Object Recognition on shape bias

18개 결과 · ⬇ CSV · JSON

shape bias

Rank	Model	shape bias	Paper	Code	Year
1	Imagen	98.7	Intriguing properties of generative classifiers	SamsungSAILMontreal/ForestDiffusion	2023
2	Stable Diffusion	92.7	Intriguing properties of generative classifiers	SamsungSAILMontreal/ForestDiffusion	2023
3	Parti	91.7	Intriguing properties of generative classifiers	SamsungSAILMontreal/ForestDiffusion	2023
4	ViT-22B-384	86.4	Scaling Vision Transformers to 22 Billion Parameters	lucidrains/flash-cosine-sim-attention	2023
5	ViT-22B-560	83.8	Scaling Vision Transformers to 22 Billion Parameters	lucidrains/flash-cosine-sim-attention	2023
6	CLIP (ViT-B)	79.9	Learning Transferable Visual Models From Natural Language Supervision	openai/CLIP · mlfoundations/open_clip · towhee-io/towhee · +79	2021
7	ViT-22B-224	78.0	Scaling Vision Transformers to 22 Billion Parameters	lucidrains/flash-cosine-sim-attention	2023
8	ResNet-50 (L2 eps 5.0 adv trained)	69.5	Do Adversarially Robust ImageNet Models Transfer Better?	MadryLab/robustness · lengstrom/gitlinks	2020
9	ResNet-50 (with strong augmentations)	62.2	The Origins and Prevalence of Texture Bias in Convolutional Neural Networks		2019
10	SWSL (ResNeXt-101)	49.8	Billion-scale semi-supervised learning for image classification	facebookresearch/semi-supervised-ImageNet1K-models · leaderj1001/Billion-scale-semi-supervised-learning · salesforce/ensemble-of-averages · +1	2019
11	AlexNet	42.9	ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness	rgeirhos/texture-vs-shape · rgeirhos/Stylized-ImageNet · LiYingwei/ShapeTextureDebiasedTraining · +4	2018
12	SimCLR (ResNet-50x2)	41.7	A Simple Framework for Contrastive Learning of Visual Representations	tensorflow/models · google-research/simclr · lightly-ai/lightly · +93	2020
13	SimCLR (ResNet-50x4)	40.7	A Simple Framework for Contrastive Learning of Visual Representations	tensorflow/models · google-research/simclr · lightly-ai/lightly · +93	2020
14	SimCLR (ResNet-50x1)	38.9	A Simple Framework for Contrastive Learning of Visual Representations	tensorflow/models · google-research/simclr · lightly-ai/lightly · +93	2020
15	GoogLeNet	31.2	ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness	rgeirhos/texture-vs-shape · rgeirhos/Stylized-ImageNet · LiYingwei/ShapeTextureDebiasedTraining · +4	2018
16	SWSL (ResNet-50)	28.6	Billion-scale semi-supervised learning for image classification	facebookresearch/semi-supervised-ImageNet1K-models · leaderj1001/Billion-scale-semi-supervised-learning · salesforce/ensemble-of-averages · +1	2019
17	ResNet-50	22.1	ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness	rgeirhos/texture-vs-shape · rgeirhos/Stylized-ImageNet · LiYingwei/ShapeTextureDebiasedTraining · +4	2018
18	VGG-16	17.2	ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness	rgeirhos/texture-vs-shape · rgeirhos/Stylized-ImageNet · LiYingwei/ShapeTextureDebiasedTraining · +4	2018