# Unsupervised Learning

This model reveals the potential of Vision Transformer (ViT) in image segmentation tasks by transforming ViT into an efficient image segmentation model through specific methods.

ChronoDepth is a temporally consistent video depth learning method based on video diffusion priors, capable of learning and predicting depth information from videos.

DUSt3R is a deep learning model for generating 3D geometric models from images, capable of easily handling geometric 3D vision tasks.

DUSt3R is a model for easily achieving geometric 3D vision from images, capable of reconstructing 3D scenes from single or multiple images.

DPT framework using DINOv2 as the backbone network for depth estimation tasks.

This model employs the DPT framework with DINOv2 as the backbone network, focusing on depth estimation tasks.

A DPT model using DINOv2 as the backbone network for depth estimation tasks.

UMT5 is a multilingual text generation model pretrained on the mC4 multilingual corpus, supporting 107 languages and optimized for language balance using the UniMax sampling strategy

A multilingual text generation model pretrained on the mC4 multilingual corpus, supporting 107 languages

A unified multilingual T5 model pre-trained on the mC4 multilingual corpus, covering 107 languages

This is a sentence embedding model based on sentence-transformers, capable of mapping sentences and paragraphs into a 768-dimensional vector space, suitable for tasks such as sentence similarity calculation and semantic search.

A sentence embedding model based on ConGen, capable of mapping sentences to a 312-dimensional vector space, suitable for tasks like semantic search.

SimeCSE_Vietnamese is a Vietnamese sentence embedding model based on SimCSE, using PhoBERT as the pretrained language model, suitable for both unlabeled and labeled data.

BiMeanVAE is a model based on Variational Autoencoder (VAE), primarily used for text summarization tasks.

Chinese GPT2-distil model, pretrained on CLUECorpusSmall dataset, suitable for Chinese text generation tasks