The Quo Vadis submission at Traffic4cast 2019

October 27, 2019 · Entered Twilight · 🏛 arXiv.org

"Last commit was 6.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: CONTRIBUTING.md, LICENSE, README.md, combine_channel_predictions.py, constants.py, environment.yml, evaluate.py, evaluate3.py, evaluate_combination.py, evaluate_knn.py, hypertune.py, hypertune.sh, hypertune_results.py, models, output, scripts, src, submission_write.py, test_data_loading.py, traffic4cast_viz.py, train.py, utils.py

Authors Dan Oneata, Cosmin George Alexandru, Marius Stanescu, Octavian Pascu, Alexandru Magan, Adrian Postelnicu, Horia Cucu arXiv ID 1910.12363 Category cs.CV: Computer Vision Cross-listed cs.LG, stat.ML Citations 0 Venue arXiv.org Repository https://github.com/danoneata/traffic4cast ⭐ 1 Last Checked 2 months ago

Abstract

We describe the submission of the Quo Vadis team to the Traffic4cast competition, which was organized as part of the NeurIPS 2019 series of challenges. Our system consists of a temporal regression module, implemented as $1\times1$ 2d convolutions, augmented with spatio-temporal biases. We have found that using biases is a straightforward and efficient way to include seasonal patterns and to improve the performance of the temporal regression model. Our implementation obtains a mean squared error of $9.47\times 10^{-3}$ on the test data, placing us on the eight place team-wise. We also present our attempts at incorporating spatial correlations into the model; however, contrary to our expectations, adding this type of auxiliary information did not benefit the main system. Our code is available at https://github.com/danoneata/traffic4cast.