D

Dino Vits16

Developed by facebook
A self-supervised Vision Transformer model trained using the DINO method, suitable for image feature extraction
Downloads 47.32k
Release Time : 3/2/2022

Model Overview

This Vision Transformer model is pre-trained on the ImageNet-1k dataset in a self-supervised manner and can extract image features for downstream tasks

Model Features

Self-supervised learning
Trained using the DINO method for self-supervision, eliminating the need for manual data labeling
Image patch processing
Processes images by dividing them into 16x16 pixel patches
General feature extraction
Learned image representations can be transferred to various downstream vision tasks

Model Capabilities

Image feature extraction
Base model for image classification
Visual representation learning

Use Cases

Computer vision
Image classification
Fine-tune by adding a classification head on top of the pre-trained model
Object detection
Used as a feature extractor for object detection tasks
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase