Oriented-DINO: Angle Decoupling Prediction and Consistency Optimizing for Oriented Detection Transformer

doi:10.1109/TGRS.2024.3450200

Oriented-DINO: Angle Decoupling Prediction and Consistency Optimizing for Oriented Detection Transformer

2024-01-01

1

PRE

AI

DOI：10.1109/TGRS.2024.3450200

Original

Original request for help

Save

Abstract

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.

Keywords:

Costs

Transformers

Feature extraction

Object detection

Detectors

Proposals

Decoding

Aerial scenes

detection transformer (DETR)

matching cost

oriented object detection (OOD)

Oriented-DINO: Angle Decoupling Prediction and Consistency Optimizing for Oriented Detection Transformer

Abstract

Journal

Organization