HyperAIHyperAI
StartseiteNeuigkeitenNeueste ForschungsarbeitenTutorialsDatensätzeWikiSOTALLM-ModelleGPU-RanglisteVeranstaltungen
Suche
Über
HyperAIHyperAI

Object Recognition On Shape Bias

Metriken

shape bias

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Modellname
shape bias
Paper TitleRepository
ViT-22B-38486.4Scaling Vision Transformers to 22 Billion Parameters-
ResNet-5022.1ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness-
ViT-22B-56083.8Scaling Vision Transformers to 22 Billion Parameters-
GoogLeNet31.2ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness-
ViT-22B-22478.0Scaling Vision Transformers to 22 Billion Parameters-
CLIP (ViT-B)79.9Learning Transferable Visual Models From Natural Language Supervision-
SWSL (ResNet-50)28.6Billion-scale semi-supervised learning for image classification-
SimCLR (ResNet-50x4)40.7A Simple Framework for Contrastive Learning of Visual Representations-
Parti91.7Intriguing properties of generative classifiers-
VGG-1617.2ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness-
Stable Diffusion92.7Intriguing properties of generative classifiers-
SimCLR (ResNet-50x1)38.9A Simple Framework for Contrastive Learning of Visual Representations-
SWSL (ResNeXt-101)49.8Billion-scale semi-supervised learning for image classification-
ResNet-50 (with strong augmentations)62.2The Origins and Prevalence of Texture Bias in Convolutional Neural Networks-
ResNet-50 (L2 eps 5.0 adv trained)69.5Do Adversarially Robust ImageNet Models Transfer Better?-
SimCLR (ResNet-50x2)41.7A Simple Framework for Contrastive Learning of Visual Representations-
Imagen98.7Intriguing properties of generative classifiers-
AlexNet42.9ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness-
0 of 18 row(s) selected.
Object Recognition On Shape Bias | SOTA | HyperAI