tanganke
/

clip-vit-large-patch14_TA8_mtl

clip_vision_model

Model card Files Files and versions

Model Card

Table: Accuracy on test datasets.

Method	SUN397	Cars	RESISC45	EuroSAT	SVHN	GTSRB	MNIST	DTD	Average
Traditional MTL	79.0	89.3	94.5	98.4	96.4	98.1	99.4	83.7	92.4

Downloads last month: 10

Safetensors

Model size

0.3B params

Tensor type

F32

·

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for tanganke/clip-vit-large-patch14_TA8_mtl

Base model

openai/clip-vit-large-patch14

Finetuned

(119)

this model

Datasets used to train tanganke/clip-vit-large-patch14_TA8_mtl

Collection including tanganke/clip-vit-large-patch14_TA8_mtl

CLIP-ViT-L/14 on the eight image classification tasks

if you find these models helpful, consider citing [our paper](https://arxiv.org/abs/2406.03280) • 9 items • Updated Aug 27, 2024