论文标题
级联细心的辍学，用于弱监督对象检测
Cascade Attentive Dropout for Weakly Supervised Object Detection
论文作者
论文摘要
弱监督的对象检测（WSOD）旨在仅使用图像级监督进行分类和定位对象。许多WSOD方法采用多个实例学习作为初始模型，在忽略整个对象的同时，很容易收敛到最歧视的对象区域，因此降低了模型检测性能。在本文中，提出了一种新颖的级联辍学策略，以减轻零件的统治问题，并有改进的全球上下文模块。我们故意丢弃渠道和空间维度的细心元素，并捕获像素间和通道间的依赖性，以诱导模型以更好地了解全局上下文。对挑战性的Pascal VOC 2007基准进行了广泛的实验，该基准获得了49.8％的地图和66.0％的Corloc，表现优于最先进。
Weakly supervised object detection (WSOD) aims to classify and locate objects with only image-level supervision. Many WSOD approaches adopt multiple instance learning as the initial model, which is prone to converge to the most discriminative object regions while ignoring the whole object, and therefore reduce the model detection performance. In this paper, a novel cascade attentive dropout strategy is proposed to alleviate the part domination problem, together with an improved global context module. We purposely discard attentive elements in both channel and space dimensions, and capture the inter-pixel and inter-channel dependencies to induce the model to better understand the global context. Extensive experiments have been conducted on the challenging PASCAL VOC 2007 benchmarks, which achieve 49.8% mAP and 66.0% CorLoc, outperforming state-of-the-arts.
