Combining Visual Saliency Methods and Sparse Keypoint Annotations to Providently Detect Vehicles at Night

1 code implementation • 25 Apr 2022 • Lukas Ewecker, Lars Ohnemus, Robin Schwager, Stefan Roos, Tim Brühl, Sascha Saralajew

We show that this approach allows for an automated derivation of different object representations, such as binary maps or bounding boxes so that detection models can be trained on different annotation variants and the problem of providently detecting vehicles at night can be tackled from different perspectives.

object-detection Object Detection