OSAD: Open-Set Aircraft Detection in SAR Images

TL;DR

This paper introduces OSAD, a novel open-set aircraft detection method for SAR images that improves unknown object detection and generalization without sacrificing known object detection performance.

Contribution

The paper proposes a new open-set detection framework with three components: GCM, LPG, and PCL, enhancing robustness and reducing classification risk in SAR image object detection.

Findings

Achieves up to 18.36% improvement in unknown object average precision.

Effectively detects unknown objects while maintaining closed-set performance.

Demonstrates superior generalization to open environments.

Abstract

Current mainstream SAR image object detection methods still lack robustness when dealing with unknown objects in open environments. Open-set detection aims to enable detectors trained on a closed set to detect all known objects and identify unknown objects in open-set environments. The key challenges are how to improve the generalization to potential unknown objects and reduce the empirical classification risk of known categories under strong supervision. To address these challenges, a novel open-set aircraft detector for SAR images is proposed, named Open-Set Aircraft Detection (OSAD), which is equipped with three dedicated components: global context modeling (GCM), location quality-driven pseudo labeling generation (LPG), and prototype contrastive learning (PCL). GCM effectively enhances the network's representation of objects by attention maps which is formed through the capture of long sequential positional relationships. LPG leverages clues about object positions and shapes to optimize localization quality, avoiding overfitting to known category information and enhancing generalization to potential unknown objects. PCL employs prototype-based contrastive encoding loss to promote instance-level intra-class compactness and inter-class variance, aiming to minimize the overlap between known and unknown distributions and reduce the empirical classification risk of known categories. Extensive experiments have demonstrated that the proposed method can effectively detect unknown objects and exhibit competitive performance without compromising closed-set performance. The highest absolute gain which ranges from 0 to 18.36% can be achieved on the average precision of unknown objects.