# Self-supervised visual feature extraction

A vision Transformer model trained with DINOv2, optimized with register tokens to enhance attention mechanisms and improve image feature extraction performance

A vision Transformer model trained with DINOv2, optimized with register tokens to enhance attention mechanisms and improve feature extraction capabilities

A compact vision Transformer model trained with DINOv2, utilizing register technology to optimize attention mechanisms and enhance image feature extraction capabilities

An image classification model based on the Vision Transformer architecture, trained on the ImageNet-1k dataset using the DINO self-supervised method.

A self-supervised feature representation model based on ConvNeXt-V2, pre-trained using the Fully Convolutional Masked Autoencoder (FCMAE) framework, suitable for image classification and feature extraction tasks.