School of Computer Science, China University of Geosciences, No. 68 Jincheng Road, Wuhan 430078, China.
School of Computer, National University of Defense Technology, Deya Road, Changsha 410073, China.
Sensors (Basel). 2023 Jan 10;23(2):773. doi: 10.3390/s23020773.
As an auxiliary means of remote sensing (RS) intelligent interpretation, remote sensing scene classification (RSSC) attracts considerable attention and its performance has been improved significantly by the popular deep convolutional neural networks (DCNNs). However, there are still several challenges that hinder the practical applications of RSSC, such as complex composition of land cover, scale-variation of objects, and redundant and noisy areas for scene classification. In order to mitigate the impact of these issues, we propose an adaptive discriminative regions learning network for RSSC, referred as ADRL-Net briefly, which locates discriminative regions effectively for boosting the performance of RSSC by utilizing a novel self-supervision mechanism. Our proposed ADRL-Net consists of three main modules, including a discriminative region generator, a region discriminator, and a region scorer. Specifically, the discriminative region generator first generates some candidate regions which could be informative for RSSC. Then, the region discriminator evaluates the regions generated by region generator and provides feedback for the generator to update the informative regions. Finally, the region scorer makes prediction scores for the whole image by using the discriminative regions. In such a manner, the three modules of ADRL-Net can cooperate with each other and focus on the most informative regions of an image and reduce the interference of redundant regions for final classification, which is robust to the complex scene composition, object scales, and irrelevant information. In order to validate the efficacy of the proposed network, we conduct experiments on four widely used benchmark datasets, and the experimental results demonstrate that ADRL-Net consistently outperforms other state-of-the-art RSSC methods.
作为遥感智能解译的辅助手段，遥感场景分类（RSSC）吸引了相当多的关注，其性能通过流行的深度卷积神经网络（DCNN）得到了显著提高。然而，仍有几个挑战阻碍了 RSSC 的实际应用，例如土地覆盖的复杂组成、目标的尺度变化以及场景分类的冗余和嘈杂区域。为了减轻这些问题的影响，我们提出了一种用于 RSSC 的自适应判别区域学习网络，简称 ADRL-Net，它通过利用新颖的自监督机制有效地定位判别区域，从而提高 RSSC 的性能。我们提出的 ADRL-Net 由三个主要模块组成，包括判别区域生成器、区域判别器和区域评分器。具体来说，判别区域生成器首先生成一些候选区域，这些区域可能对 RSSC 有帮助。然后，区域判别器评估区域生成器生成的区域，并为生成器提供反馈，以更新有信息的区域。最后，区域评分器通过使用判别区域对整个图像进行预测评分。通过这种方式，ADRL-Net 的三个模块可以相互协作，关注图像中最有信息的区域，并减少冗余区域对最终分类的干扰，从而对复杂的场景组成、目标尺度和不相关信息具有鲁棒性。为了验证所提出网络的有效性，我们在四个广泛使用的基准数据集上进行了实验，实验结果表明 ADRL-Net 始终优于其他最先进的 RSSC 方法。
