Identifying tiny objects from extremely low-resolution (LR) unmanned-aerial-vehicle-based remote sensing images is generally considered as a very challenging task, because of very limited information in the object areas. In recent years, there have been very limited attempts to approach this problem. These attempts intend to deal with LR image classification by enhancing either the poor image quality or image representations. In this article, we argue that the performance improvement in LR image classification is affected by the inconsistency of the information loss and learning priority on low-frequency (LF) components and high-frequency (HF) components. To address this LF–HF inconsistency problem, we propose a dual-stream representation learning generative adversarial network (DRL-GAN). The core idea is to produce enhanced image representations optimal for LR recognition by simultaneously recovering the missing information in LF and HF components, respectively, under the guidance of high-resolution (HR) images. We evaluate the performance of DRL-GAN on the challenging task of LR image classification. A comparison of the experimental results on the LR benchmark, namely HRSC and CIFAR-10, and our newly collected ‘WIDER-SHIP’ dataset demonstrates the effectiveness of our DRL-GAN, which significantly improves the classification performance, with up to 10% gain on average.

中文翻译：

---

DRL-GAN：无人机应用中用于低分辨率图像分类的双流表示学习 GAN

从基于极低分辨率 (LR) 无人机的遥感图像中识别微小物体通常被认为是一项非常具有挑战性的任务，因为物体区域的信息非常有限。近年来，解决这个问题的尝试非常有限。这些尝试旨在通过​​增强较差的图像质量或图像表示来处理 LR 图像分类。在本文中，我们认为 LR 图像分类的性能改进受到低频 (LF) 分量和高频 (HF) 分量的信息丢失和学习优先级不一致的影响。为了解决这个 LF-HF 不一致问题，我们提出了一种双流表示学习生成对抗网络（DRL-GAN）。核心思想是在高分辨率 (HR) 图像的指导下，通过同时恢复 LF 和 HF 分量中的缺失信息，生成最适合 LR 识别的增强图像表示。我们评估了 DRL-GAN 在 LR 图像分类这一具有挑战性的任务上的性能。LR 基准（即 HRSC 和 CIFAR-10）上的实验结果与我们新收集的“WIDER-SHIP”数据集的比较证明了我们的 DRL-GAN 的有效性，它显着提高了分类性能，增益高达 10%一般。