OpenCodePapers

image-classification-on-omnibenchmark

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.
PaperCodeAverage Top-1 AccuracyModelNameReleaseDate
Neural Prompt Search✓ Link47.6NOAH-ViTB/162022-06-09
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows✓ Link46.4SwinTransformer2021-03-25
Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy✓ Link45.4Bamboo-R502022-03-15
Parameter-Efficient Transfer Learning for NLP✓ Link44.5Adapter-ViTB/162019-02-02
Learning Transferable Visual Models From Natural Language Supervision✓ Link42.1CLIP-RN502021-02-26
Billion-scale semi-supervised learning for image classification✓ Link40.4IG-1B2019-05-02
Big Transfer (BiT): General Visual Representation Learning✓ Link40.4BiT-M2019-12-24
Emerging Properties in Self-Supervised Vision Transformers✓ Link38.9DINO2021-04-29
Unsupervised Learning of Visual Features by Contrasting Cluster Assignments✓ Link38.3SwAV2020-06-17
Deep Residual Learning for Image Recognition✓ Link37.4ResNet-1012015-12-10
MEAL V2: Boosting Vanilla ResNet-50 to 80%+ Top-1 Accuracy on ImageNet without Tricks✓ Link36.6MEAL-V22020-09-17
MoPro: Webly Supervised Learning with Momentum Prototypes✓ Link36.1MoPro-V22020-09-17
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks✓ Link35.8EfficientNetB42019-05-28
Momentum Contrast for Unsupervised Visual Representation Learning✓ Link34.8MoCoV22019-11-13
Deep Residual Learning for Image Recognition✓ Link34.3ResNet-502015-12-10
Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning✓ Link32.3InceptionV42016-02-23
MLP-Mixer: An all-MLP Architecture for Vision✓ Link32.2MLP-Mixer2021-05-04
Manifold Mixup: Better Representations by Interpolating Hidden States✓ Link31.6Manifold2018-06-13
CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features✓ Link31.1CutMix2019-05-13
Re-labeling ImageNet: from Single to Multi-Labels, from Global to Localized Labels✓ Link30.8ReLabel2021-01-13
Masked Autoencoders Are Scalable Vision Learners✓ Link30.6MAE2021-11-11
BEiT: BERT Pre-Training of Image Transformers✓ Link30.1BeiT2021-06-15
Check out how to contribute new results.