Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing Data
This is the official PyTorch implementation of the SeCo paper:
@article{manas2021seasonal,
title={Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing Data},
author={Ma{\~n}as, Oscar and Lacoste, Alexandre and Giro-i-Nieto, Xavier and Vazquez, David and Rodriguez, Pau},
journal={arXiv preprint arXiv:2103.16607},
year={2021}
}
Preparation
Install Python dependencies by running:
pip install -r requirements.txt
Data Collection
First, obtain Earth Engine authentication credentials by following the installation instructions.
Then, to collect and download a new SeCo dataset from a random set of Earth locations, run:
python datasets/seco_downloader.py \
--save_path [folder where data will be downloaded] \
--num_locations 200000
Unsupervised Pre-training
To do unsupervised pre-training of a ResNet-18 model on the SeCo dataset, run:
python main_pretrain.py \
--data_dir datasets/seco_1m --data_mode seco \
--base_encoder resnet18
Transferring to Downstream Tasks
With a pre-trained SeCo model, to train a supervised linear classifier on 10% of the BigEarthNet training set in a 4-GPU machine, run:
python main_bigearthnet.py \
--gpus 4 --accelerator dp --batch_size 1024 \
--data_dir datasets/bigearthnet --train_frac 0.1 \
--backbone_type pretrain --ckpt_path checkpoints/seco_resnet18_1m.ckpt \
--freeze_backbone --learning_rate 1e-3
To train a supervised linear classifier on EuroSAT from a pre-trained SeCo model, run:
python main_eurosat.py \
--data_dir datasets/eurosat \
--backbone_type pretrain --ckpt_path checkpoints/seco_resnet18_1m.ckpt
To train a supervised change detection model on OSCD from a pre-trained SeCo model, run:
python main_oscd.py \
--data_dir datasets/oscd \
--backbone_type pretrain --ckpt_path checkpoints/seco_resnet18_1m.ckpt
Datasets
Our collected SeCo datasets can be downloaded as following:
| #images | RGB preview | size | link | md5 |
|---|---|---|---|---|
| 100K | ✓ | 7.3 GB | download | ebf2d5e03adc6e657f9a69a20ad863e0 |
| ~1M | 36.3 GB | download | 187963d852d4d3ce6637743ec3a4bd9e |
Pre-trained Models
Our pre-trained SeCo models can be downloaded as following:
| dataset | architecture | link | md5 |
|---|---|---|---|
| SeCo-100K | ResNet-18 | download | dcf336be31f6c6b0e77dcb6cc958fca8 |
| SeCo-1M | ResNet-18 | download | 53d5c41d0f479bdfd31d6746ad4126db |
| SeCo-100K | ResNet-50 | download | 9672c303f6334ef816494c13b9d05753 |
| SeCo-1M | ResNet-50 | download | 7b09c54aed33c0c988b425c54f4ef948 |
5 Mar 4, 2022
55 Nov 23, 2022
9 Jun 10, 2022
55 Dec 12, 2022
53 Dec 2, 2022
43 Jan 5, 2023
222 Dec 28, 2022
176 Dec 24, 2022
125 Dec 13, 2022
38 Aug 31, 2022
1 May 24, 2022
7 Nov 29, 2022
2 Nov 19, 2021
11 Sep 30, 2022
8 Nov 21, 2022
15 Sep 23, 2022
13 Nov 19, 2022
19 Dec 17, 2022