DeepGlint-AI/mlcd-vit-base-patch32-224

Model

2

stars

7

commits

1

linked in READMEs

Nov 4, 2024

updated

clip_vision_model
safetensors

README

[Paper] [GitHub]

This model is trained using the COYO700M dataset. The results below are from linear probe evaluations, demonstrating the model's performance on various benchmarks.

DatasetCLIPMLCD
Food10188.890.2
CIFAR1095.196.9
CIFAR10080.586.8
Birdsnap58.572.1
SUN39776.677.4
Cars81.893.5
Aircraft52.074.7
VOC200787.790.4
DTD76.583.5
Pets90.093.6
Cal10193.097.7
Flowers96.998.8
ImageNet76.179.1

Contributors

xiangan

7 commits

DeepGlint-AI/mlcd-vit-base-patch32-224

Model

2

stars

7

commits

1

linked in READMEs

Nov 4, 2024

updated

clip_vision_model
safetensors

README

[Paper] [GitHub]

This model is trained using the COYO700M dataset. The results below are from linear probe evaluations, demonstrating the model's performance on various benchmarks.

DatasetCLIPMLCD
Food10188.890.2
CIFAR1095.196.9
CIFAR10080.586.8
Birdsnap58.572.1
SUN39776.677.4
Cars81.893.5
Aircraft52.074.7
VOC200787.790.4
DTD76.583.5
Pets90.093.6
Cal10193.097.7
Flowers96.998.8
ImageNet76.179.1

Contributors

xiangan

7 commits