# High-dimensional feature extraction

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

MegaDescriptor-L-224 is an image feature model based on the Swin-L architecture, designed specifically for animal re-identification tasks, and pre-trained by Supervisely on animal re-identification datasets.

A Vision Transformer (ViT) image feature model with registers, pre-trained using 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.