@InProceedings{LorenzoPorzi2020,
author="Lorenzo Porzi
and Markus Hofinger
and Idoia Ruiz
and Joan Serrat
and Samuel Rota Bulo
and Peter Kontschieder",
title="Learning Multi-Object Tracking and Segmentation from Automatic Annotations",
booktitle="33rd IEEE Conference on Computer Vision and Pattern Recognition",
year="2020",
pages="6845--6854",
abstract="In this work we contribute a novel pipeline to automatically generate training data, and to improve over state-of-the-art multi-object tracking and segmentation (MOTS) methods. Our proposed track mining algorithm turns raw street-level videos into high-fidelity MOTS training data, is scalable and overcomes the need of expensive and time-consuming manual annotation approaches. We leverage state-of-the-art instance segmentation results in combination with optical flow predictions, also trained on automatically harvested training data. Our second major contribution is MOTSNet -- a deep learning, tracking-by-detection architecture for MOTS -- deploying a novel mask-pooling layer for improved object association over time. Training MOTSNet with our automatically extracted data leads to significantly improved sMOTSA scores on the novel KITTI MOTS dataset (+1.9\%/+7.5\% on cars/pedestrians), and MOTSNet improves by +4.1\% over previously best methods on the MOTSChallenge dataset. Our most impressive finding is that we can improve over previous best-performing works, even in complete absence of manually annotated MOTS training data.",
optnote="ADAS; 600.124; 600.118",
optnote="exported from refbase (http://refbase.cvc.uab.es/show.php?record=3402), last updated on Tue, 16 Nov 2021 13:32:28 +0100",
doi="10.1109/cvpr42600.2020.00688",
opturl="https://ieeexplore.ieee.org/abstract/document/9157138",
file=":http://refbase.cvc.uab.es/files/PHR2020.pdf:PDF"
}