| Image Classification |
CIFAR-10 |
ViT-H/14 Percentage correct 99.5 |
An Image is Worth 16x16 Words: Transformers for Image... |
huggingface/transformers +157 |
265 |
Compare |
| Image Generation |
CIFAR-10 |
GMem FID 1.22 |
Generative Modeling with Explicit Memory |
lins-lab/gmem |
78 |
Compare |
| Long-tail Learning |
CIFAR-10-LT (ρ=10) |
GLMC+MaxNorm (ResNet-34, channel x4) Error Rate 5 |
Global and Local Mixture Consistency Cumulative Learning... |
ynu-yangpeng/GLMC +1 |
50 |
Compare |
| Semi-Supervised Image Classification |
CIFAR-10, 4000 Labels |
Semi-SST (ViT-Small) Percentage error 1.41±0.10 |
SST: Self-training with Self-adaptive Thresholding for... |
— |
49 |
Compare |
| Neural Architecture Search |
CIFAR-10 |
NAT-M4 Top-1 Error Rate 1.6% |
Neural Architecture Transfer |
human-analysis/neural-architecture-transfer +1 |
41 |
Compare |
| Image Clustering |
CIFAR-10 |
TURTLE (CLIP + DINOv2) Accuracy 0.995 |
Let Go of Your Labels with Unsupervised Transfer |
mlbio-epfl/turtle |
40 |
Compare |
| Anomaly Detection |
One-class CIFAR-10 |
CLIP (OE) AUROC 99.6 |
Exposing Outlier Exposure: What Can Be Learned From Few,... |
liznerski/eoe |
36 |
Compare |
| Long-tail Learning |
CIFAR-10-LT (ρ=100) |
GLMC+MaxNorm (ResNet-34, channel x4) Error Rate 10.42 |
Global and Local Mixture Consistency Cumulative Learning... |
ynu-yangpeng/GLMC +1 |
28 |
Compare |
| Semi-Supervised Image Classification |
CIFAR-10, 250 Labels |
Semi-SST (ViT-Small) Percentage error 2.42±0.13 |
SST: Self-training with Self-adaptive Thresholding for... |
— |
27 |
Compare |
| Conditional Image Generation |
CIFAR-10 |
EDM-G++ (conditional) FID 1.64 |
Refining Generative Process with Discriminator Guidance... |
alsdudrla10/DG +1 |
25 |
Compare |
| Semi-Supervised Image Classification |
CIFAR-10, 40 Labels |
SemiOccam Percentage error 3.51 |
ViTSGMM: A Robust Semi-Supervised Image Recognition... |
Shu1L0n9/SemiOccam |
21 |
Compare |
| Graph Classification |
CIFAR10 100k |
NeuralWalker Accuracy (%) 80.027 ± 0.185 |
Learning Long Range Dependencies on Graphs via Random Walks |
borgwardtlab/neuralwalker |
20 |
Compare |
| Neural Architecture Search |
CIFAR-10 Image Classification |
NAT-M4 Percentage error 1.6 |
Neural Architecture Transfer |
human-analysis/neural-architecture-transfer +1 |
19 |
Compare |
| Density Estimation |
CIFAR-10 |
i-DODE NLL (bits/dim) 2.42 |
Improved Techniques for Maximum Likelihood Estimation... |
thu-ml/i-dode |
15 |
Compare |
| Out-of-Distribution Detection |
CIFAR-10 vs CIFAR-100 |
DHM AUROC 100 |
Deep Hybrid Models for Out-of-Distribution Detection |
— |
14 |
Compare |
| Out-of-Distribution Detection |
CIFAR-10 |
DHM AUROC 100 |
Deep Hybrid Models for Out-of-Distribution Detection |
— |
10 |
Compare |
| Semi-Supervised Image Classification |
CIFAR-10, 1000 Labels |
MixMatch Accuracy 92.25 |
MixMatch: A Holistic Approach to Semi-Supervised Learning |
google-research/mixmatch +29 |
9 |
Compare |
| Unsupervised Image Classification |
CIFAR-10 |
TURTLE (CLIP + DINOv2) Accuracy 99.5 |
Let Go of Your Labels with Unsupervised Transfer |
mlbio-epfl/turtle |
9 |
Compare |
| Adversarial Defense |
CIFAR-10 |
WRN-28-10 Accuracy 90.03 |
Language Guided Adversarial Purification |
Visual-Conception-Group/LGAP |
8 |
Compare |
| Active Learning |
CIFAR10 (10,000) |
TypiClust Accuracy 93.2 |
Active Learning on a Budget: Opposite Strategies Suit... |
avihu111/typiclust |
7 |
Compare |
| Personalized Federated Learning |
CIFAR-10 |
pFedHN-PC ACC@1-10Clients 92.47 |
Personalized Federated Learning using Hypernetworks |
KarhouTam/FL-bench +1 |
7 |
Compare |
| Sequential Image Classification |
noise padded CIFAR-10 |
FlexTCN-6 % Test Accuracy 69.87% |
FlexConv: Continuous Kernel Convolutions with... |
rjbruin/flexconv |
7 |
Compare |
| Adversarial Attack |
CIFAR-10 |
Xu et al. Attack: PGD20 78.680 |
An Orthogonal Classifier for Improving the Adversarial... |
MTandHJ/roboc |
6 |
Compare |
| Anomaly Detection |
Leave-One-Class-Out CIFAR-10 |
BCE-CLIP AUROC 98.4 |
Exposing Outlier Exposure: What Can Be Learned From Few,... |
liznerski/eoe |
6 |
Compare |
| Small Data Image Classification |
CIFAR-10, 500 Labels |
ChimeraMix+AutoAugment Accuracy (%) 70.09 |
ChimeraMix: Image Classification on Small Datasets via... |
creinders/chimeramix |
6 |
Compare |
| Stochastic Optimization |
CIFAR-10 WRN-28-10 - 200 Epochs |
Adam (eps-adjusted) Accuracy 96.36 |
Domain-independent Dominance of Adaptive Methods |
lolemacs/avagrad |
6 |
Compare |
| Unsupervised Anomaly Detection with Specified Settings -- 1% anomaly |
CIFAR-10 |
LVAD AUC-ROC 0.940 |
Locally varying distance transform for unsupervised... |
wen-yan-lin/LVAD-Locally-Varying-Anomaly-Detection |
6 |
Compare |
| Unsupervised Anomaly Detection with Specified Settings -- 10% anomaly |
CIFAR-10 |
LVAD AUC-ROC 0.903 |
Locally varying distance transform for unsupervised... |
wen-yan-lin/LVAD-Locally-Varying-Anomaly-Detection |
6 |
Compare |
| Unsupervised Anomaly Detection with Specified Settings -- 20% anomaly |
cifar10 |
Shell-Renormalized AUC-ROC 0.896 |
Shell Theory: A Statistical Model of Reality |
wen-yan-lin/shell-theory |
6 |
Compare |
| Unsupervised Anomaly Detection with Specified Settings -- 30% anomaly |
CIFAR-10 |
Shell-Renormalized AUC-ROC 0.894 |
Shell Theory: A Statistical Model of Reality |
wen-yan-lin/shell-theory |
6 |
Compare |
| Unsupervised Anomaly Detection with Specified Settings -- 0.1% anomaly |
CIFAR-10 |
LVAD AUC-ROC 0.930 |
Locally varying distance transform for unsupervised... |
wen-yan-lin/LVAD-Locally-Varying-Anomaly-Detection |
6 |
Compare |
| Adversarial Robustness |
CIFAR-10 |
Mixed classifier Accuracy 95.23 |
Improving the Accuracy-Robustness Trade-Off of... |
codelion/adaptive-classifier +1 |
5 |
Compare |
| Data Augmentation |
CIFAR-10 |
Shake-Shake (26 2×96d) (Faster AA) Percentage error 2 |
Faster AutoAugment: Learning Augmentation Strategies... |
moskomule/dda |
5 |
Compare |
| Neural Architecture Search |
NATS-Bench Size, CIFAR-10 |
GreenMachine-3 Kendall's Tau 0.888 |
GreenMachine: Automatic Design of Zero-Cost Proxies for... |
RodriguesGabriel/greenmachine |
5 |
Compare |
| Neural Network Compression |
CIFAR-10 |
ShuffleNet – Quantised Size (MB) 1.9 |
Quantisation and Pruning for Neural Network Compression... |
kpaupamah/compression-and-regularisation |
5 |
Compare |
| Open-World Semi-Supervised Learning |
CIFAR-10 |
OpenLDN (ResNet-18) All accuracy (10% Labeled) 92.8 |
OpenLDN: Learning to Discover Novel Classes for... |
nayeemrizve/openldn |
5 |
Compare |
| Small Data Image Classification |
CIFAR-10, 100 Labels |
ChimeraMix+AutoAugment Accuracy (%) 49.75 |
ChimeraMix: Image Classification on Small Datasets via... |
creinders/chimeramix |
5 |
Compare |
| Small Data Image Classification |
CIFAR-10, 1000 Labels |
ChimeraMix+AutoAugment Accuracy (%) 76.76 |
ChimeraMix: Image Classification on Small Datasets via... |
creinders/chimeramix |
5 |
Compare |
| Image Classification |
CIFAR-10 (with noisy labels) |
SSR Accuracy (under 20% Sym. label noise) 96.74% |
SSR: An Efficient and Robust Framework for Learning with... |
MrChenFeng/SSR_BMVC2022 |
4 |
Compare |
| Network Pruning |
CIFAR-10 |
TAS-pruned ResNet-110 Accuracy 94.33 |
Network Pruning via Transformable Architecture Search |
D-X-Y/GDAS +3 |
4 |
Compare |
| Provable Adversarial Defense |
CIFAR-10 |
SLL X-Large Accuracy 70.3 |
A Unified Algebraic Perspective on Lipschitz Neural Networks |
araujoalexandre/lipschitz-sll-networks |
4 |
Compare |
| Semi-Supervised Image Classification |
cifar10, 250 Labels |
ReMixMatch Percentage correct 93.73 |
ReMixMatch: Semi-Supervised Learning with Distribution... |
google-research/mixmatch +2 |
4 |
Compare |
| Semi-Supervised Image Classification |
CIFAR-10, 2000 Labels |
MixMatch Accuracy 92.97 |
MixMatch: A Holistic Approach to Semi-Supervised Learning |
google-research/mixmatch +29 |
4 |
Compare |
| Stochastic Optimization |
CIFAR-10 ResNet-18 - 200 Epochs |
SGD - cosine LR schedule Accuracy 95.55 |
Benchopt: Reproducible, efficient and collaborative... |
deepmind/optax +2 |
4 |
Compare |
| Data Free Quantization |
CIFAR10 |
ResNet-20 CIFAR-10 CIFAR-10 W4A4 Top-1 Accuracy 91.26 |
Qimera: Data-free Quantization with Synthetic Boundary... |
iamkanghyunchoi/qimera +1 |
3 |
Compare |
| Image Generation |
CIFAR-10 (10% data) |
DiffAugment-StyleGAN2 FID 14.5 |
Differentiable Augmentation for Data-Efficient GAN Training |
POSTECH-CVLab/PyTorch-StudioGAN +12 |
3 |
Compare |
| Image Generation |
CIFAR-10 (20% data) |
DiffAugment-StyleGAN2 FID 12.15 |
Differentiable Augmentation for Data-Efficient GAN Training |
POSTECH-CVLab/PyTorch-StudioGAN +12 |
3 |
Compare |
| Online Clustering |
cifar10 |
OHC online NMI 10.5 |
Hard Regularization to Prevent Deep Online Clustering... |
lou1sm/online_hard_clustering |
3 |
Compare |
| Semi-Supervised Image Classification |
CIFAR-10, 20 Labels |
MutexMatch (k=0.6C) Percentage error 7.77 |
MutexMatch: Semi-Supervised Learning with Mutex-Based... |
NJUyued/MutexMatch4SSL |
3 |
Compare |
| Semi-Supervised Image Classification |
cifar-10, 10 Labels |
BOSS Accuracy (Test) 95.1 |
Building One-Shot Semi-supervised (BOSS) Learning up to... |
lnsmith54/BOSS |
3 |
Compare |
| Supervised Image Retrieval |
CIFAR-10 |
SSB-VAE Precision@100 0.910 |
Self-Supervised Bernoulli Autoencoders for... |
amacaluso/SSB-VAE |
3 |
Compare |
| Image Classification |
CIFAR-10, 40% Symmetric Noise |
FaMUS Percentage correct 95.37 |
Faster Meta Update Strategy for Noise-Robust Deep Learning |
youjiangxu/FaMUS |
2 |
Compare |
| Image Classification |
CIFAR-10, 60% Symmetric Noise |
MentorMix Percentage correct 91.3 |
Faster Meta Update Strategy for Noise-Robust Deep Learning |
youjiangxu/FaMUS |
2 |
Compare |
| Image Classification |
CIFAR-10 Image Classification |
ASF-former-S Params 19.3M |
Adaptive Split-Fusion Transformer |
szx503045266/asf-former |
2 |
Compare |
| Nature-Inspired Optimization Algorithm |
CIFAR-10 |
Position-wise optimizer training time (s) 23 |
Position-wise optimizer: A nature-inspired optimization algorithm |
— |
2 |
Compare |
| Quantization |
CIFAR-10 |
3DCNN_VIVA_3 MAP 160327.04 |
Compressing 3DCNNs Based on Tensor Train Decomposition |
— |
2 |
Compare |
| Self-Supervised Learning |
cifar10 |
ResNet50 average top-1 classification accuracy 93.89 |
Guarding Barlow Twins Against Overfitting with Mixed Samples |
wgcban/mix-bt |
2 |
Compare |
| Semi-Supervised Image Classification (Cold Start) |
CIFAR-10, 100 Labels |
SimCLR-kmediods-PAWS Percentage error 6.1 |
Cold PAWS: Unsupervised class discovery and addressing... |
emannix/cold-paws-simclr-and-paws-semi-supervised-learning +1 |
2 |
Compare |
| Semi-Supervised Image Classification |
CIFAR-10, 80 Labels |
MutexMatch (k=0.6C) Percentage error 5 |
MutexMatch: Semi-Supervised Learning with Mutex-Based... |
NJUyued/MutexMatch4SSL |
2 |
Compare |
| Small Data Image Classification |
cifar10, 10 labels |
VAE % Test Accuracy 45.96% |
Performance Analysis of Semi-supervised Learning in the... |
varunmannam/Papers_with_Code |
2 |
Compare |
| Stochastic Optimization |
CIFAR-10 |
Resnet18 Accuracy (max) 86.85 |
Mixing ADAM and SGD: a Combined Optimization Method |
gitlab.com/nicolalandro/multi_optimizer |
2 |
Compare |
| Zero-Shot Learning |
CIFAR-10 |
ZLaP* Accuracy 93.6 |
Label Propagation for Zero-shot Classification with... |
vladan-stojnic/zlap |
2 |
Compare |
| Anomaly Detection |
CIFAR-10 |
RCALAD Mean AUC 65.7 |
Spot The Odd One Out: Regularized Complete Cycle... |
zahradehghanian97/rcalad |
1 |
Compare |
| Continual Learning |
Split CIFAR-10 (5 tasks) |
H² Top 1 Accuracy % 97.3 |
Helpful or Harmful: Inter-Task Association in Continual Learning |
Jin0316/Helpful-or-Harmful-Inter-Task-Association |
1 |
Compare |
| Contrastive Learning |
CIFAR-10 |
IPCL (ResNet18) Accuracy (Top-1) 84.77 |
IPCL: Iterative Pseudo-Supervised Contrastive Learning... |
SonalKumar95/IPCL |
1 |
Compare |
| Density Estimation |
CIFAR-10 (Conditional) |
MAF Log-likelihood 5872 |
Masked Autoregressive Flow for Density Estimation |
tensorflow/probability +20 |
1 |
Compare |
| Graph Classification |
CIFAR-10 |
CKGCN Accuracy 72.785 |
CKGConv: General Graph Convolution with Continuous Kernels |
networkslab/ckgconv |
1 |
Compare |
| Image Classification |
cifar-10,4000 |
WRN-28-2 + UDA+AutoDropout Percentage error 4.2 |
AutoDropout: Learning Dropout Patterns to Regularize... |
google-research/google-research |
1 |
Compare |
| Image Classification |
cifar10 |
SAM Accuracy 0.9672 |
— |
— |
1 |
Compare |
| Image Compression |
CIFAR-10 |
Lossyless Compressor Bit rate 1410 |
Lossy Compression for Lossless Prediction |
YannDubs/lossyless |
1 |
Compare |
| Image Retrieval |
CIFAR-10 |
Custom: 3 conv + 2 fcn Average-mAP 0.6755 |
Deep Supervised Hashing for Fast Image Retrieval |
bgswaroop/deep-hashing |
1 |
Compare |
| Learning with noisy labels |
CIFAR-10 |
InstanceGM Test Accuracy 95.9 |
Instance-Dependent Noisy Label Learning via Graphical Modelling |
arpit2412/InstanceGM |
1 |
Compare |
| Novel Class Discovery |
cifar10 |
AutoNovel Clustering Accuracy 0.924 |
AutoNovel: Automatically Discovering and Learning Novel... |
k-han/AutoNovel |
1 |
Compare |
| Out-of-Distribution Detection |
CIFAR10 |
Wide ResNet 40x2 AUROC 99.3 |
RODD: A Self-Supervised Approach for Robust... |
UmarKhalidcs/RODD |
1 |
Compare |
| Out-of-Distribution Detection |
cifar10 |
Wideresnet 40 AUROC 99.3 |
RODD: A Self-Supervised Approach for Robust... |
UmarKhalidcs/RODD |
1 |
Compare |
| Out of Distribution (OOD) Detection |
CIFAR-10 |
ZClassifier AUCROC 0.9994 |
ZClassifier: Temperature Tuning and Manifold... |
ShimSoonYong/ZClassifier |
1 |
Compare |
| Parameter Prediction |
CIFAR10 |
GHN-2 Classification Accuracy (BN-free) 36.8 |
Parameter Prediction for Unseen Deep Architectures |
facebookresearch/ppuda |
1 |
Compare |
| Partial Label Learning |
CIFAR-10 (partial ratio 0.1) |
ILL Accuracy 96.37 |
Imprecise Label Learning: A Unified Framework for... |
hhhhhhao/general-framework-weak-supervision |
1 |
Compare |
| Partial Label Learning |
CIFAR-10 (partial ratio 0.3) |
ILL Accuracy 96.26 |
Imprecise Label Learning: A Unified Framework for... |
hhhhhhao/general-framework-weak-supervision |
1 |
Compare |
| Partial Label Learning |
CIFAR-10 (partial ratio 0.5) |
ILL Accuracy 95.91 |
Imprecise Label Learning: A Unified Framework for... |
hhhhhhao/general-framework-weak-supervision |
1 |
Compare |
| Representation Learning |
CIFAR10 |
Resnet 18 Accuracy (%) 97.05 |
AlignMixup: Improving Representations By Interpolating... |
Westlake-AI/openmixup +1 |
1 |
Compare |
| Self-Supervised Learning |
CIFAR-10 |
CorInfomax (ResNet18) Top-1 Accuracy 93.18 |
Self-Supervised Learning with an Information... |
serdarozsoy/corinfomax-ssl |
1 |
Compare |
| Semi-Supervised Image Classification (Cold Start) |
CIFAR-10, 30 Labels |
SimCLR-kmediods-PAWS Percentage error 6.4 |
Cold PAWS: Unsupervised class discovery and addressing... |
emannix/cold-paws-simclr-and-paws-semi-supervised-learning +1 |
1 |
Compare |
| Semi-Supervised Image Classification (Cold Start) |
CIFAR-10, 40 Labels |
FixMatch-USL-T Percentage error 6.5 |
Unsupervised Selective Labeling for More Effective... |
TonyLianLong/UnsupervisedSelectiveLabeling |
1 |
Compare |
| Semi-Supervised Image Classification |
CIFAR-10, 500 Labels |
MixMatch Accuracy 91.35 |
MixMatch: A Holistic Approach to Semi-Supervised Learning |
google-research/mixmatch +29 |
1 |
Compare |
| Semi-Supervised Image Classification |
CIFAR-10, 100 Labels |
SimCLR-kmediods-PAWS Percentage error 6.1 |
Cold PAWS: Unsupervised class discovery and addressing... |
emannix/cold-paws-simclr-and-paws-semi-supervised-learning +1 |
1 |
Compare |
| Semi-Supervised Image Classification |
CIFAR-10, 30 Labels |
SimCLR-kmediods-PAWS Percentage error 6.4 |
Cold PAWS: Unsupervised class discovery and addressing... |
emannix/cold-paws-simclr-and-paws-semi-supervised-learning +1 |
1 |
Compare |
| Small Data Image Classification |
CIFAR-10, 250 Labels |
GLICO Top-1 accuracy % 43 |
Generative Latent Implicit Conditional Optimization when... |
IdanAzuri/glico-learning-small-sample |
1 |
Compare |
| Transductive Zero-Shot Classification |
CIFAR-10 |
ZLaP Accuracy 93.6 |
Label Propagation for Zero-shot Classification with... |
vladan-stojnic/zlap |
1 |
Compare |
| Classification |
cifar10 |
no rows |
— |
— |
0 |
Compare |
| Semi-Supervised Image Classification |
CIFAR-10, 40 Labels |
no rows |
— |
— |
0 |
Compare |