Skip to content
ModelListedExternal
Download

DynamicVis

This repository contains the official pretraining weights of the paper DynamicVis: An Efficient and General Visual Foundation Model for Remote Sensing Image Understanding.

KindOtherVersionRevision 0832edf

Model source

Kind
Other
File size
174 MB–1.12 GB
Version
vRevision 0832edf
Updated
Sep 16, 2026
Downloads
0
Source
Hugging Face

Source description

This repository contains the official pretraining weights of the paper DynamicVis: An Efficient and General Visual Foundation Model for Remote Sensing Image Understanding.

Code is available on Github.

Sources

1 source
Hugging FacePrimaryVersion 0832edfbedfd3b9fafcf7f72d54cc29021659cb0
huggingface.co/KyanChen/DynamicVis/tree/0832edfbedfd3b9fafcf7f72d54cc29021659cb0

Verified Sep 16

Model artifacts

8 artifacts

pretrain_dynamicvis_b_bf16_mamba_best_single-label_f1-score_epoch_170.pth

pth · 174 MB · SHA-256 08ab25e4866a…7f91 · Hugging Face

Download

pretrain_dynamicvis_b_bf16_mamba_epoch_200.pth

pth · 492 MB · SHA-256 f625e344edf5…c561 · Hugging Face

Download

pretrain_dynamicvis_b_bf16_mamba_wo_token_reduction_best_single-label_f1-score_epoch_180.pth

pth · 184 MB · SHA-256 c997bac50b77…3e3a · Hugging Face

Download

pretrain_dynamicvis_b_bf16_mamba_wo_token_reduction_epoch_200.pth

pth · 503 MB · SHA-256 7eced7e2e7ab…042d · Hugging Face

Download

pretrain_dynamicvis_l_bf16_mamba_best_single-label_f1-score_epoch_150.pth

pth · 393 MB · SHA-256 e1ca8b1f166d…fd22 · Hugging Face

Download

pretrain_dynamicvis_l_bf16_mamba_epoch_200.pth

pth · 1.11 GB · SHA-256 af589445b3cf…8921 · Hugging Face

Download

pretrain_dynamicvis_l_bf16_mamba_wo_token_reduction_best_single-label_f1-score_epoch_190.pth

pth · 416 MB · SHA-256 824a70e24cb6…ca71 · Hugging Face

Download

pretrain_dynamicvis_l_bf16_mamba_wo_token_reduction_epoch_200.pth

pth · 1.12 GB · SHA-256 d18c46e40808…bfb3 · Hugging Face

Download

Source excerpts

2 excerpts

--- license: apache-2.0 tags: - image-feature-extraction --- This repository contains the official pretraining weights of the paper [**DynamicVis: An Efficient and General Visual Foundation Model for Remote Sensing Image Understanding**](https://huggingface.co/papers/2503.16426). Code is available on [Github](https://github.com/KyanChen/DynamicVis).

Source context: 0 downloads · 1 likes · Pipeline image-feature-extraction · Repo KyanChen/DynamicVis