OpenCodePapers
object-recognition-on-shape-bias
Object Recognition
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Show papers without code
Paper
Code
shape bias
↕
ModelName
ReleaseDate
↕
Intriguing properties of generative classifiers
✓ Link
98.7
Imagen
2023-09-28
Intriguing properties of generative classifiers
✓ Link
92.7
Stable Diffusion
2023-09-28
Intriguing properties of generative classifiers
✓ Link
91.7
Parti
2023-09-28
Scaling Vision Transformers to 22 Billion Parameters
✓ Link
86.4
ViT-22B-384
2023-02-10
Scaling Vision Transformers to 22 Billion Parameters
✓ Link
83.8
ViT-22B-560
2023-02-10
Learning Transferable Visual Models From Natural Language Supervision
✓ Link
79.9
CLIP (ViT-B)
2021-02-26
Scaling Vision Transformers to 22 Billion Parameters
✓ Link
78.0
ViT-22B-224
2023-02-10
Do Adversarially Robust ImageNet Models Transfer Better?
✓ Link
69.5
ResNet-50 (L2 eps 5.0 adv trained)
2020-07-16
The Origins and Prevalence of Texture Bias in Convolutional Neural Networks
62.2
ResNet-50 (with strong augmentations)
2019-11-20
Billion-scale semi-supervised learning for image classification
✓ Link
49.8
SWSL (ResNeXt-101)
2019-05-02
ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness
✓ Link
42.9
AlexNet
2018-11-29
A Simple Framework for Contrastive Learning of Visual Representations
✓ Link
41.7
SimCLR (ResNet-50x2)
2020-02-13
A Simple Framework for Contrastive Learning of Visual Representations
✓ Link
40.7
SimCLR (ResNet-50x4)
2020-02-13
A Simple Framework for Contrastive Learning of Visual Representations
✓ Link
38.9
SimCLR (ResNet-50x1)
2020-02-13
ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness
✓ Link
31.2
GoogLeNet
2018-11-29
Billion-scale semi-supervised learning for image classification
✓ Link
28.6
SWSL (ResNet-50)
2019-05-02
ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness
✓ Link
22.1
ResNet-50
2018-11-29
ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness
✓ Link
17.2
VGG-16
2018-11-29