Enhancing Infrared Small Target Detection Robustness with Bi-Level Adversarial Framework

TL;DR

This paper introduces a bi-level adversarial framework with a hierarchical reinforced learning strategy and a spatial-frequency interaction network to improve the robustness of infrared small target detection against various corruptions, outperforming existing methods.

Contribution

It presents a novel bi-level optimization approach with dynamic adversarial learning and a spatial-frequency network to enhance detection robustness under challenging conditions.

Findings

Improves IOU by 21.96% across corruptions

Promotes 4.97% IOU on general benchmarks

Demonstrates robustness against diverse background disturbances

Abstract

The detection of small infrared targets against blurred and cluttered backgrounds has remained an enduring challenge. In recent years, learning-based schemes have become the mainstream methodology to establish the mapping directly. However, these methods are susceptible to the inherent complexities of changing backgrounds and real-world disturbances, leading to unreliable and compromised target estimations. In this work, we propose a bi-level adversarial framework to promote the robustness of detection in the presence of distinct corruptions. We first propose a bi-level optimization formulation to introduce dynamic adversarial learning. Specifically, it is composited by the learnable generation of corruptions to maximize the losses as the lower-level objective and the robustness promotion of detectors as the upper-level one. We also provide a hierarchical reinforced learning strategy to discover the most detrimental corruptions and balance the performance between robustness and accuracy. To better disentangle the corruptions from salient features, we also propose a spatial-frequency interaction network for target detection. Extensive experiments demonstrate our scheme remarkably improves 21.96% IOU across a wide array of corruptions and notably promotes 4.97% IOU on the general benchmark. The source codes are available at https://github.com/LiuZhu-CV/BALISTD.