# Zero-Shot Classification

Based on the OpenCLIP-ViT-L-14 model, the Test-Time Register technology is introduced to improve the model's interpretability and the performance of downstream tasks.

A vision-language model fine-tuned from openai/clip-vit-large-patch14, trained for 10 epochs

Git-RSCLIP is a vision-language model pretrained on the Git-10M dataset, specializing in multimodal understanding of remote sensing images.

A CLIP-ViT model optimized for image geolocation recognition, fine-tuned for continent-level queries.

GIT is a dual-conditional Transformer decoder based on CLIP image tokens and text tokens, designed for image-to-text generation tasks.

The first open-source Chinese CLIP model, pre-trained on 123 million image-text pairs, with RoBERTa-large architecture as the text encoder.

Japanese CLOOB (Contrastive Leave-One-Out Boost) model trained by rinna Co., Ltd. for cross-modal understanding of images and text