (ViT-Large)2026-06-03
Going deeper with Image Transformers✓ Link93.1CaiT-M-36 U 2242021-03-31
Efficient Stitchable Task Adaptation✓ Link93.08ESTA2023-11-29
Three things everyone should know about Vision Transformers✓ Link93.0ViT-L (attn fine-tune)2022-03-18
TResNet: High Performance GPU-Dedicated Architecture✓ Link92.6TResNet-L-V22020-03-30
Sheared Backpropagation for Fine-tuning Foundation Models92.4PREBR++JS@70%2024-06-17
EfficientNetV2: Smaller Models and Faster Training✓ Link92.3EfficientNetV2-L2021-04-01
EfficientNetV2: Smaller Models and Faster Training✓ Link92.2EfficientNetV2-M2021-04-01
Big Transfer (BiT): General Visual Representation Learning✓ Link92.17BiT-M (ResNet)2019-12-24
Multi-label Cluster Discrimination for Visual Representation Learning✓ Link92.0MLCD ViT-L/14 (linear probe)2024-07-24
Star with Bilinear Mapping✓ Link91.9SBM-B2025-06-11
Incorporating Convolution Designs into Visual Transformers✓ Link91.8CeiT-S2021-03-22
Incorporating Convolution Designs into Visual Transformers✓ Link91.8CeiT-S (384 finetune resolution)2021-03-22
BEiT: BERT Pre-Training of Image Transformers✓ Link91.8BEiT (extra data)2021-06-15
Scalable Pre-training of Large Autoregressive Image Models✓ Link91.8AIM-7B (layer 20)2024-01-16
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks✓ Link91.764MEfficientNet-B72019-05-28
EfficientNetV2: Smaller Models and Faster Training✓ Link91.5EfficientNetV2-S2021-04-01
Stabilizing Feature Geometry in Noisy Pretrained Models for Robust Downstream Tasks91.48FGS (Swin-L, ImageNet-21K)2026-06-03
GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism✓ Link91.3GPIPE2018-11-16
AdapterTune: Zero-Initialized Low-Rank Adapters for Frozen Vision Transformers✓ Link91.2AdapterTune (ViT-B/16)2026-03-16
Transformer in Transformer✓ Link91.165.6MTNT-B2021-02-27
HAMSA: Scanning-Free Vision State Space Models via SpectralPulseNet✓ Link91.0Hamsa-B2026-04-16
Pay Attention to Attention Distribution: A New Local Lipschitz Bound for Transformers90.94JaSMin (ViT-B, k=10, lambda=1e-3, max)2025-07-10
Training data-efficient image transformers & distillation through attention✓ Link90.886MDeiT-B2020-12-23
ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyond✓ Link90.8ViTAE-S2022-02-21
Edge-RecViT: Efficient Vision Transformer via Semantic-Refined Dynamic Recursion✓ Link90.78Edge-RecViT (Base)2026-06-03
Going Deep: Deep Visual Prompting with LoTeP90.57LoTeP-CP2026-09-08
Masked Siamese Networks for Label-Efficient Learning✓ Link90.5MSN ViT-B/162022-04-14
A General and Efficient Training for Transformer via Token Expansion✓ Link90.37DeiT Small + ToE2024-03-31
Global Filter Networks for Image Classification✓ Link90.354MGFNet-H-B2021-07-01
Rethinking Recurrent Neural Networks and Other Improvements for Image Classification✓ Link90.27E2E-3M2020-07-30
Bridging Vision and Language Concepts through Optimal Transport Semantic Flow✓ Link90.21OTF-CBM2026-06-25
Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy✓ Link90.2Bamboo (ViT-B/16)2022-03-15
HAMSA: Scanning-Free Vision State Space Models via SpectralPulseNet✓ Link90.2Hamsa-S2026-04-16
Sample- and Parameter-Efficient Auto-Regressive Image Models✓ Link90.0XTRA-H (ViT-H/14) (extra data)2024-11-23
ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks✓ Link89.90PyramidNet-272 (ASAM)2021-02-23
Sharpness-Aware Minimization for Efficiently Improving Generalization✓ Link89.7PyramidNet (SAM)2020-10-03
Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognition✓ Link89.63DVT (T2T-ViT-24)2021-05-31
ResMLP: Feedforward networks for image classification with data-efficient training✓ Link89.5ResMLP-242021-05-07
Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture✓ Link89.5I-JEPA ViT-G/162023-01-19
DnA: Denoising Attention for Visual Tasks✓ Link89.5DnA (ViT-B)2026-06-25
Friendly Sharpness-Aware Minimization✓ Link89.49F-SAM2024-03-19
Towards Better Accuracy-efficiency Trade-offs: Divide and Co-training✓ Link89.4632.8MPyramidNet-272, S=42020-11-30
Incorporating Convolution Designs into Visual Transformers✓ Link89.4CeiT-T2021-03-22
AutoAugment: Learning Augmentation Policies from Data✓ Link89.3PyramidNet+ShakeDrop2018-05-24
Align Once to Explain: Feature Alignment for Scalable B-cosification of Foundational Vision Transformers✓ Link89.14ALOE DINOv3 ViT-B/162026-06-03
When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations✓ Link89.1ViT-B/16- SAM2021-06-03
ConvMLP: Hierarchical Convolutional MLPs for Vision✓ Link89.1ConvMLP-M2021-09-09
LoKi: Low-dimensional KAN for Efficient Fine-tuning Image Models89.1LoKi2025-06-11
ConvMLP: Hierarchical Convolutional MLPs for Vision✓ Link88.6ConvMLP-L2021-09-09
Effect of Pre-Training Scale on Intra- and Inter-Domain Full and Few-Shot Transfer Learning for Natural and Medical X-Ray Chest Images✓ Link88.54ResNet-152x4-AGC (ImageNet-21K)2021-05-31
Generative Pretraining from Pixels✓ Link88.5iGPT-L2020-07-17
ColorNet: Investigating the importance of color spaces for image classification✓ Link88.419.0MColorNet2019-02-01
Mamba-Adaptor: State Space Model Adaptor for Visual Recognition88.34Mamba-Adaptor (VMamba-B)2025-05-19
Fast AutoAugment✓ Link88.3PyramidNet+ShakeDrop (Fast AA)2019-05-01
Neural Architecture Transfer✓ Link88.39.0MNAT-M42020-05-12
Learning from Itself: Mining Internal Knowledge from Vision Language Models for Continual Learning✓ Link88.12LfI (OpenCLIP ViT-L/14, LAION-400M) (extra data)2026-06-03
GliaNet: Adaptive Neural Network Structure Learning with Glia-Driven88.05GliaNet (ViT-B)2025-06-11
Incorporating Convolution Designs into Visual Transformers✓ Link88CeiT-T (384 finetune resolution)2021-03-22
Neural Architecture Transfer✓ Link87.77.8MNAT-M32020-05-12
When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations✓ Link87.6ViT-S/16- SAM2021-06-03
Neural Architecture Transfer✓ Link87.56.4MNAT-M22020-05-12
Dense Vision Transformer Compression with Few Samples87.5DC-ViT-B (extra data)2024-03-27
PSO-Convolutional Neural Networks with Heterogeneous Learning Rate✓ Link87.48Dynamics 12022-05-20
Towards Better Accuracy-efficiency Trade-offs: Divide and Co-training✓ Link87.4426.3MDenseNet-BC-190, S=42020-11-30
ConvMLP: Hierarchical Convolutional MLPs for Vision✓ Link87.4ConvMLP-S2021-09-09
Progressive Neural Architecture Generation87.2PNAG2026-06-03
ResMLP: Feedforward networks for image classification with data-efficient training✓ Link87.0ResMLP-122021-05-07
Towards Better Accuracy-efficiency Trade-offs: Divide and Co-training✓ Link86.90WRN-40-10, S=42020-11-30
ResNet strikes back: An improved training procedure in timm✓ Link86.925MResNet50 (A1)2021-10-01
MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks✓ Link86.81WRN-28-10 * 32021-03-10
Regularizing Neural Networks via Adversarial Model Perturbation✓ Link86.64PyramidNet + AA (AMP)2020-10-10
Self-Knowledge Distillation with Progressive Refinement of Targets✓ Link86.41PyramidNet-200 + Shakedrop + Cutmix + PS-KD2020-06-22
When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations✓ Link86.4Mixer-B/16- SAM2021-06-03
Deep Feature Response Discriminative Calibration✓ Link86.31ResCNet-502024-11-16
CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features✓ Link86.19PyramidNet-200 + Shakedrop + Cutmix2019-05-13
MUXConv: Information Multiplexing in Convolutional Neural Networks✓ Link86.12.1MMUXNet-m2020-03-31
Neural Architecture Transfer✓ Link86.03.8MNAT-M12020-05-12
SpikingResformer: Bridging ResNet and Vision Transformer in Spiking Neural Networks✓ Link85.98SpikingResformer-S2024-03-21
MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks✓ Link85.77WRN-28-102021-03-10
Towards Better Accuracy-efficiency Trade-offs: Divide and Co-training✓ Link85.74WRN-28-10, S=42020-11-30
MULTIFLOW: Shifting Towards Task-Agnostic Vision-Language Pruning✓ Link85.6MULTIFLOW (DINO_B/16, 63% sparsity) (extra data)2024-04-08
85.59WRN-28-8 (SAMix+DM)
Closest Neighbors are Harmful for Lightweight Masked Auto-encoders✓ Link85.57NoR-MAE (ViT-Small)2025-06-11
Boosting Discriminative Visual Representation Learning with Scenario-Agnostic Mixup✓ Link85.50WRN-28-8 +SAMix2021-11-30
Improving Neural Architecture Search Image Classifiers via Ensemble Learning✓ Link85.42ASANas2019-03-14
$λ$-JEPA Spectral Anti-Collapse Regularization for Self-Supervised Learning✓ Link85.4λ-JEPA ViT-B/16 (linear probe)2026-09-28
85.38WRN-28-8 (AutoMix+DM)
SparseSwin: Swin Transformer with Sparse Transformer Block✓ Link85.3517.58MSparseSwin2023-09-11
85.25WRN-28-8 (PuzzleMix+DM)
When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations✓ Link85.2ResNet-50-SAM2021-06-03
AutoMix: Unveiling the Power of Mixup for Stronger Classifiers✓ Link85.16WRN-28-8 +AutoMix2021-03-24
WaveMix: A Resource-efficient Neural Network for Image Analysis✓ Link85.09WaveMixLite-256/72022-05-28
Linear Attention with Global Context: A Multipole Attention Mechanism for Vision and Physics✓ Link85.08MANO-tiny2025-07-03
Neural networks with late-phase weights✓ Link85.00WRN 28-142020-07-25
ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias✓ Link85.0ViTAE-T2021-06-07
Expeditious Saliency-guided Mix-up through Random Gradient Thresholding✓ Link85R-Mix (WideResNet 28-10)2022-12-09
EEEA-Net: An Early Exit Evolutionary Neural Architecture Search✓ Link84.98EEEA-Net-C (b=5)+ CO2021-08-13
Expeditious Saliency-guided Mix-up through Random Gradient Thresholding✓ Link84.9RL-Mix (WideResNet 28-10)2022-12-09
Automatic Data Augmentation via Invariance-Constrained Learning✓ Link84.89Wide-ResNet-28-102022-09-29
Squeeze-and-Excitation Networks✓ Link84.59SENet + ShakeEven + Cutout2017-09-05
Boosting Discriminative Visual Representation Learning with Scenario-Agnostic Mixup✓ Link84.42ResNeXt-50(32x4d) + SAMix2021-11-30
Non-convex Learning via Replica Exchange Stochastic Gradient MCMC✓ Link84.38WRN-28-10 with reSGHMC2020-08-12
Averaging Weights Leads to Wider Optima and Better Generalization✓ Link84.16PyramidNet-272 + SWA2018-03-14
Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup✓ Link84.05WRN28-102020-09-15
Gated Convolutional Networks with Hybrid Connectivity for Image Classification✓ Link84.0411.4MHCGNet-A32019-08-26
Random Entangled Tokens for Adversarially Robust Vision Transformer84.02ReiT (ViT-S, NAT)2024-06-17
Expeditious Saliency-guided Mix-up through Random Gradient Thresholding✓ Link83.97WideResNet 28-10 + CutMix (OneCycleLR scheduler)2022-12-09
FMix: Enhancing Mixed Sample Data Augmentation✓ Link83.95DenseNet-BC-190 + FMix2020-02-27
Oriented Response Networks✓ Link83.85ORN2017-01-07
Grafit: Learning fine-grained image representations with coarse labels83.7Grafit (ResNet-50)2020-11-25
AutoMix: Unveiling the Power of Mixup for Stronger Classifiers✓ Link83.64ResNeXt-50(32x4d) + AutoMix2021-03-24
Pre-training Vision Models with Mandelbulb Variations✓ Link83.6ViT-B (MandelbulbVAR-Hybrid-21k)2024-06-17
TokenMixup: Efficient Attention-guided Token-level Data Augmentation for Transformers✓ Link83.57CCT-7/3x1+HTM+VTM2022-10-14
Gated Convolutional Networks with Hybrid Connectivity for Image Classification✓ Link83.463.1MHCGNet-A22019-08-26
Res2Net: A New Multi-scale Backbone Architecture✓ Link83.44Res2NeXt-292019-04-02
FDSML: Formula-Driven Supervised Metric Learning with Parameter-Aware Triplet Loss✓ Link83.3FDSML (ViT-Base, each) (extra data)2026-10-29
mixup: Beyond Empirical Risk Minimization✓ Link83.20DenseNet-BC-190 + Mixup2017-10-25
Contextual Classification Using Self-Supervised Auxiliary Models for Deep Neural Networks✓ Link83.2SSAL-DenseNet 190-402021-01-07
EnAET: A Self-Trained framework for Semi-Supervised and Supervised Learning with Ensemble Transformations✓ Link83.13EnAET2019-11-21
Neural networks with late-phase weights✓ Link83.06WRN 28-102020-07-25
Your Image is My Video: Reshaping the Receptive Field via Image-To-Video Differentiable AutoAugmentation and Fusion83.06DAS (WideResNet-28-2)2024-03-22
Expeditious Saliency-guided Mix-up through Random Gradient Thresholding✓ Link83.02R-Mix (ResNeXt 29-4-24)2022-12-09
Single-bit-per-weight deep convolutional neural networks without batch-normalization layers for embedded systems✓ Link82.95Wide ResNet+Cutout+no BN scale/offset learning2019-07-16
Non-convex Learning via Replica Exchange Stochastic Gradient MCMC✓ Link82.95WRN-16-8 with reSGHMC2020-08-12
Densely Connected Convolutional Networks✓ Link82.82DenseNet-BC2016-08-25
Masked Siamese Networks for Label-Efficient Learning✓ Link82.8MSN ViT-B/16 (linear probe)2022-04-14
ANDHRA Bandersnatch: Training Neural Networks to Predict Parallel Realities✓ Link82.784ABNet-2G-R3-Combined2024-11-28
Escaping the Big Data Paradigm with Compact Transformers✓ Link82.72CCT-7/3x1*2021-04-12
EXACT: How to Train Your Accuracy✓ Link82.68EXACT (WRN-28-10)2022-05-19
Selective Kernel Networks✓ Link82.67SKNet-29 (ResNeXt-29, 16×32d)2019-03-15
Densely Connected Convolutional Networks✓ Link82.62DenseNet2016-08-25
Learning Implicitly Recurrent CNNs Through Parameter Sharing✓ Link82.57Shared WRN2019-02-26
Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding✓ Link82.56Transformer local-attention (NesT-B)2021-05-26
Expeditious Saliency-guided Mix-up through Random Gradient Thresholding✓ Link82.43RL-Mix (ResNeXt 29-4-24)2022-12-09
When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations✓ Link82.4Mixer-S/16- SAM2021-06-03
Expeditious Saliency-guided Mix-up through Random Gradient Thresholding✓ Link82.32R-Mix (WideResNet 16-8)2022-12-09
Expeditious Saliency-guided Mix-up through Random Gradient Thresholding✓ Link82.3ResNeXt 29-4-24 + CutMix (OneCycleLR scheduler)2022-12-09
Locality-Attending Vision Transformer✓ Link82.2LocAtViT (Base)2026-03-05
Attend and Rectify: a Gated Attention Mechanism for Fine-Grained Recovery✓ Link82.18WARN2018-07-19
Expeditious Saliency-guided Mix-up through Random Gradient Thresholding✓ Link82.16RL-Mix (WideResNet 16-8)2022-12-09
Averaging Weights Leads to Wider Optima and Better Generalization✓ Link82.15WRN+SWA2018-03-14
Self-Supervised Representation Learning from Arbitrary Scenarios82.1ASL (ViT-S, fine-tuning)2024-06-17
STAA-SNN: Spatial-Temporal Attention Aggregator for Spiking Neural Networks82.05STAA-SNN (ResNet-19, T=4)2025-03-04
Manifold Mixup: Better Representations by Interpolating Hidden States✓ Link81.96Manifold Mixup2018-06-13
Gated Convolutional Networks with Hybrid Connectivity for Image Classification✓ Link81.871.1MHCGNet-A12019-08-26
Expeditious Saliency-guided Mix-up through Random Gradient Thresholding✓ Link81.79WideResNet 16-8 + CutMix (OneCycleLR scheduler)2022-12-09
Learning Identity Mappings with Residual Gates81.73Residual Gates + WRN2016-11-04
Revisiting a kNN-based Image Classification System with High-capacity Storage81.7kNN-CLIP2022-04-03
Attention Augmented Convolutional Networks✓ Link81.6AA-Wide-ResNet2019-04-22
PDO-eConvs: Partial Differential Operator Based Equivariant Convolutions✓ Link81.6PDO-eConv (p8, 4.6M)2020-07-20
Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision✓ Link81.53SEER (RegNet10B)2022-02-16
Expeditious Saliency-guided Mix-up through Random Gradient Thresholding✓ Link81.49R-Mix (PreActResNet-18)2022-12-09
On the Performance Analysis of Momentum Method: A Frequency Domain Perspective✓ Link81.44ResNet50 (FSGDM)2024-11-29
Improving Generalization via Meta-Learning on Hard Samples81.42LRWOpt2024-03-18
Automatic Data Augmentation via Invariance-Constrained Learning✓ Link81.19Wide-ResNet-40-22022-09-29
Wide Residual Networks✓ Link81.15Wide ResNet2016-05-23
Caption Bottleneck Models✓ Link81.14CaBM2026-07-01
Deep Competitive Pathway Networks✓ Link81.10CoPaNet-R-1642017-09-29
Rethinking Spiking Self-Attention Mechanism: Implementing a-XNOR Similarity Calculation in Spiking Transformers81.08M-ViT + α-SSA (α=0.3)2025-06-11
ANDHRA Bandersnatch: Training Neural Networks to Predict Parallel Realities✓ Link80.830ABNet-2G-R32024-11-28
Training-Adaptive Convolutional Sparse Coding via Information Bottleneck for Robust Visual Representation✓ Link80.76TA-CSC-18 all2026-09-17
Expeditious Saliency-guided Mix-up through Random Gradient Thresholding✓ Link80.75RL-Mix (PreActResNet-18)2022-12-09
Intrinsically Stable Spiking Neural Networks: Overcoming the Performance Barrier in the Absence of Batch Normalization80.72IS-SNN SEW-ResNet-19 (T=6, strong augmentation)2026-06-30
Expeditious Saliency-guided Mix-up through Random Gradient Thresholding✓ Link80.6PreActResNet-18 + CutMix (OneCycleLR scheduler)2022-12-09
Gated Attention Coding for Training High-performance and Efficient Spiking Neural Networks✓ Link80.45GAC-SNN2023-08-12
ANDHRA Bandersnatch: Training Neural Networks to Predict Parallel Realities✓ Link80.354ABNet-2G-R22024-11-28
Towards Principled Design of Deep Convolutional Networks: Introducing SimpNet✓ Link80.29SimpleNetv22018-02-17
UPANets: Learning from the Universal Pixel Attention Networks✓ Link80.29UPANets2021-03-15
Prune Once: Retraining-Free Task-Agnostic Pruning for Vision-Language Models✓ Link80.27PORTA (OpenAI CLIP-ViT-bigG, 55% sparsity)2026-08-07
SageMix: Saliency-Guided Mixup for Point Clouds✓ Link80.16PreActResNet-18 + SageMix2022-10-13
Non-convex Learning via Replica Exchange Stochastic Gradient MCMC✓ Link80.14ResNet56 with reSGHMC2020-08-12
PDO-eConvs: Partial Differential Operator Based Equivariant Convolutions✓ Link79.99PDO-eConv (p8, 2.62M)2020-07-20
Training Neural Networks with Local Error Signals✓ Link79.9VGG11B(3x) + LocalLearning2019-01-20
Improving Accuracy and Calibration via Differentiated Deep Mutual Learning79.3Diff-DML-2 (ResNet50)2025-06-11
With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations✓ Link79NNCLR2021-04-29
ANDHRA Bandersnatch: Training Neural Networks to Predict Parallel Realities✓ Link78.792ABNet-2G-R12024-11-28
Auto-Train-Once: Controller Network Guided Automatic Network Pruning from Scratch✓ Link78.54Auto-Train-Once (ATO)2024-03-21
Regularizing Neural Networks via Adversarial Model Perturbation✓ Link78.49PreActResNet18 (AMP)2020-10-10
Lets keep it simple, Using simple architectures to outperform deeper and more complex architectures✓ Link78.37SimpleNetv12016-08-22
RepAn: Enhanced Annealing through Re-parameterization✓ Link78.37RepAn (ResNet-18, ACNet)2024-06-17
Fourier or Wavelet bases as counterpart self-attention in spikformer for efficient visual classification78.3FWformer-4-384 (2D-FFT, MS)2024-03-27
Pre-training of Lightweight Vision Transformers on Small Datasets with Minimally Scaled Images78.273.64MViT (lightweight, MAE pre-trained)2024-02-06
Hyperbolic Busemann Neural Networks✓ Link78.1BMLR-P2026-02-21
Exploring the Transferability of Visual Prompting for Multimodal Large Language Models✓ Link77.92TVP (ours)2024-04-17
Augmenting Deep Classifiers with Polynomial Neural Networks✓ Link77.9PDC2021-04-16
Rethinking Depthwise Separable Convolutions: How Intra-Kernel Correlations Lead to Improved MobileNets✓ Link77.7MobileNetV3-large x1.0 (BSConv-U)2020-03-30
FLAVA: A Foundational Language And Vision Alignment Model✓ Link77.68FLAVA2021-12-08
Escaping the Big Data Paradigm with Compact Transformers✓ Link77.313.17MCCT-6/3x12021-04-12
Identity Mappings in Deep Residual Networks✓ Link77.3ResNet-10012016-03-16
Large-Scale Evolution of Image Classifiers✓ Link77Evolution2017-03-03
DIANet: Dense-and-Implicit Attention Network✓ Link76.98DIANet2019-05-25
Encoding the latent posterior of Bayesian Neural Networks for uncertainty quantification✓ Link76.85LP-BNN (ours) + cutout2020-12-04
Learning Class Unique Features in Fine-Grained Visual Classification76.64ResNet-18+MM+FRL2020-11-22
SQS: Bayesian DNN Compression through Sparse Quantized Sub-distributions✓ Link76.63SQS (ResNet-18,4bit,50%nonzero,M=50)2026-09-07
Non-convex Learning via Replica Exchange Stochastic Gradient MCMC✓ Link76.55ResNet32 with reSGHMC2020-08-12
Momentum Residual Neural Networks✓ Link76.38MomentumNet2021-02-15
Dynamic Group Normalization: Spatio-Temporal Adaptation to Evolving Data Statistics76.12Dynamic Group Normalization (DGN)2025-06-11
Steganographic Passport: An Owner and User Verifiable Credential for Deep Model IP Protection Without Retraining76.1Steganographic Passport (ResNet-18, BN)2024-04-03
LANCE: Low Rank Activation Compression for Efficient On-Device Continual Learning✓ Link75.94LANCE (ResNet34, 4 layers)2025-09-25
Spatially-sparse convolutional neural networks✓ Link75.7SSCNN2014-09-22
Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)✓ Link75.7Exponential Linear Units2015-11-23
CNN Filter DB: An Empirical Investigation of Trained Convolutional Filters✓ Link75.59ResNet-92022-03-29
Deep Networks with Stochastic Depth✓ Link75.42Stochastic Depth2016-03-30
Boosting Order-Preserving and Transferability for Neural Architecture Search: a Joint Architecture Refined Search and Fine-tuning Approach✓ Link75.38Supernet Shifting2024-03-18
JointSQ: Joint Sparsification-Quantization for Distributed Learning75.04JointSQ2024-06-17
Mish: A Self Regularized Non-Monotonic Activation Function✓ Link74.41ResNet v2-110 (Mish activation)2019-08-23
Differentiable Spike: Rethinking Gradient-Descent for Training Spiking Neural Networks74.24Dspike (ResNet-18)2021-12-01
Non-convex Learning via Replica Exchange Stochastic Gradient MCMC✓ Link74.14ResNet20 with reSGHMC2020-08-12
MixMatch: A Holistic Approach to Semi-Supervised Learning✓ Link74.1MixMatch2019-05-06
Beta-Rank: A Robust Convolutional Filter Pruning Method For Imbalanced Medical Image Analysis✓ Link74.0174.01Beta-Rank2023-04-15
How to Use Dropout Correctly on Residual Networks with Batch Normalization✓ Link73.98PreResNet-1102023-02-13
ANDHRA Bandersnatch: Training Neural Networks to Predict Parallel Realities✓ Link73.930ABNet-2G-R02024-11-28
Flexible Group Count Enables Hassle-Free Structured Pruning73.63LeanFlex-GKP (ResNet110, PR=43.75%)2025-06-11
Fractional Max-Pooling✓ Link73.6Fractional MP2014-12-18
Deep Residual Networks with Exponential Linear Unit✓ Link73.5ResNet+ELU2016-04-14
Drainage: A Unifying Framework for Addressing Class Uncertainty✓ Link73.31Drainage2025-12-02
PDO-eConvs: Partial Differential Operator Based Equivariant Convolutions✓ Link73PDO-eConv (p6m,0.37M)2020-07-20
Not All Objectives Are Born Equal: Priority-Constrained Descent for Hierarchical Multi-Objective Optimization✓ Link73.0Priority-Constrained Descent (PCD)2026-09-21
Stochastic Optimization of Plain Convolutional Neural Networks with Simple methods✓ Link72.964,252,298SOPCNN2020-01-24
PDO-eConvs: Partial Differential Operator Based Equivariant Convolutions✓ Link72.87PDO-eConv (p6,0.36M)2020-07-20
SIMPLER: Efficient Foundation Model Adaptation via Similarity-Guided Layer Pruning for Earth Observation72.8SIMPLER (ViT-MAE, ImageNet-pretrained) (extra data)2026-03-20
Population Normalization for Federated Learning72.74Noisy Population Normalization (NPN)2025-06-11
Scalable Bayesian Optimization Using Deep Neural Networks✓ Link72.6Tuned CNN2015-02-19
Stochastic Subsampling With Average Pooling72.537ResNet-110 (SAP)2024-09-25
Competitive Multi-scale Convolution72.4CMsC2015-11-18
All you need is a good init✓ Link72.3Fitnet4-LSUV2015-11-19
How transfer learning is used in generative models for image classification: improved accuracy✓ Link71.52GAN+ResNet2024-12-09
Grouped Pointwise Convolutions Reduce Parameters in Convolutional Neural Networks✓ Link71.360.52MkMobileNet V3 Large 16ch2022-06-30
Batch-normalized Maxout Network in Network✓ Link71.1BNM NiN2015-11-09
Online Training Through Time for Spiking Neural Networks✓ Link71.05OTTT2022-10-09
On the Importance of Normalisation Layers in Deep Learning with Piecewise Linear Activation Units70.8MIM2015-08-03
AZ-NAS: Assembling Zero-Cost Proxies for Network Architecture Search✓ Link70.75AZ-NAS2024-03-28
OrthCaps: An Orthogonal CapsNet with Sparse Attention Routing and Pruning70.56OrthCaps-D2024-03-20
A Few Gaussians Is All You Need: SSOG-Attention That Steers Instead of Scores✓ Link70.4SSOG factorized +μδ2026-08-15
WaveMix: A Resource-efficient Neural Network for Image Analysis✓ Link70.20WaveMix-Lite-256/72022-05-28
IM-Loss: Information Maximization Loss for Spiking Neural Networks70.18IM-Loss (VGG-16)2022-10-31
Learning Activation Functions to Improve Deep Neural Networks✓ Link69.2NiN+APL2014-12-21
Dynamic Sparse Attention and Mixture-of-Experts for Iterative Visual Classification69.2DSA-MoE2026-08-02
Stacked What-Where Auto-encoders✓ Link69.1SWWAE2015-06-08
Deep Convolutional Decision Jungle for Image Classification69NiN+Superclass+CDJ2017-06-06
Fourier-basis Functions to Bridge Augmentation Gap: Rethinking Frequency Augmentation in Image Classification✓ Link68.48CCT + PRIME + AFA2024-03-04
Spectral Representations for Convolutional Neural Networks68.4Spectral Representations for Convolutional Neural Networks2015-06-11
"BNN - BN = ?": Training Binary Neural Networks without Batch Normalization✓ Link68.34ReActNet-182021-04-16
Training Very Deep Networks✓ Link67.8VDN2015-07-22
Deep Convolutional Neural Networks as Generic Feature Extractors67.7DCNN+GFE2017-10-06
Generalizing Pooling Functions in Convolutional Neural Networks: Mixed, Gated, and Tree✓ Link67.6Tree+Max-Avg pooling2015-09-30
Selection-as-Nonlinearity: Bridging Attention and Activation via a Joint Game-Decision Lens for Interpretable, Discriminative Visual Representations✓ Link67.6Swin-CSaN (CIFAR-Swin-Tiny)2026-06-03
HD-CNN: Hierarchical Deep Convolutional Neural Network for Large Scale Visual Recognition✓ Link67.4HD-CNN2014-10-03
Universum Prescription: Regularization using Unlabeled Data67.2Universum Prescription2015-11-11
ResNet50_on_Cifar_100_Without_Transfer_Learning✓ Link67.060ResNet50 Without Transfer Learning2020-08-03
Learning the Connections in Direct Feedback Alignment66.78AlexNet (KP)2021-01-01
Striving for Simplicity: The All Convolutional Net✓ Link66.3ACN2014-12-21
Hyperspherical Classification with Dynamic Label-to-Prototype Assignment✓ Link66.22DL2PA (ResNet-32, d=50)2024-03-25
DLME: Deep Local-flatness Manifold Embedding✓ Link66.1DLME (ResNet-18, linear)2022-07-07
FatNet: High Resolution Kernels for Classification Using Fully Convolutional Optical Neural Networks✓ Link66ResNet-18 (modified)2022-10-30
Deeply-Supervised Nets✓ Link65.4DSN2014-09-18
Network In Network✓ Link64.3NiN2013-12-16
Discriminative Transfer Learning with Tree-based Priors63.2Tree Priors2013-12-01
Improving Deep Neural Networks with Probabilistic Maxout Units61.9DNN+Probabilistic Maxout2013-12-20
Maxout Networks✓ Link61.43Maxout Network (k=2)2013-02-18
Unsharp Masking Layer: Injecting Prior Knowledge in Convolutional Networks for Image Classification✓ Link60.36ResNet20+UnsharpMaskLayer2019-09-29
Convolutional Xformers for Vision✓ Link60.11Convolutional Linear Transformer for Vision (CLTV)2022-01-25
FatNet: High Resolution Kernels for Classification Using Fully Convolutional Optical Neural Networks✓ Link60FatNet of ResNet-182022-10-30
FatNet: High Resolution Kernels for Classification Using Fully Convolutional Optical Neural Networks✓ Link60Optical Simulation of FatNet2022-10-30
Empirical Evaluation of Rectified Activations in Convolutional Network✓ Link59.8RReLU2015-05-05
Stochastic Pooling for Regularization of Deep Convolutional Neural Networks✓ Link57.5Stochastic Pooling2013-01-16
How Important is Weight Symmetry in Backpropagation?✓ Link48.75Sign-symmetry2015-10-17
Learning the Connections in Direct Feedback Alignment48.03AlexNet (DFA)2021-01-01
Sharpness-Aware Minimization for Efficiently Improving Generalization✓ Link42.64CNN392020-10-03
Sharpness-Aware Minimization for Efficiently Improving Generalization✓ Link36.07CNN362020-10-03
Sharpness-aware Quantization for Deep Neural Networks✓ Link35.05CNN372021-11-24
Learning the Connections in Direct Feedback Alignment19.49AlexNet (FA)2021-01-01
Efficient Adaptive Ensembling for Image Classification96.808efficient adaptive ensembling2022-06-15
Label Ranker: Self-Aware Preference for Classification Label Position in Visual Masked Self-Supervised Pre-Trained Model✓ Link90.82%Label-Ranker2025-03-03
Performance of Gaussian Mixture Model Classifiers on Embedded Feature Spaces✓ Link91.2DGMMC-S2024-10-17
Check out how to contribute new results. Then edit this file on GitLab or GitHub.