MobileViTv2 + DeepLabv3 (shehan97/mobilevitv2-1.0-voc-deeplabv3)

MobileViTv2 model pre-trained on PASCAL VOC at resolution 512x512. It was introduced in Separable Self-attention for Mobile Vision Transformers by Sachin Mehta and Mohammad Rastegari, and first released in this repository. The license used is Apple sample code license .

Disclaimer: The team releasing MobileViT did not write a model card for this model so this model card has been written by the Hugging Face team.

Model Description

MobileViTv2 is constructed by replacing the multi-headed self-attention in MobileViT with separable self-attention.

The model in this repo adds a DeepLabV3 head to the MobileViT backbone for semantic segmentation.

Intended uses & limitations

You can use the raw model for semantic segmentation. See the model hub to look for fine-tuned versions on a task that interests you.

How to use

Here is how to use this model:

from transformers import MobileViTv2FeatureExtractor, MobileViTv2ForSemanticSegmentation
from PIL import Image
import requests

url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(url, stream=True).raw)

feature_extractor = MobileViTv2FeatureExtractor.from_pretrained("shehan97/mobilevitv2-1.0-voc-deeplabv3")
model = MobileViTv2ForSemanticSegmentation.from_pretrained("shehan97/mobilevitv2-1.0-voc-deeplabv3")

inputs = feature_extractor(images=image, return_tensors="pt")

outputs = model(**inputs)
logits = outputs.logits

predicted_mask = logits.argmax(1).squeeze(0)

Currently, both the feature extractor and model support PyTorch.

Training data

The MobileViT + DeepLabV3 model was pretrained on ImageNet-1k , a dataset consisting of 1 million images and 1,000 classes, and then fine-tuned on the PASCAL VOC2012 dataset.

BibTeX entry and citation info

@inproceedings{vision-transformer,
title = {Separable Self-attention for Mobile Vision Transformers},
author = {Sachin Mehta and Mohammad Rastegari},
year = {2022},
URL = {https://arxiv.org/abs/2206.02680}
}