.png){kind=icon}
返回
Oriented-DINO: Angle Decoupling Prediction and Consistency Optimizing for Oriented Detection Transformer
.png){kind=icon}
PRE
AI
DOI：10.1109/TGRS.2024.3450200.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Considering the arbitrary orientation of remote sensing objects, accurate angle prediction plays a crucial role in achieving precise oriented object detection (OOD) of aerial scenes. Existing transformer-based methods typically adopt an iterative refinement mechanism to update angle prediction and perform bipartite graph matching based on the combined matching costs. However, these methods may suffer from angle error accumulation across decoder layers and inconsistency between the L1 cost and the rotated intersection-of-union (IoU) cost, thus resulting in inaccurate angle prediction. To address these problems, this article proposes a novel transformer-based OOD method named Oriented-DINO (ODINO), which comprises three important components: error-mitigating angle decoupling prediction (EADP) module, nonlinear angle-conversion consistency optimizer (NACO), and query-driven diversity (QD) loss. To mitigate the angle error, the EADP module decouples angle prediction from the iterative box refinement process and uses independent branches to directly predict the angle. To address the issue of inconsistent matching, the NACO module uses a nonlinear function for angle conversion in matching cost calculation. This approach effectively alleviates the matching cost discrepancy in angle boundary case, while preserving the consistency in other instances. To avoid highly overlapped predictions triggered by similar queries, we introduce the QD loss to encourage the generation of diverse object queries, thus avoiding redundant predictions and enhancing prediction accuracy. Extensive experimental results demonstrate that our method achieves superior performance on OOD task.
Keyword:
Costs
Transformers
Feature extraction
Object detection
Detectors
Proposals
Decoding
Aerial scenes
detection transformer (DETR)
matching cost
oriented object detection (OOD)
期刊
IF:
8.6
论文数:
2.2W
被引数:
10.7W
机构
暂无机构信息
引用论文
Conductivity Enhancement in Thin Silicon-on-Insulator Layer Embedding Artificial Dislocation Network
.png){kind=icon}
PREAI
分享收藏Inflexibility of mental planning: A characteristic disorder with prefrontal lobe lesions?心理计划的僵化: 前额叶病变的特征性障碍？
PREAI
分享收藏
ARS-DETR: Aspect Ratio-Sensitive Detection Transformer for Aerial Oriented Object DetectionArs-detr: 用于面向空中目标检测的纵横比敏感检测变压器
OAAI
OAAI分享收藏A General Gaussian Heatmap Label Assignment for Arbitrary-Oriented Object Detection面向任意对象检测的通用高斯热图标签分配OAAI
OAAI分享收藏
查看更多内容