论文标题
浮点：对对象属性的分解学习，以改进多个目标多部分场景解析
FLOAT: Factorized Learning of Object Attributes for Improved Multi-object Multi-part Scene Parsing
论文作者
论文摘要
多目标多部分场景解析是一项具有挑战性的任务，需要检测场景中的多个对象类并分割每个对象中的语义部分。在本文中，我们提出了Float，这是一个分解的标签空间框架，用于可扩展的多对象多部分解析。我们的框架涉及对象类别的独立密集预测和零件属性，这些预测可提高可扩展性并降低任务复杂性与单片标签空间对应物相比。此外，我们提出了一种推理时间“变焦”精炼技术，可显着提高细分质量，尤其是对于较小的物体/零件。与最新状态相比，Float在Pascal-Part-58数据集中获得了平均值（MIOU）的绝对改善2.0％，而分割质量IOU（SQIOU）的绝对提高为4.8％。对于较大的Pascal-Part-108数据集，MIOU的改进为2.1％，SQIOU的改善为3.9％。我们将先前排除在Pascal-Part数据集的零件属性和其他次要部分结合在一起，以创建最全面，最具挑战性的版本，我们将其配音Pascal-Part-2010。 Float在新数据集中获得了MIOU的8.6％的改善，SQIOU的改善为7.5％，证明了其在具有挑战性的物体和零件的多样性中的解析有效性。代码和数据集可在floatseg.github.io上找到。
Multi-object multi-part scene parsing is a challenging task which requires detecting multiple object classes in a scene and segmenting the semantic parts within each object. In this paper, we propose FLOAT, a factorized label space framework for scalable multi-object multi-part parsing. Our framework involves independent dense prediction of object category and part attributes which increases scalability and reduces task complexity compared to the monolithic label space counterpart. In addition, we propose an inference-time 'zoom' refinement technique which significantly improves segmentation quality, especially for smaller objects/parts. Compared to state of the art, FLOAT obtains an absolute improvement of 2.0% for mean IOU (mIOU) and 4.8% for segmentation quality IOU (sqIOU) on the Pascal-Part-58 dataset. For the larger Pascal-Part-108 dataset, the improvements are 2.1% for mIOU and 3.9% for sqIOU. We incorporate previously excluded part attributes and other minor parts of the Pascal-Part dataset to create the most comprehensive and challenging version which we dub Pascal-Part-201. FLOAT obtains improvements of 8.6% for mIOU and 7.5% for sqIOU on the new dataset, demonstrating its parsing effectiveness across a challenging diversity of objects and parts. The code and datasets are available at floatseg.github.io.
