MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining

Di Wang, Jing Zhang, Minqiang Xu, Lin Liu, Dongsheng Wang, Erzhong Gao, Chengxi Han, Haonan Guo, Bo Du,
Dacheng Tao and Liangpei Zhang

Update | Overview | Datasets and Models | Usage | Statement

🚩 Current applications

Remote Sensing Related Works: Please see Remote Sensing;

Remote Sensing Supervised Pretraining Foundation Model: Please see RSP;

100M-parameter Remote Sensing Unsupervised Pretraining Foundation Model: Please see RVSA;

Large-Scale RS Segmentation Pretraining Dataset: Please see SAMRS;

Other applications: ViTAE | VSA | QFormer | ViTPose | Matting | Scene Text Spotting | Video Object Segmentation

🔥 Update

2024.05.24

Accepted by IEEE JSTARS Special issue on "Large-Scale Pretraining for Interpretation Promotion in Remote Sensing Domain"

2024.03.30

The codes, configs and logs are released!

2024.03.29

The change detection finetuned models are released!

2024.03.29

The semantic segmentation finetuned models are released!

2024.03.28

The rotated object detection finetuned models are released!

2024.03.28

The horizontal object detection finetuned models are released!

2024.03.27

The scene classification finetuned models are released!

2024.03.26

The pretrained models are released!

2024.03.25

The SOTA-RBB set of the pretraining dataset is uploaded to OneDrive and Baidu!

2024.03.21

The paper is post on arxiv!

🌞 Overview

This is the official repository of the paper: MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining

Figure 1: The overall pipeline of MTP.

In this study, we explore the Multi-Task Pretraining (MTP) paradigm for RS foundation models. Using a shared encoder and task-specific decoder architecture, we conduct multi-task supervised pretraining on the SAMRS dataset, encompassing semantic segmentation, instance segmentation, and rotated object detection. MTP supports both convolutional neural networks and vision transformer foundation models with over 300 million parameters. The pretrained models are finetuned on various RS downstream tasks, such as scene classification, horizontal and rotated object detection, semantic segmentation, and change detection. We hope this research encourages further exploration of RS foundation models and anticipate the widespread application of these models across diverse fields of RS image interpretation.

📖 Datasets and Models

Pretraining Dataset

We clip the DOTA-2.0 rotated bounding box version and produce the segmentation label by SAM, obtaining SOTA-RBB. (original SAMRS uses DOTA-2.0 horizontal bounding box version)

SOTA-RBB and the SIOR and FAST of original SAMRS is together used for implementing MTP.

We have uploaded SOTA-RBB to OneDive and Baidu.

Pretrained Models

Pretrain	Pretraining Dataset	Backbone	Backbone Weights	Model Weights
MAE	Million-AID	ViT-L	Baidu & OneDrive	-
MAE + MTP	SAMRS	ViT-B+RVSA	Baidu & OneDrive	Baidu & OneDrive
MAE + MTP	SAMRS	ViT-L+RVSA	Baidu & OneDrive	Baidu & OneDrive
IMP + MTP	SAMRS	InternImage-XL	Baidu & OneDrive	Baidu & OneDrive

Finetuned Models

Scene Classification

Pretrain	Dataset	Backbone	OA	Config	Log	Weights
MAE + MTP	EuroSAT	ViT-B＋RVSA	98.76	Config	Log	Baidu & OneDrive
MAE + MTP	EuroSAT	ViT-L＋RVSA	98.78	Config	Log	Baidu & OneDrive
IMP + MTP	EuroSAT	InternImage-XL	99.24	Config	Log	Baidu & OneDrive
MAE + MTP	RESISC-45	ViT-B＋RVSA	95.57	Config	Log	Baidu & OneDrive
MAE + MTP	RESISC-45	ViT-L＋RVSA	95.88	Config	Log	Baidu & OneDrive
IMP + MTP	RESISC-45	InternImage-XL	96.27	Config	Log	Baidu & OneDrive

Horizontal Object Detection

Pretrain	Dataset	Backbone	Method	AP50	Config	Log	Weights
MAE + MTP	Xview	ViT-B＋RVSA	RetinaNet	16.40	Config	Log	Baidu & OneDrive
MAE + MTP	Xview	ViT-L＋RVSA	RetinaNet	19.40	Config	Log	Baidu & OneDrive
IMP + MTP	Xview	InternImage-XL	RetinaNet	18.20	Config	Log	Baidu & OneDrive
MAE + MTP	DIOR	ViT-B＋RVSA	Faster-RCNN	79.00	Config	Log	Baidu & OneDrive
MAE + MTP	DIOR	ViT-L＋RVSA	Faster-RCNN	81.70	Config	Log	Baidu & OneDrive
IMP + MTP	DIOR	InternImage-XL	Faster-RCNN	78.30	Config	Log	Baidu & OneDrive

Rotated Object Detection (SLURM part)

Pretrain	Dataset	Backbone	Method	mAP	Config	Log	Weights
MAE + MTP	DIOR-R	ViT-B＋RVSA	Oriented-RCNN	71.29	Config	Log	Baidu & OneDrive
MAE + MTP	DIOR-R	ViT-L＋RVSA	Oriented-RCNN	74.54	Config	Log	Baidu & OneDrive
IMP + MTP	DIOR-R	InternImage-XL	Oriented-RCNN	72.17	Config	Log	Baidu & OneDrive
MAE + MTP	FAIR1M-2.0	ViT-B＋RVSA	Oriented-RCNN	51.92	Config	Log	Baidu & OneDrive
MAE + MTP	FAIR1M-2.0	ViT-L＋RVSA	Oriented-RCNN	53.00	Config	Log	Baidu & OneDrive
IMP + MTP	FAIR1M-2.0	InternImage-XL	Oriented-RCNN	50.93	Config	Log	Baidu & OneDrive

Semantic Segmentation

Pretrain	Dataset	Backbone	Method	mIOU	Config	Log	Weights
MAE + MTP	SpaceNetv1	ViT-B＋RVSA	UperNet	79.63	Config	Log	Baidu & OneDrive
MAE + MTP	SpaceNetv1	ViT-L＋RVSA	UperNet	79.54	Config	Log	Baidu & OneDrive
IMP + MTP	SpaceNetv1	InternImage-XL	UperNet	79.16	Config	Log	Baidu & OneDrive
MAE + MTP	LoveDA	ViT-B＋RVSA	UperNet	52.39	Config	Log	Baidu & OneDrive
MAE + MTP	LoveDA	ViT-L＋RVSA	UperNet	54.17	Config	Log	Baidu & OneDrive
IMP + MTP	LoveDA	InternImage-XL	UperNet	54.17	Config	Log	Baidu & OneDrive

Change Detection

Pretrain	Dataset	Backbone	Method	F1	Config	Log	Weights
MAE + MTP	OSCD	ViT-B＋RVSA	UNet	53.36	Config	Log	Baidu & OneDrive
MAE + MTP	OSCD	ViT-L＋RVSA	UNet	55.92	Config	Log	Baidu & OneDrive
IMP + MTP	OSCD	InternImage-XL	UNet	55.61	Config	Log	Baidu & OneDrive
MAE + MTP	WHU	ViT-B＋RVSA	UNet	94.32	Config	Log	Baidu & OneDrive
MAE + MTP	WHU	ViT-L＋RVSA	UNet	94.75	Config	Log	Baidu & OneDrive
IMP + MTP	WHU	InternImage-XL	UNet	95.59	Config	Log	Baidu & OneDrive
MAE + MTP	LEVIR	ViT-B＋RVSA	UNet	92.22	Config	Log	Baidu & OneDrive
MAE + MTP	LEVIR	ViT-L＋RVSA	UNet	92.67	Config	Log	Baidu & OneDrive
IMP + MTP	LEVIR	InternImage-XL	UNet	92.54	Config	Log	Baidu & OneDrive
MAE + MTP	SVCD/CDD	ViT-B＋RVSA	UNet	97.87	Config	Log	Baidu & OneDrive
MAE + MTP	SVCD/CDD	ViT-L＋RVSA	UNet	97.98	Config	Log	Baidu & OneDrive
IMP + MTP	SVCD/CDD	InternImage-XL	UNet	98.33	Config	Log	Baidu & OneDrive

🔧 Usage

Environment

This environment adopts new version OpenMMLab series to support multi-task pretraining and finetuning on various RS tasks.

Package	Version	Package	Version	Package	Version	Package	Version
Python	3.8.17	timm	0.9.5	MMEngine	0.8.4	MMDetection	3.1.0
Pytorch	1.10.0	OpenCV	4.8.0	MMPretrain	1.2.0	MMRotate	1.0.0rc1
Torchvision	0.10.0	MMCV	2.0.0	MMSegmentation	1.0.0	Open-CD	1.1.0

❗❗❗ We also configure an environment for MMRotate 0.3.4

Package	Version	Package	Version	Package	Version
Python	3.8.0	timm	0.9.2	MMEngine	0.10.3
Pytorch	1.10.0	OpenCV	4.7.0	MMDetection	2.28.2
Torchvision	0.10.0	MMCV-full	1.6.1	MMRotate	0.3.4

This environment is used for multi-scale prediction of FAIR1M-2.0 and DOTA-V1.0.

Preparing Pretraining Dataset

Download SOTA-RBB and the SIOR and FAST sets from SAMRS dataset.
Transform the *.pkl in SAMRS dataset to COCO *.json.
```
python scripts/convert_pkl_json.py
```

Performing Multi-Task Pretraining

We conduct the MTP with SLURM. This is an example of pretraining ViT-L + RVSA:

srun -J mtp -p gpu --gres=dcu:4 --ntasks=32 --ntasks-per-node=4 --cpus-per-task=8 --kill-on-bad-exit=1 \
python main_pretrain.py \
    --backbone 'vit_l_rvsa' --tasks 'ss' 'is' 'rd' \
    --datasets 'sota' 'sior' 'fast' \
    --batch_size 3 --batch_size_val 3 --workers 8 \
    --save_path [folder path of saved model] \
    --distributed 'True' --end_iter 80000 \
    --image_size 448 --init_backbone 'mae' --port '16003' --batch_mode 'avg' --background 'True' --use_ckpt 'True' --interval 5000

The training can be recovered by setting --ft and --resume

--ft 'True' --resume [path of saved multi-task pretrained model]

Preparing Finetuning Dataset

For Xview: using scripts/prepare_xview_dataset.py, it contains the following functions:

Transform geojson to labels in yolo format
Divide training and testing sets
Clip images and yolo format labels
Transform yolo format labels to COCO format *.json

For DIOR: transform *.xml to COCO *.json format for feeding into MMDetection

python scripts/dior_h_2_coco.py

For FAIR1M: transform *.txt in DOTA format to required *.xml for submitting

python scripts/dota_submit_txt_to_fair1m_xml.py --txt_dir [path of *.txt]

For SpaceNetv1: extracting segmentation mask from geojson

python scripts/process_spacenet.py

Finetuning on Various RS tasks

Except for the rotated detection, we perform the finetuning on the SLURM. Here are examples:

Scene Classification (using MMPretrain)

Training and Validation on EuroSAT using MAE + MTP pretrained ViT-L + RVSA:

srun -J mmpretrn -p gpu --gres=dcu:4 --ntasks=8 --ntasks-per-node=4 --cpus-per-task=8 --kill-on-bad-exit=1 \
python -u tools/train.py configs/mtp/vit-rvsa-l-224-mae-mtp_eurosat.py \
--work-dir=/diwang/work_dir/multitask_pretrain/finetune/classification/eurosat/vit-rvsa-l-224-mae-mtp_eurosat \
--launcher="slurm" --cfg-options 'find_unused_parameters'=True

Horizontal Object Detection (using MMDetection)

Training on DIOR using Faster-RCNN with a backbone network of MAE + MTP pretrained ViT-L + RVSA:

srun -J mmdet -p gpu --gres=dcu:4 --ntasks=4 --ntasks-per-node=4 --cpus-per-task=8 --kill-on-bad-exit=1 \
python -u tools/train.py configs/mtp/dior/faster_rcnn_rvsa_l_800_mae_mtp_dior.py \
--work-dir=/diwang/work_dir/multitask_pretrain/finetune/Horizontal_Detection/dior/faster_rcnn_rvsa_l_800_mae_mtp_dior \
--launcher="slurm"

Then testing and generating dection results:

srun -J mmdet -p gpu --gres=dcu:4 --ntasks=4 --ntasks-per-node=4 --cpus-per-task=8 --kill-on-bad-exit=1 \
python -u tools/test.py configs/mtp/dior/faster_rcnn_rvsa_l_800_mae_mtp_dior.py \
/diwang/work_dir/multitask_pretrain/finetune/Horizontal_Detection/dior/faster_rcnn_rvsa_l_800_mae_mtp_dior/epoch_12.pth \
--work-dir=/diwang/work_dir/multitask_pretrain/finetune/Horizontal_Detection/dior/faster_rcnn_rvsa_l_800_mae_mtp_dior/predict \
--show-dir=/diwang/work_dir/multitask_pretrain/finetune/Horizontal_Detection/dior/faster_rcnn_rvsa_l_800_mae_mtp_dior/predict/show \
--launcher="slurm" --cfg-options val_cfg=None val_dataloader=None val_evaluator=None

Rotated Object Detection (using MMRotate, running on both SLURM and GPU server)

1. Running on SLURM:

(Using MMRotate 1.0.0rc1) Training on DIOR-R using Oriented-RCNN with a backbone network of MAE + MTP pretrained ViT-L + RVSA:

srun -J mmrot -p gpu --gres=dcu:4 --ntasks=4 --ntasks-per-node=4 --cpus-per-task=8 --kill-on-bad-exit=1 \
python -u tools/train.py configs/mtp/diorr/oriented_rcnn_rvsa_l_800_mae_mtp_diorr.py \
--work-dir=/diwang22/work_dir/multitask_pretrain/finetune/Rotated_Detection/diorr/oriented_rcnn_rvsa_l_800_mae_mtp_diorr \
--launcher="slurm"

(Using MMRotate 1.0.0rc1) Testing on DIOR-R for evaluation and visualizing detection maps.

srun -J mmrot -p gpu --gres=dcu:4 --ntasks=8 --ntasks-per-node=4 --cpus-per-task=8 --kill-on-bad-exit=1 \
python -u tools/test.py configs/mtp/oriented_rcnn_rvsa_l_800_mae_mtp_diorr.py \
/diwang22/work_dir/multitask_pretrain/finetune/Rotated_Detection/diorr/oriented_rcnn_rvsa_l_800_mae_mtp_diorr/epoch_12.pth \
--work-dir=/diwang22/work_dir/multitask_pretrain/finetune/Rotated_Detection/diorr/oriented_rcnn_rvsa_l_800_mae_mtp_diorr/predict \
--show-dir=/diwang22/work_dir/multitask_pretrain/finetune/Rotated_Detection/diorr/oriented_rcnn_rvsa_l_800_mae_mtp_diorr/predict/show \
--launcher="slurm" --cfg-options val_cfg=None val_dataloader=None val_evaluator=None

(Using MMRotate 0.3.4) If the dataset is evaluated online, we use --format-only, here is an example of testing on FAIR1M-2.0 for submitting results and visualizing detection maps.

srun -J mmrot -p gpu --gres=dcu:4 --ntasks=16 --ntasks-per-node=4 --cpus-per-task=8 --kill-on-bad-exit=1 \
python -u tools/test.py configs/mtp/fair1m/oriented_rcnn_rvsa_l_800_mae_mtp_fair1m20.py \
/diwang22/work_dir/multitask_pretrain/finetune/Rotated_Detection/fair1mv2/oriented_rcnn_rvsa_l_800_mae_mtp_fair1m20/epoch_12.pth --format-only \
--show-dir=/diwang22/work_dir/multitask_pretrain/finetune/Rotated_Detection/fair1mv2/oriented_rcnn_rvsa_l_800_mae_mtp_fair1m20/predict/show \
--eval-options submission_dir=/diwang22/work_dir/multitask_pretrain/finetune/Rotated_Detection/fair1mv2/oriented_rcnn_rvsa_l_800_mae_mtp_fair1m20/predict/submit \
--launcher="slurm"

2. Running on GPU server:

(Using MMRotate 1.0.0rc1) Training on DOTA-2.0 using Oriented-RCNN with a backbone network of MAE + MTP pretrained ViT-L + RVSA:

CUDA_VISIBLE_DEVICES=0,1,2,3 python -m torch.distributed.launch --nproc_per_node=4 --nnodes=1 --master_port=40002 --master_addr=1.2.3.4 \
tools/train.py configs/mtp/dotav2/oriented_rcnn_rvsa_l_1024_mae_mtp_dota20.py \
--work-dir=/data/diwang22/work_dir/multitask_pretrain/finetune/Rotated_Detection/dotav2/oriented_rcnn_rvsa_l_1024_mae_mtp_dota20

(Using MMRotate 1.0.0rc1) Single-scale testing on DOTA-2.0 for submitting online evaluation results and visualizing detection maps.

CUDA_VISIBLE_DEVICES=0 python tools/test.py configs/mtp/dotav2/oriented_rcnn_rvsa_l_1024_mae_mtp_dota20.py \
/data/diwang22/work_dir/multitask_pretrain/finetune/Rotated_Detection/dotav2/oriented_rcnn_rvsa_l_1024_mae_mtp_dota20/epoch_40.pth \
--work-dir=/data/diwang22/work_dir/multitask_pretrain/finetune/Rotated_Detection/dotav2/oriented_rcnn_rvsa_l_1024_mae_mtp_dota20/test \
--show-dir=/data/diwang22/work_dir/multitask_pretrain/finetune/Rotated_Detection/dotav2/oriented_rcnn_rvsa_l_1024_mae_mtp_dota20/test/vis

(Using MMRotate 0.3.4) Multi-scale testing on DOTA-V1.0 for submitting online evaluation results and visualizing detection maps.

CUDA_VISIBLE_DEVICES=0 python tools/test.py configs/mtp/dotav1/oriented_rcnn_rvsa_l_1024_mae_mtp_dota10.py \
/data/diwang22/work_dir/multitask_pretrain/finetune/Rotated_Detection/dotav1/oriented_rcnn_rvsa_l_1024_mae_mtp_dota10/epoch_12.pth --format-only \
--show-dir=/data/diwang22/work_dir/multitask_pretrain/finetune/Rotated_Detection/dotav1/oriented_rcnn_rvsa_l_1024_mae_mtp_dota10/predict/show \
--eval-options submission_dir=/data/diwang22/work_dir/multitask_pretrain/finetune/Rotated_Detection/dotav1/oriented_rcnn_rvsa_l_1024_mae_mtp_dota10/predict/submit

Semantic Segmentation (using MMSegmentation)

Training on SpaceNetv1 using UperNet with a backbone network of MAE + MTP pretrained ViT-L + RVSA:

srun -J mmseg -p gpu --gres=dcu:4 --ntasks=8 --ntasks-per-node=4 --cpus-per-task=8 --kill-on-bad-exit=1 \
python -u tools/train.py configs/mtp/spacenetv1/rvsa-l-upernet-384-mae-mtp-spacenetv1.py \
--work-dir=/diwang22/work_dir/multitask_pretrain/finetune/Semantic_Segmentation/spacenetv1/rvsa-l-upernet-384-mae-mtp-spacenetv1 \
--launcher="slurm" --cfg-options 'find_unused_parameters'=True

Testing on SpaceNetv1 for accuracy evaluation and generating prediction maps:

srun -J mmseg -p gpu --gres=dcu:4 --ntasks=8 --ntasks-per-node=4 --cpus-per-task=8 --kill-on-bad-exit=1 \
python -u tools/test.py configs/mtp/spacenetv1/rvsa-l-upernet-384-mae-mtp-spacenetv1.py \
/diwang22/work_dir/multitask_pretrain/finetune/Semantic_Segmentation/spacenetv1/rvsa-l-upernet-384-mae-mtp-spacenetv1/iter_80000.pth \
--work-dir=/diwang22/work_dir/multitask_pretrain/finetune/Semantic_Segmentation/spacenetv1/rvsa-l-upernet-384-mae-mtp-spacenetv1/predict \
--show-dir=/diwang22/work_dir/multitask_pretrain/finetune/Semantic_Segmentation/spacenetv1/rvsa-l-upernet-384-mae-mtp-spacenetv1/predict/show \
--launcher="slurm" --cfg-options val_cfg=None val_dataloader=None val_evaluator=None

Online Evaluation: Testing on LoveDA for submittting online evaluation results and generating prediction maps:

srun -J mmseg -p gpu --gres=dcu:4 --ntasks=4 --ntasks-per-node=4 --cpus-per-task=8 --kill-on-bad-exit=1 \
python -u tools/test.py configs/mtp/loveda/rvsa-l-upernet-512-mae-mtp-loveda.py \
/diwang22/work_dir/multitask_pretrain/finetune/Semantic_Segmentation/loveda/rvsa-l-upernet-512-mae-mtp-loveda/iter_80000.pth \
--work-dir=/diwang22/work_dir/multitask_pretrain/finetune/Semantic_Segmentation/loveda/rvsa-l-upernet-512-mae-mtp-loveda/predict \
--out=/diwang22/work_dir/multitask_pretrain/finetune/Semantic_Segmentation/loveda/rvsa-l-upernet-512-mae-mtp-loveda/predict/submit \
--show-dir=/diwang22/work_dir/multitask_pretrain/finetune/Semantic_Segmentation/loveda/rvsa-l-upernet-512-mae-mtp-loveda/predict/show \
--launcher="slurm" --cfg-options val_cfg=None val_dataloader=None val_evaluator=None

Note: after inferencing, the predictions of LoveDA needs to manually reduce 1 to meet the requirement of evaluation site

python scripts/change_loveda_label.py

Change Detection (using Open-CD)

Training on WHU using UperNet with a backbone network of MAE + MTP pretrained ViT-L + RVSA:

srun -J opencd -p gpu --gres=dcu:4 --ntasks=8 --ntasks-per-node=4 --cpus-per-task=8 --kill-on-bad-exit=1 \
python -u tools/train.py configs/mtp/whu/rvsa-l-unet-256-mae-mtp_whu.py \
--work-dir=/diwang22/work_dir/multitask_pretrain/finetune/Change_Detection/whu/rvsa-l-unet-256-mae-mtp_whu \
--launcher="slurm" --cfg-options 'find_unused_parameters'=True

Testing for accuracy evaluation and generating prediction maps:

srun -J opencd -p gpu --gres=dcu:4 --ntasks=8 --ntasks-per-node=4 --cpus-per-task=8 --kill-on-bad-exit=1 \
python -u tools/test.py configs/mtp/whu/rvsa-l-unet-256-mae-mtp_whu.py \
/diwang22/work_dir/multitask_pretrain/finetune/Change_Detection/whu/rvsa-l-unet-256-mae-mtp_whu/epoch_200.pth \
--work-dir=/diwang22/work_dir/multitask_pretrain/finetune/Change_Detection/whu/rvsa-l-unet-256-mae-mtp_whu/predict \
--show-dir=/diwang22/work_dir/multitask_pretrain/finetune/Change_Detection/whu/rvsa-l-unet-256-mae-mtp_whu/predict/show \
--launcher="slurm" --cfg-options val_cfg=None val_dataloader=None val_evaluator=None

Decoder Parameter Reusing

Take an example of reusing segmentation decoder in finetuning:

Change the keys of MTP saved weights:
```
python scripts/change_ckpt.py
```

Then training with the revised weights

srun -J mmseg -p gpu --gres=dcu:4 --ntasks=8 --ntasks-per-node=4 --cpus-per-task=8 --kill-on-bad-exit=1 \
python -u tools/train.py configs/mtp/spacenetv1/rvsa-b-upernet-384-mae-mtp-spacenetv1.py \
--work-dir=/diwang22/work_dir/multitask_pretrain/finetune/Semantic_Segmentation/spacenetv1/rvsa-b-upernet-384-mae-mtp-spacenetv1_reuse_decoder \
--launcher="slurm" \
--cfg-options 'find_unused_parameters'=True load_from=[path of the revised weights]

The remaining steps are the same as regular testing.

🎵 Citation

If you find MTP helpful, please consider giving this repo a ⭐ and citing:

@ARTICLE{MTP,
  author={Wang, Di and Zhang, Jing and Xu, Minqiang and Liu, Lin and Wang, Dongsheng and Gao, Erzhong and Han, Chengxi and Guo, Haonan and Du, Bo and Tao, Dacheng and Zhang, Liangpei},
  journal={IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing}, 
  title={MTP: Advancing Remote Sensing Foundation Model Via Multi-Task Pretraining}, 
  year={2024},
  volume={},
  number={},
  pages={1-24},
  doi={10.1109/JSTARS.2024.3408154}}

🎺 Statement

This project is for research purpose only. For any other questions please contact di.wang at gmail.com or whu.edu.cn.

💖 Thanks

💡 Relevant Projects

[1] An Empirical Study of Remote Sensing Pretraining, IEEE TGRS, 2022 | Paper | Github
Di Wang^∗, Jing Zhang^∗, Bo Du, Gui-Song Xia and Dacheng Tao

[2] Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model, IEEE TGRS, 2022 | Paper | Github
Di Wang^∗, Qiming Zhang^∗, Yufei Xu^∗, Jing Zhang, Bo Du, Dacheng Tao and Liangpei Zhang

[3] SAMRS: Scaling-up Remote Sensing Segmentation Dataset with Segment Anything Model, NeurIPS Datasets and Benchmarks Track, 2023 | Paper | Github
Di Wang^∗, Jing Zhang, Bo Du, Minqiang Xu, Lin Liu, Dacheng Tao and Liangpei Zhang

vitae-transformer / mtp Goto Github PK

mtp's Introduction