ML Research Wiki / Benchmarks / Image Classification / DTD

DTD

Image Classification Benchmark

Performance Over Time

📊 Showing 11 results | 📏 Metric: Accuracy

Top Performing Models

Rank	Model	Paper	Accuracy	Date	Code
1	Linear FT(ViT-L/14) 📚	Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models	90.00	2023-05-22	📦 gortizji/tangent_task_arithmetic
2	RADAM (ConvNeXt-L) 📚	RADAM: Texture Recognition through Randomized Aggregated Encoding of Deep Activation Maps	84.00	2023-03-08	📦 scabini/RADAM
3	µ2Net+ (ViT-L/16) 📚	A Continual Development Methodology for Large-scale Multitask Dynamic ML Systems	82.23	2022-09-15	📦 google-research/google-research
4	Bamboo (ViT-B/16) 📚	Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy	81.90	2022-03-15	📦 zhangyuanhan-ai/bamboo 📦 davidzhangyuanhan/bamboo
5	µ2Net (ViT-L/16) 📚	An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems	81.00	2022-05-25	📦 google-research/google-research
6	SEER (RegNet10B - linear eval) 📚	Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision	80.50	2022-02-16	📦 facebookresearch/vissl
7	Inceptionv4 📚	Non-binary deep transfer learning for image classification	79.79	2021-07-19	📦 XuyangSHEN/Non-binary-deep-transfer-learning-for-image-classification
8	TWIST (ResNet-50) 📚	Self-Supervised Learning by Estimating Twin Class Distributions	76.60	2021-10-14	📦 bytedance/TWIST 📦 beresandras/contrastive-classification-keras
9	TransBoost-ResNet50 📚	TransBoost: Improving the Best ImageNet Performance using Deep Transduction	76.49	2022-05-26	📦 omerb01/transboost
10	NNCLR 📚	With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations	75.50	2021-04-29	📦 lightly-ai/lightly 📦 keras-team/keras-io 📦 vturrisi/solo-learn 📦 beresandras/contrastive-classification-keras

All Papers (11)

Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models

2023

Linear FT(ViT-L/14)

gortizji/tangent_task_arithmetic

RADAM: Texture Recognition through Randomized Aggregated Encoding of Deep Activation Maps

2023

RADAM (ConvNeXt-L)

scabini/RADAM

A Continual Development Methodology for Large-scale Multitask Dynamic ML Systems

2022

µ2Net+ (ViT-L/16)

google-research/google-research

Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy

2022

Bamboo (ViT-B/16)

zhangyuanhan-ai/bamboo davidzhangyuanhan/bamboo

An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems

2022

µ2Net (ViT-L/16)

google-research/google-research

Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision

2022

SEER (RegNet10B - linear eval)

facebookresearch/vissl

Non-binary deep transfer learning for image classification

2021

Inceptionv4

XuyangSHEN/Non-binary-deep-transfer-learning-for-image-classification

Self-Supervised Learning by Estimating Twin Class Distributions

2021

TWIST (ResNet-50)

bytedance/TWIST beresandras/contrastive-classification-keras

TransBoost: Improving the Best ImageNet Performance using Deep Transduction

2022

TransBoost-ResNet50

omerb01/transboost

With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations

2021

NNCLR

lightly-ai/lightly keras-team/keras-io

Non-binary deep transfer learning for image classification

2021

Inceptionv4 (random initialization)

XuyangSHEN/Non-binary-deep-transfer-learning-for-image-classification

DTD

Performance Over Time

Edit Benchmark Results

Edit Result

Top Performing Models

All Papers (11)

Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models

RADAM: Texture Recognition through Randomized Aggregated Encoding of Deep Activation Maps

A Continual Development Methodology for Large-scale Multitask Dynamic ML Systems

Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy

An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems

Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision

Non-binary deep transfer learning for image classification

Self-Supervised Learning by Estimating Twin Class Distributions

TransBoost: Improving the Best ImageNet Performance using Deep Transduction

With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations

Non-binary deep transfer learning for image classification

Model	Paper	Accuracy	Date
Linear FT(ViT-L/14)	Task Arithmetic in the Tangent Space: Improved Ed…	90.00	2023-05-22
RADAM (ConvNeXt-L)	RADAM: Texture Recognition through Randomized Agg…	84.00	2023-03-08
µ2Net+ (ViT-L/16)	A Continual Development Methodology for Large-sca…	82.23	2022-09-15
Bamboo (ViT-B/16)	Bamboo: Building Mega-Scale Vision Dataset Contin…	81.90	2022-03-15
µ2Net (ViT-L/16)	An Evolutionary Approach to Dynamic Introduction …	81.00	2022-05-25
SEER (RegNet10B - linear eval)	Vision Models Are More Robust And Fair When Pretr…	80.50	2022-02-16
Inceptionv4	Non-binary deep transfer learning for image class…	79.79	2021-07-19
TWIST (ResNet-50)	Self-Supervised Learning by Estimating Twin Class…	76.60	2021-10-14
TransBoost-ResNet50	TransBoost: Improving the Best ImageNet Performan…	76.49	2022-05-26
NNCLR	With a Little Help from My Friends: Nearest-Neigh…	75.50	2021-04-29
Inceptionv4 (random initialization)	Non-binary deep transfer learning for image class…	66.80	2021-07-19