Classification Matters More: Global Instance Contrast for Fine-grained SAR Aircraft Detection

Since significant intra-class differences and inconspicuous inter-class variations, fine-grained aircraft detection in synthetic aperture radar (SAR) images is challenging. And the inherent lack of detailed features and severe noise interference in SAR images make it difficult to learn class-specifi...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on geoscience and remote sensing 2023-01, Vol.61, p.1-1
Main Authors: Zhao, Danpei, Chen, Ziqiang, Gao, Yue, Shi, Zhenwei
Format: Article
Language:English
Subjects:
Aircraft
Aircraft detection
Classification
Detection
Detectors
edge-aware box refinement
Feature extraction
Fine-grained detection
global instance contrast
Localization
Location awareness
Modules
quality-aware focal loss
Radar detection
Radar imaging
SAR (radar)
Synthetic aperture radar
synthetic aperture radar (SAR)
Task analysis
Training
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Since significant intra-class differences and inconspicuous inter-class variations, fine-grained aircraft detection in synthetic aperture radar (SAR) images is challenging. And the inherent lack of detailed features and severe noise interference in SAR images make it difficult to learn class-specific feature representations. Current detection approaches focus more on localization accuracy and ignore classification performance, which is more critical in fine-grained detection. To address the above challenges, we present GICNet: Global Instance Contrast for fine-grained SAR aircraft detection. A Global Instance-level Contrast (GIC) module is proposed to improve inter-class divergences and intra-class compactness. With a specially constructed global instance set, GICNet can contrast a large number of different aircraft targets while keeping a small batch size. Furthermore, we design a novel quality-aware focal loss (QAFL) to facilitate the accurate classification of well-localized aircraft targets. Meanwhile, to maintain localization performance, we develop a new edge-aware bounding-box refinement (EABR) module to refine predicted coarse bounding boxes. Experimental results show that our GICNet outperforms current advanced detectors and achieves a new state-of-the-art performance on the GaoFen-3 SAR aircraft detection dataset. Especially, GICNet also has advantages in reducing misclassification and recognizing well-located targets.
ISSN:0196-2892
1558-0644
DOI:10.1109/TGRS.2023.3250507