CFC-Net: A Critical Feature Capturing Network for Arbitrary-Oriented Object Detection in Remote Sensing Images

TL;DR

CFC-Net introduces a novel framework that enhances object detection in remote sensing images by capturing critical features, refining anchors, and optimizing label assignment, leading to improved accuracy and real-time performance.

Contribution

The paper proposes a new network architecture with polarization attention, rotation anchor refinement, and dynamic anchor learning for better detection of arbitrarily oriented objects.

Findings

Achieves superior detection performance on multiple datasets.

Effectively refines anchors for better localization.

Provides real-time detection capabilities.

Abstract

Object detection in optical remote sensing images is an important and challenging task. In recent years, the methods based on convolutional neural networks have made good progress. However, due to the large variation in object scale, aspect ratio, and arbitrary orientation, the detection performance is difficult to be further improved. In this paper, we discuss the role of discriminative features in object detection, and then propose a Critical Feature Capturing Network (CFC-Net) to improve detection accuracy from three aspects: building powerful feature representation, refining preset anchors, and optimizing label assignment. Specifically, we first decouple the classification and regression features, and then construct robust critical features adapted to the respective tasks through the Polarization Attention Module (PAM). With the extracted discriminative regression features, the Rotation Anchor Refinement Module (R-ARM) performs localization refinement on preset horizontal anchors to obtain superior rotation anchors. Next, the Dynamic Anchor Learning (DAL) strategy is given to adaptively select high-quality anchors based on their ability to capture critical features. The proposed framework creates more powerful semantic representations for objects in remote sensing images and achieves high-performance real-time object detection. Experimental results on three remote sensing datasets including HRSC2016, DOTA, and UCAS-AOD show that our method achieves superior detection performance compared with many state-of-the-art approaches. Code and models are available at https://github.com/ming71/CFC-Net.