3rd Place Solution of Traffic4Cast 2021 Core Challenge

This is the code for our solution to the NeurIPS 2021 Traffic4Cast Core Challenge.

Paper

Our solution is described in the "Solving Traffic4Cast Competition with U-Net and Temporal Domain Adaptation" paper.

If you wish to cite this code, please do it as follows:

@misc{konyakhin2021solving,
      title={Solving Traffic4Cast Competition with U-Net and Temporal Domain Adaptation}, 
      author={Vsevolod Konyakhin and Nina Lukashina and Aleksei Shpilman},
      year={2021},
      eprint={2111.03421},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

Competition and Demonstration Track @ NeurIPS 2021

Learnt parameters

The models' learnt parameters are available by the link: https://drive.google.com/file/d/1zD0CecX4P3v5ugxaHO2CQW9oX7_D4BCa/view?usp=sharing
Please download the archive and unzip it into the weights folder of the repository, so its structure looks like the following:

├── ...
├── traffic4cast
├── weights
│   ├── densenet                 
│   │   ├── BERLIN_1008_1430_densenet_unet_mse_best_val_loss_2019=78.4303.pth                     
│   │   ├── CHICAGO_1010_1730_densenet_unet_mse_best_val_loss_2019=41.1579.pth
│   │   └── MELBOURNE_1009_1619_densenet_unet_mse_best_val_loss_2019=25.7395.pth    
│   ├── effnetb5
│   │   ├── BERLIN_1008_1430_efficientnetb5_unet_mse_best_val_loss_2019=80.3510.pth    
│   │   ├── CHICAGO_1012_1035_efficientnetb5_unet_mse_best_val_loss_2019=41.6425.pth
│   │   ├── ISTANBUL_1012_2315_efficientnetb5_unet_mse_best_val_loss_2019=55.7918.pth    
│   │   └── MELBOURNE_1010_0058_efficientnetb5_unet_mse_best_val_loss_2019=26.0132.pth    
│   └── unet
│       ├── BERLIN_0806_1425_vanilla_unet_mse_best_val_loss_2019=0.0000_v5.pth    
│       ├── CHICAGO_0805_0038_vanilla_unet_mse_best_val_loss_2019=42.6634.pth
│       ├── ISTANBUL_0805_2317_vanilla_unet_mse_best_val_loss_2019=0.0000_v4.pth
│       └── MELBOURNE_0804_1942_vanilla_unet_mse_best_val_loss_2019=26.7588.pth
├── ...

Submission reproduction

To generate the submission file, please run the following script:

# $1 - absolute path to the dataset, $2 device to run inference
sh submission.sh {absolute path to dataset} {cpu, cuda}
# Launch example
sh submission.sh /root/data/traffic4cast cuda

The above sctipt generates the submission file submission/submission_all_unets_da_none_mpcpm1_mean_temporal_{date}.zip, which gave us the best MSE of 49.379068541527 on the final leaderboard.

3rd Place Solution of the Traffic4Cast Core Challenge @ NeurIPS 2021

Related tags

Overview

3rd Place Solution of Traffic4Cast 2021 Core Challenge

Paper

Learnt parameters

Submission reproduction

Owner

A different spin on dataclasses.

Robocop is your personal mini voice assistant made using Python.

Time-Optimal Planning for Quadrotor Waypoint Flight

Traditional deepdream with VQGAN+CLIP and optical flow. Ready to use in Google Colab

Predicting 10 different clothing types using Xception pre-trained model.

Mercer Gaussian Process (MGP) and Fourier Gaussian Process (FGP) Regression

Code for You Only Cut Once: Boosting Data Augmentation with a Single Cut

Extract MNIST handwritten digits dataset binary file into bmp images

End-to-End Dense Video Captioning with Parallel Decoding (ICCV 2021)

CondenseNet: Light weighted CNN for mobile devices

Self-Supervised Monocular DepthEstimation with Internal Feature Fusion(arXiv), BMVC2021

ADSPM: Attribute-Driven Spontaneous Motion in Unpaired Image Translation

Unified API to facilitate usage of pre-trained "perceptor" models, a la CLIP

Builds a LoRa radio frequency fingerprint identification (RFFI) system based on deep learning techiniques

SberSwap Video Swap base on deep learning

Jiminy Cricket Environment (NeurIPS 2021)

Deep RGB-D Saliency Detection with Depth-Sensitive Attention and Automatic Multi-Modal Fusion (CVPR'2021, Oral)

Submodular Subset Selection for Active Domain Adaptation (ICCV 2021)

Look Who’s Talking: Active Speaker Detection in the Wild

Python-based Informatics Kit for Analysing Chemical Units