Instance search is an interesting task as well as a challenging issue due to the lack of effective feature representation. In this paper, an instance level feature representation built upon fully convolutional instance-aware segmentation is proposed. The feature is ROI-pooled from the segmented instance region. So that instances in various sizes and layouts are represented by deep features in uniform length. This representation is further enhanced by the use of deformable ResNeXt blocks. Superior performance is observed in terms of its distinctiveness and scalability on a challenging evaluation dataset built by ourselves. In addition, the proposed enhancement on the network structure also shows superior performance on the instance segmentation task.

由于缺乏有效的特征表示，实例搜索是一项有趣的任务，也是一个具有挑战性的问题。在本文中，提出了一种基于完全卷积实例感知分割的实例级特征表示。该特征是从分割的实例区域中汇集的 ROI。因此，各种大小和布局的实例都由长度一致的深层特征表示。使用可变形 ResNeXt 块进一步增强了这种表示。在我们自己构建的具有挑战性的评估数据集上，在其独特性和可扩展性方面观察到了卓越的性能。此外，所提出的对网络结构的增强也显示出在实例分割任务上的优越性能。