Encoding oriented bounding boxes as structure tensors and regressing the three matrix entries with L1 loss gives accurate, low-cost angle prediction in oriented object detection.
Learning roi transformer for oriented object detection in aerial images
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Structure Tensor Representation for Robust Oriented Object Detection
Encoding oriented bounding boxes as structure tensors and regressing the three matrix entries with L1 loss gives accurate, low-cost angle prediction in oriented object detection.