# Visual Feature Extraction

This is the ONNX format version of the facebook/dinov2-base model, suitable for computer vision tasks.

DINOv2 is a visual feature extraction model based on Vision Transformer (ViT), which enhances feature extraction capabilities by introducing register mechanisms.

A visual feature extraction model developed by NVIDIA for generating image embeddings, supporting downstream tasks such as image classification.

DINOv2 is a visual model released by Facebook Research that extracts general visual features through self-supervised learning, suitable for various downstream tasks.

DPT framework using DINOv2 as the backbone network for depth estimation tasks.

This model employs the DPT framework with DINOv2 as the backbone network, focusing on depth estimation tasks.

This is a multi-category image classification model trained using AutoTrain, capable of recognizing various object categories.

CvT-13 is a hybrid architecture model combining convolutional neural networks and vision transformers, pre-trained on the ImageNet-1k dataset, suitable for image classification tasks.

RegNet image classification model trained on ImageNet-1k, featuring an efficient network structure designed through neural architecture search