BBRefinement: A Universal Scheme to Improve the Precision of Box Object Detectors
We present a conceptually simple yet powerful and general scheme for refining the predictions of bounding boxes produced by an arbitrary object detector. Our approach was trained separately on single objects extracted from ground truth labels. For inference, it can be coupled with an arbitrary objec...
Main Authors: | Hurtik, P. (Author), Hynar, D. (Author), Vajgl, M. (Author) |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI
2022
|
Subjects: | |
Online Access: | View Fulltext in Publisher |
Similar Items
-
Bounding Box Projection for Regression Uncertainty in Oriented Object Detection
by: Qian Wu, et al.
Published: (2021-01-01) -
RatioNet: Ratio Prediction Network for Object Detection
by: Kuan Zhao, et al.
Published: (2021-03-01) -
Arbitrary-angle bounding box based location for object detection in remote sensing image
by: Fei Sun, et al.
Published: (2021-01-01) -
A Scale Balanced Loss for Bounding Box Regression
by: Degang Sun, et al.
Published: (2020-01-01) -
Grasping Objects Mixed With Towels
by: Xiaoman Wang, et al.
Published: (2020-01-01)