Computer Vision

SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptation

We introduce the largest synthetic dataset for autonomous driving to study continuous domain adaptation and multi-task perception.

On the Practicality of Deterministic Epistemic Uncertainty

We provide a taxonomy of DUMs, evaluate their calibration under continuous distributional shifts, and extend them to semantic segmentation.

Leveraging Crowdsourced GPS Data for Road Extraction From Aerial Imagery

Leveraging crowdsourced GPS data to improve and support road extraction from aerial imagery.

Combining Satellite Imagery and GPS Data for Road Extraction

Combining satellite imagery with GPS data to improve road extraction quality

Stacked U-Nets with Multi-output for Road Extraction

A new method for road extraction using stacked U-Nets with multiple output, hybrid loss function used to address the problem of unbalanced classes of training data, and post-processing methods to bridge prediction gaps.