Skip to footer
Home Research Artificial Intelligence / Machine Learning Deep Parametric Continuous Convolutional Neural Networks

Deep Parametric Continuous Convolutional Neural Networks


We propose an approach for semi-automatic annotation of object instances. While most current methods treat object segmentation as a pixel-labeling problem, we here cast it as a polygon prediction task, mimicking how most current datasets have been annotated. In particular, our approach takes as input an image crop and sequentially produces vertices of the polygon outlining the object. This allows a human annotator to interfere at any time and correct a vertex if needed, producing as accurate segmentation as desired by the annotator. We show that our approach speeds up the annotation process by a factor of 4.7 across all classes in Cityscapes, while achieving 78.4% agreement in IoU with original ground-truth, matching the typical agreement between human annotators. For cars, our speed-up factor is 7.3 for an agreement of 82.2%. We further show generalization capabilities of our approach to unseen datasets.


Shenlong Wang, Simon Suo, Wei-Chiu Ma, Andrei PokrovskyRaquel Urtasun


CVPR 2018

Full Paper

‘Deep Parametric Continuous Convolutional Neural Networks’ (PDF)

Uber ATG

Previous article Learning deep structured active contours end-to-end
Next article Matching Adversarial Networks
Shenlong Wang is research scientist at Uber ATG Toronto working on the development of self-driving cars. He is also a PhD student at University of Toronto. His advisor is Prof. Raquel Urtasun. He has a broad interest in computer vision, machine learning and robotics. He is particularly interested in 3D vision and deep structured models.
Simon is a research scientist at Uber ATG Toronto and a graduate student at Univeristy of Toronto, supervised by Prof. Raquel Urtasun. His research interest mainly lies in machine learning and robotics. At ATG, he aims to use understanding of interactive scenarios to improve planning and simulation. Before joining University of Toronto, Simon studied Computer Science at Universtiy of Waterloo.
Wei-Chiu Ma is a PhD student at MIT advised by Prof. Antonio Torralba. His research interests lie in the intersection of computer vision and machine learning, in particular low-level vision and 3D vision. He also works part-time at Uber ATG Toronto with Prof. Raquel Urtasun to apply his research to self-driving vehicles.
Andrei Pokrovsky is a researcher/engineer at Uber Advanced Technologies Group Toronto.
Raquel Urtasun is the Chief Scientist for Uber ATG and the Head of Uber ATG Toronto. She is also a Professor at the University of Toronto, a Canada Research Chair in Machine Learning and Computer Vision and a co-founder of the Vector Institute for AI. She is a recipient of an NSERC EWR Steacie Award, an NVIDIA Pioneers of AI Award, a Ministry of Education and Innovation Early Researcher Award, three Google Faculty Research Awards, an Amazon Faculty Research Award, a Connaught New Researcher Award, a Fallona Family Research Award and two Best Paper Runner up Prize awarded CVPR in 2013 and 2017. She was also named Chatelaine 2018 Woman of the year, and 2018 Toronto’s top influencers by Adweek magazine