# Image feature extraction

AIM-v2 is an image encoder model based on the timm library, with a scale of 1 billion parameters, suitable for image feature extraction tasks.

ResNet101 image encoder based on CLIP framework, extracting image features through Global Average Pooling (GAP)

A vision transformer model based on the Transformer architecture, trained using the DINOv2 method and introducing a register mechanism to solve the artifact problem of traditional ViT models.

I-JEPA is a self-supervised learning method that predicts representations of other parts of an image from partial representations, without relying on predefined manual data transformations or pixel-level detail filling.

I-JEPA is a self-supervised learning method that predicts representations of other parts of an image from partial representations, without relying on predefined manual data transformations or pixel-level detail filling.

SSCD is a deep learning model for image copy detection, capable of extracting image features and performing similarity comparisons.

A Vision Transformer (ViT) based image classification model, pretrained on ImageNet-21k by Google Research using JAX framework and later ported to PyTorch. Suitable for feature extraction and fine-tuning scenarios.

EVA02 is a Vision Transformer model pre-trained on ImageNet-22k through masked image modeling, suitable for image classification and feature extraction tasks.

An image feature model based on Vision Transformer (ViT), trained using the self-supervised DINO method, suitable for image classification and feature extraction tasks.

A sketch classifier based on the ResNet-34 architecture, fine-tuned on the TU-Berlin dataset, suitable for sketch recognition and classification tasks.

This Vision Transformer model is pretrained using the MSN method and excels in few-shot scenarios, suitable for tasks like image classification

This Vision Transformer (ViT) model is pretrained on the ImageNet-21k dataset at 224x224 resolution, suitable for image classification tasks.

A Vision Transformer model pretrained on ImageNet-21k, featuring an extra-large architecture suitable for visual tasks like image classification.