MA2-FPN for Tiny Object Detection from Remote Sensing Images

Tiny object detection has been a challenging topic in computer vision recent years. Moreover, in remote sensing field, smaller and clustered tiny objects make its detection more difficult compared to ground-based images. This makes general detectors fail to achieve good performance when facing tiny...

Full description

Saved in:
Bibliographic Details
Published in2022 15th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI) pp. 1 - 8
Main Authors Li, Saiwei, Tong, Qiang, Liu, Xuhong, Cui, Zhanqi, Liu, Xiulei
Format Conference Proceeding
LanguageEnglish
Published IEEE 05.11.2022
Subjects
Aggregates
Attention Mechanism
Computer vision
Convolution
Detectors
Feature extraction
Feature Pyramid Network
Image segmentation
Object detection
Remote Sensing
Tiny Object Detection
Online AccessGet full text

Cover

More Information
Summary:Tiny object detection has been a challenging topic in computer vision recent years. Moreover, in remote sensing field, smaller and clustered tiny objects make its detection more difficult compared to ground-based images. This makes general detectors fail to achieve good performance when facing tiny objects in remote sensing images. In this paper, we propose a Mask Augmented Attention Feature Pyramid Network(MA 2 -FPN) to detect tiny objects in remote sensing images, which consists of two modules, Attention Enhancement Module(AEM) and Mask Supervision Module(MSM). Specifically, AEM aggregates tiny target context and spatial feature information by large kernel separable convolutional attention mechanism, and MSM supervises AEM through a segmentation attention loss to aggregate attention information more accurately while suppressing the influence of irrelevant background. Experiments based on the AI-TOD benchmark show that our MA 2 -FPN achieves state-of-the-art(SOTA) level.
DOI:10.1109/CISP-BMEI56279.2022.9980328