RDCNet: Rotation-Aware Feature Representation and Aspect-Adaptive Label Assignment for Efficient Arbitrary-Oriented Object Detection

Recent advances in arbitrary-oriented object detection (AOOD) for remote sensing imagery have largely relied on high-capacity architectures, such as two-stage detectors and transformer-based models, to handle arbitrary object orientations and extreme aspect ratios. Although these approaches achieve...

Celý popis

Podrobná bibliografie

Hlavní autoři:	Jihye Ryu, Jaegeun Yoon, Kwangho Song
Médium:	Artigo
Jazyk:	Inglês
Vydáno:	IEEE 2026-01-01
Edice:	IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Témata:	Aspect-adaptive label assignment (AALA) label assignment one-stage detector oriented object detection remote sensing (RS) rotation-aware deformable convolution (RDC)
On-line přístup:	https://ieeexplore.ieee.org/document/11495006/
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!