# Self-supervised visual features

ONNX format version of DINOv2-small, suitable for vision tasks

A vision Transformer (ViT)-based image feature model, pre-trained on the LVD-142M dataset using the self-supervised DINOv2 method.

A vision Transformer model trained with DINOv2, improved by adding register tokens to enhance attention mechanism, eliminate artifacts, and boost performance

DINOv2 is a visual feature extraction model developed by Facebook Research team, achieving powerful image representation capabilities through self-supervised learning.

DINOv2 is a self-supervised visual feature extraction model developed by Facebook Research, capable of generating robust visual feature representations.

DINOv2 is a visual feature extraction model developed by Facebook Research that generates robust visual features without supervised learning.

A visual Transformer (ViT) image feature model with registers, pre-trained using the self-supervised DINOv2 method on the LVD-142M dataset.

A Vision Transformer (ViT) image feature model with registers, pre-trained using self-supervised DINOv2 method on the LVD-142M dataset.

A vision Transformer (ViT) image feature model with registers, pretrained using the self-supervised DINOv2 method on the LVD-142M dataset.

A visual transformer (ViT) image feature model with registers, pre-trained using the self-supervised DINOv2 method on the LVD-142M dataset.

A small vision Transformer model trained using the DINOv2 method, suitable for image feature extraction and classification tasks

A small-scale vision Transformer model trained using the DINOv2 method, extracting image features through self-supervised learning

A vision Transformer model trained using the DINOv2 method for self-supervised image feature extraction

A vision Transformer model trained using the DINOv2 method, extracting robust visual features from massive image data through self-supervised learning

Vision Transformer model trained using the DINOv2 method, extracting image features through self-supervised learning

A vision Transformer (ViT)-based image feature model pre-trained using self-supervised DINOv2 method on the LVD-142M dataset

A self-supervised image feature model based on Vision Transformer (ViT), pre-trained using the DINOv2 method on the LVD-142M dataset, suitable for image classification and feature extraction tasks.

A giant vision Transformer (ViT)-based image feature extraction model, pre-trained using self-supervised DINOv2 method on the LVD-142M dataset

A Vision Transformer (ViT)-based image feature model, pre-trained using self-supervised DINOv2 method on the LVD-142M dataset

Large-scale image feature extraction model based on Vision Transformer (ViT), pre-trained on ImageNet-1k dataset using self-supervised Masked Autoencoder (MAE) method

Vision Transformer (ViT) based image feature extraction model, pre-trained on ImageNet-1k dataset using self-supervised masked autoencoder (MAE) method