Enhancing Fine-grained Object Detection in Aerial Images via Orthogonal Mapping

TL;DR

This paper proposes Orthogonal Mapping, a novel method that reduces semantic confusion in fine-grained object detection in aerial images by enforcing orthogonal constraints in feature space, leading to improved accuracy.

Contribution

It introduces Orthogonal Mapping, a simple technique that can be integrated into existing detectors to enhance fine-grained object detection performance.

Findings

Achieves 4.08% mAP improvement over FCOS on ShipRSImageNet

Effectively reduces semantic confusion in FGOD tasks

Demonstrates superior performance on three FGOD datasets

Abstract

Fine-Grained Object Detection (FGOD) is a critical task in high-resolution aerial image analysis. This letter introduces Orthogonal Mapping (OM), a simple yet effective method aimed at addressing the challenge of semantic confusion inherent in FGOD. OM introduces orthogonal constraints in the feature space by decoupling features from the last layer of the classification branch with a class-wise orthogonal vector basis. This effectively mitigates semantic confusion and enhances classification accuracy. Moreover, OM can be seamlessly integrated into mainstream object detectors. Extensive experiments conducted on three FGOD datasets (FAIR1M, ShipRSImageNet, and MAR20) demonstrate the effectiveness and superiority of the proposed approach. Notably, with just one line of code, OM achieves a 4.08% improvement in mean Average Precision (mAP) over FCOS on the ShipRSImageNet dataset. Codes are released at https://github.com/ZhuHaoranEIS/Orthogonal-FGOD.