Most generic object detectors are mainly built for standard object detection tasks such as COCO and PASCAL VOC. They might not work well and/or efficiently on tasks of other domains consisting of images that are visually different from standard datasets. To this end, many advances have been focused on adapting a general-purposed object detector with limited domain-specific designs. However, designing a successful task-specific detector requires extraneous manual experiments and parameter tuning through trial and error. In this paper, we first propose and examine a fully-automatic pipeline to design a fully-specialized detector (FSD) which mainly incorporates a neural-architectural-searched model by exploring ideal network structures over the backbone and task-specific head. On the DeepLesion dataset, extensive results show that FSD can achieve 3.1 mAP gain while using approximately 40% fewer parameters on binary lesion detection task and improved the mAP by around 10% on multi-type lesion detection task via our region-aware graph modeling compared with existing general-purposed medical lesion detection networks.

翻译：摘要：大多数通用目标检测器主要针对标准目标检测任务（如COCO和PASCAL VOC）构建。对于由视觉上不同于标准数据集的图像组成的其他领域任务，这些检测器可能无法良好和/或高效地工作。为此，许多研究专注于对通用目标检测器进行适应性改造，仅添加有限的领域专用设计。然而，设计一个成功的任务专用检测器需要大量额外的人工实验以及通过试错进行的参数调优。本文首先提出并检验了一种全自动流水线，用于设计完全专用检测器（FSD），该方法主要通过探索骨干网络和任务专用头部上的理想网络结构，整合了神经架构搜索模型。在DeepLesion数据集上的大量实验结果表明，与现有的通用医学病灶检测网络相比，在二分类病灶检测任务上，FSD可在使用约40%更少参数的情况下获得3.1个mAP的提升；通过我们提出的区域感知图建模，在多类型病灶检测任务上，mAP提升了约10%。