no code implementations • 10 Jun 2021 • Jeffri M. Llerena, Luis Felipe Zeni, Lucas N. Kristen, Claudio Jung
Most object detection methods use bounding boxes to encode and represent the object shape and location.
1 code implementation • 23 Apr 2020 • Luis Felipe Zeni, Claudio Jung
Then, we present an adaptive supervision aggregation function that dynamically changes the aggregation criteria for selecting boxes related to one of the ground-truth classes, background, or even ignored during the generation of each refinement module supervision.