tanganke
/

clip-vit-base-patch32_TA8_mtl

clip_vision_model

Model card Files Files and versions Community

Edit model card

Model Card

Table: Accuracy on test datasets.

Method	SUN397	Cars	RESISC45	EuroSAT	SVHN	GTSRB	MNIST	DTD	Average
Traditional MTL	72.3	76.6	92.2	97.9	95.5	97.7	99.3	77.7	88.6

Downloads last month: 2

Safetensors

Model size

87.5M params

Tensor type

F32

·

Inference API

Unable to determine this model's library. Check the docs .

Model tree for tanganke/clip-vit-base-patch32_TA8_mtl

Base model

openai/clip-vit-base-patch32

Finetuned

(42)

this model

Datasets used to train tanganke/clip-vit-base-patch32_TA8_mtl

Collection including tanganke/clip-vit-base-patch32_TA8_mtl

CLIP-ViT-B/32 on the eight image classication tasks

if you find these models helpful, consider citing [our paper](https://arxiv.org/abs/2406.03280) • 9 items • Updated Aug 27