Experiments on Flood Segmentation on Sentinel-1 SAR Imagery with Cyclical Pseudo Labeling and Noisy Student Training

Last update: Dec 28, 2022

Overview

Flood Detection Challenge

This repository contains code for our submission to the ETCI 2021 Competition on Flood Detection (Winning Solution #2).

Accompanying paper: Flood Segmentation on Sentinel-1 SAR Imagery with Semi-Supervised Learning.

by Sayak Paul*, Siddha Ganju*.

(*) equal contribution.

Team

Executing the code

We executed the scripts and notebooks on a Vertex AI Notebook instance. The instance has four Tesla V100 GPUs and its base configuration is n1-standard-16.

We use Python 3.8 and PyTorch 1.9. Apart from the requirements specified in requirements.txt you'd need to install the following as well to run the scripts and notebooks:

$ pip install git+https://github.com/qubvel/segmentation_models.pytorch
$ pip install git+https://github.com/lucasb-eyer/pydensecrf.git

Our scripts and notebooks make use of mixed-precision training (via torch.cuda.amp) and distributed training (via torch.nn.parallelDistributedDataParallel). With this combination we are able to achieve significant boosts in the overall model training time.

Execution instructions for the scripts (src) and notebooks (notebooks) are provided in their respective directories.

Pre-trained weights

For complete reproducibility, we provide the pre-trained weights here. With these weights and the workflow depicted in the notebooks and scripts one should be able to get an IoU of ~0.76 (as per the competition leaderboard) on the test set provided at the competition.

Results

You can verify the reported results here. Just switch to "Test (Phase 2)" after clicking the link.

FAQ

Create a new Notebooks instance

Acknowledgements

We are grateful to the ML-GDE program for providing GCP credits to support our experiments.
Thanks to Charmi Chokshi, and domain experts Nick Leach and Veda Sunkara for insightful discussions.

Citation

@misc{paul2021flood,
      title={Flood Segmentation on Sentinel-1 SAR Imagery with Semi-Supervised Learning}, 
      author={Sayak Paul and Siddha Ganju},
      year={2021},
      eprint={2107.08369},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

You might also like...

Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation (CVPR 2021)

Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation (CVPR 2021, official Pytorch implementatio

247 Dec 25, 2022

[NeurIPS 2021] Deceive D: Adaptive Pseudo Augmentation for GAN Training with Limited Data

Deceive D: Adaptive Pseudo Augmentation for GAN Training with Limited Data (NeurIPS 2021) This repository provides the official PyTorch implementation

155 Nov 30, 2021

[CVPR 2021] Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision

TorchSemiSeg [CVPR 2021] Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision by Xiaokang Chen1, Yuhui Yuan2, Gang Zeng1, Jingdong Wang

387 Jan 8, 2023

[CVPR 2022] Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels

Using Unreliable Pseudo Labels Official PyTorch implementation of Semi-Supervised Semantic Segmentation Using Unreliable Pseudo Labels, CVPR 2022. Ple

268 Dec 24, 2022

Code and model benchmarks for "SEVIR : A Storm Event Imagery Dataset for Deep Learning Applications in Radar and Satellite Meteorology"

NeurIPS 2020 SEVIR Code for paper: SEVIR : A Storm Event Imagery Dataset for Deep Learning Applications in Radar and Satellite Meteorology Requirement

USAF - MIT Artificial Intelligence Accelerator

46 Dec 15, 2022

Train a deep learning net with OpenStreetMap features and satellite imagery.

DeepOSM Classify roads and features in satellite imagery, by training neural networks with OpenStreetMap (OSM) data. DeepOSM can: Download a chunk of

1.3k Nov 24, 2022

To propose and implement a multi-class classification approach to disaster assessment from the given data set of post-earthquake satellite imagery.

2 Jan 5, 2022

Change is Everywhere: Single-Temporal Supervised Object Change Detection in Remote Sensing Imagery (ICCV 2021)

Change is Everywhere Single-Temporal Supervised Object Change Detection in Remote Sensing Imagery by Zhuo Zheng, Ailong Ma, Liangpei Zhang and Yanfei

125 Dec 13, 2022

A PyTorch implementation of Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks

SVHNClassifier-PyTorch A PyTorch implementation of Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks If

182 Jan 3, 2023

Experiments on Flood Segmentation on Sentinel-1 SAR Imagery with Cyclical Pseudo Labeling and Noisy Student Training

Related tags

Overview

Flood Detection Challenge

Team

Executing the code

Pre-trained weights

Results

FAQ

Acknowledgements

Citation

You might also like...

Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation (CVPR 2021)

[NeurIPS 2021] Deceive D: Adaptive Pseudo Augmentation for GAN Training with Limited Data

[CVPR 2021] Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision

[CVPR 2022] Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels

Code and model benchmarks for "SEVIR : A Storm Event Imagery Dataset for Deep Learning Applications in Radar and Satellite Meteorology"

Train a deep learning net with OpenStreetMap features and satellite imagery.

To propose and implement a multi-class classification approach to disaster assessment from the given data set of post-earthquake satellite imagery.

Change is Everywhere: Single-Temporal Supervised Object Change Detection in Remote Sensing Imagery (ICCV 2021)

A PyTorch implementation of Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks

Releases(v1.0.0)

v1.0.0(Jul 15, 2021)

Owner

Siddha Ganju

A robotic arm that mimics hand movement through MediaPipe tracking.

A JAX implementation of Broaden Your Views for Self-Supervised Video Learning, or BraVe for short.

PyContinual (An Easy and Extendible Framework for Continual Learning)

Apply AnimeGAN-v2 across frames of a video clip

ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detection

VR-Caps: A Virtual Environment for Active Capsule Endoscopy

TensorFlow-LiveLessons - "Deep Learning with TensorFlow" LiveLessons

QI-Q RoboMaster2022 CV Algorithm

Prompts - Read a textfile of prompts and import into anki via ankiconnect

PyTorch IPFS Dataset

Production First and Production Ready End-to-End Speech Recognition Toolkit

Bayesian algorithm execution (BAX)

A simple but complete full-attention transformer with a set of promising experimental features from various papers

Embeds a story into a music playlist by sorting the playlist so that the order of the music follows a narrative arc.

Betafold - AlphaFold with tunings

Collection of tasks for fast prototyping, baselining, finetuning and solving problems with deep learning.

A collection of Jupyter notebooks to play with NVIDIA's StyleGAN3 and OpenAI's CLIP for a text-based guided image generation.

Deep metric learning methods implemented in Chainer

[CVPR'20] TTSR: Learning Texture Transformer Network for Image Super-Resolution

VACA: Designing Variational Graph Autoencoders for Interventional and Counterfactual Queries