Weakly supervised object detection (WSOD) in remote sensing images remains a challenging task when learning object detectors with only image-level labels. As we know, object proposal generation plays a crucial role in WSOD. At present, the proposal generation of most existing WSOD methods mainly relies on heuristic strategies such as selective search and Edge Boxes. However, the proposals obtained by the above methods cannot well cover the entire objects, severely hindering the performance of WSOD. To address this issue, this article proposes a Self-guided Proposal Generation approach, termed SPG. It can be easily implemented with most WSOD methods in a unified framework. To this end, we first introduce a confidence propagation approach to obtain the objectness confidence map for each image, which, on the one hand, highlights informative object locations and, on the other hand, aggregates discriminative feature representation by combining the objectness confidence map with the deep features. Then, the proposal generation is implemented by mining informative regions as proposals on the objectness confidence map. Extensive evaluations on two challenging datasets demonstrate that our SPG significantly improves the baseline methods, online instance classifier refinement (OICR) and min-entropy latent model (MELM), by large margins (for OICR: 15.86% mAP and 12.89% CorLoc gains on the NWPU VHR-10.v2 dataset and 3.65% mAP and 4.87% CorLoc gains on the DIOR dataset; for MELM: 20.51% mAP and 23.54% CorLoc gains on the NWPU VHR-10.v2 dataset and 7.11% mAP and 4.96% CorLoc gains on the DIOR dataset) and achieves the state-of-the-art results compared with existing methods.

中文翻译：

---

用于弱监督目标检测的自引导建议生成

当学习仅具有图像级标签的对象检测器时，遥感图像中的弱监督对象检测 (WSOD) 仍然是一项具有挑战性的任务。众所周知，对象建议生成在 WSOD 中起着至关重要的作用。目前，大多数现有 WSOD 方法的提案生成主要依赖于启发式策略，例如选择性搜索和边缘框。然而，上述方法得到的proposals并不能很好地覆盖整个对象，严重阻碍了WSOD的性能。为了解决这个问题，本文提出了一种自我指导的提案生成方法，称为 SPG。它可以在一个统一的框架中使用大多数 WSOD 方法轻松实现。为此，我们首先引入了一种置信度传播方法来获得每个图像的对象置信度图，一方面，突出信息丰富的对象位置，另一方面，通过将对象置信度图与深度特征相结合来聚合判别特征表示。然后，通过在对象置信度图上挖掘信息区域作为建议来实现建议生成。对两个具有挑战性的数据集的广泛评估表明，我们的 SPG 显着改进了基线方法、在线实例分类器细化 (OICR) 和最小熵潜在模型 (MELM)，大幅提高了（对于 OICR：15.86% mAP 和 12.89% CorLoc 在NWPU VHR-10.v2 数据集和 DIOR 数据集上 3.65% 的 mAP 和 4.87% CorLoc 增益；对于 MELM：NWPU VHR-10.v2 数据集上 20.51% 的 mAP 和 23.54% CorLoc 增益以及 7.11% 的 mAP 和 4。