paper-with-me

홈 › Papers

ABBSPO: Adaptive Bounding Box Scaling and Symmetric Prior based Orientation Prediction for Detecting Aerial Image Objects

2025-12-10 · Woojin Lee, Hyugjae Chang, Jaeho Moon, Jaehyup Lee, Munchurl Kim arxiv

Weakly supervised oriented object detection (WS-OOD) has gained attention as a cost-effective alternative to fully supervised methods, providing both efficiency and high accuracy. Among weakly supervised approaches, horizontal bounding box (HBox)-supervised OOD stands out for its ability to directly leverage existing HBox annotations while achieving the highest accuracy under weak supervision settings. This paper introduces adaptive bounding box scaling and symmetry-prior-based orientation prediction, called ABBSPO, a framework for WS-OOD. Our ABBSPO addresses limitations of previous HBox-supervised OOD methods, which compare ground truth (GT) HBoxes directly with the minimum circumscribed rectangles of predicted RBoxes, often leading to inaccurate scale estimation. To overcome this, we propose: (i) Adaptive Bounding Box Scaling (ABBS), which appropriately scales GT HBoxes to optimize for the size of each predicted RBox, ensuring more accurate scale prediction; and (ii) a Symmetric Prior Angle (SPA) loss that exploits inherent symmetry of aerial objects for self-supervised learning, resolving issues in previous methods where learning collapses when predictions for all three augmented views (original, rotated, and flipped) are consistently incorrect. Extensive experimental results demonstrate that ABBSPO achieves state-of-the-art performance, outperforming existing methods.

📄 PDF Abstract BibTeX arXiv:2512.10031

Code (0)

등록된 구현이 없습니다.

Tasks

Self-Supervised LearningObject Detection

Similar Papers 제목 키워드 기반

ABBSPO: Adaptive Bounding Box Scaling and Symmetric Prior based Orientation Prediction for Detecting Aerial Image Objects

2025-01-01 · CVPR 2025 1 · Woojin Lee, Hyugjae Chang, Jaeho Moon, Jaehyup Lee 외

Weakly supervised Oriented Object Detection (WS-OOD) has gained attention as a cost-effective alternative to fully supervised methods, providing efficiency and high accuracy. Among weakly supervised approaches, horiz…

object-detectionObject DetectionOriented Object DetectionSelf-Supervised Learning

Aligning Object Detector Bounding Boxes with Human Preference

2024-08-20 · Ombretta Strafforello, Osman S. Kayhan, Oana Inel, Klamer Schutte 외

Previous work shows that humans tend to prefer large bounding boxes over small bounding boxes with the same IoU. However, we show here that commonly used object detectors predict large and small boxes equally often. In t…

Object

Sketchy Bounding-box Supervision for 3D Instance Segmentation

2025-05-22 · CVPR 2025 1 · Qian Deng, Le Hui, Jin Xie, Jian Yang

Bounding box supervision has gained considerable attention in weakly supervised 3D instance segmentation. While this approach alleviates the need for extensive point-level annotations, obtaining accurate bounding boxes i…

3D Instance SegmentationInstance SegmentationSemantic Segmentation

SAGE: Sequence-level Adaptive Gradient Evolution for Generative Recommendation

2026-01-29 · Yu Xie, Xing Kai Ren, Ying Qi, Hu Yao arxiv

Reinforcement learning-based preference optimization is increasingly used to align list-wise generative recommenders with complex, multi-objective user feedback, yet existing optimizers such as Gradient-Bounded Policy Op…

Reinforcement Learning

AdaScale: Towards Real-time Video Object Detection Using Adaptive Scaling

2019-02-08 · Ting-Wu Chin, Ruizhou Ding, Diana Marculescu

In vision-enabled autonomous systems such as robots and autonomous cars, video object detection plays a crucial role, and both its speed and accuracy are important factors to provide reliable operation. The key insight w…

object-detectionObject DetectionVideo Object Detection