当前位置: X-MOL 学术IEEE Trans. Pattern Anal. Mach. Intell. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Towards Partial Supervision for Generic Object Counting in Natural Scenes
IEEE Transactions on Pattern Analysis and Machine Intelligence ( IF 23.6 ) Pub Date : 2020-09-01 , DOI: 10.1109/tpami.2020.3021025
Hisham Cholakkal 1 , Guolei Sun 2 , Salman Khan 1 , Fahad Shahbaz Khan 1 , Ling Shao 1, 3 , Luc Van Gool 2
Affiliation  

Generic object counting in natural scenes is a challenging computer vision problem. Existing approaches either rely on instance-level supervision or absolute count information to train a generic object counter. We introduce a partially supervised setting that significantly reduces the supervision level required for generic object counting. We propose two novel frameworks, named lower-count (LC) and reduced lower-count (RLC), to enable object counting under this setting. Our frameworks are built on a novel dual-branch architecture that has an image classification and a density branch. Our LC framework reduces the annotation cost due to multiple instances in an image by using only lower-count supervision for all object categories. Our RLC framework further reduces the annotation cost arising from large numbers of object categories in a dataset by only using lower-count supervision for a subset of categories and class-labels for the remaining ones. The RLC framework extends our dual-branch LC framework with a novel weight modulation layer and a category-independent density map prediction. Experiments are performed on COCO, Visual Genome and PASCAL 2007 datasets. Our frameworks perform on par with state-of-the-art approaches using higher levels of supervision. Additionally, we demonstrate the applicability of our LC supervised density map for image-level supervised instance segmentation.

中文翻译:

自然场景中通用对象计数的部分监督

自然场景中的通用对象计数是一个具有挑战性的计算机视觉问题。现有方法要么依赖实例级监督,要么依赖绝对计数信息来训练通用对象计数器。我们引入了部分监督设置,显着降低了通用对象计数所需的监督级别。我们提出了两个新颖的框架,称为低计数 (LC) 和减少低计数 (RLC),以在此设置下启用对象计数。我们的框架建立在具有图像分类和密度分支的新型双分支架构上。我们的 LC 框架通过仅对所有对象类别使用较低计数的监督来降低由于图像中的多个实例而导致的注释成本。我们的 RLC 框架进一步降低了由数据集中大量对象类别引起的注释成本,方法是仅对类别子集使用较低计数的监督,对其余类别使用类标签。RLC 框架扩展了我们的双分支 LC 框架,具有新颖的权重调制层和与类别无关的密度图预测。实验在 COCO、Visual Genome 和 PASCAL 2007 数据集上进行。我们的框架与使用更高级别监督的最先进方法的性能相当。此外,我们展示了我们的 LC 监督密度图对图像级监督实例分割的适用性。RLC 框架扩展了我们的双分支 LC 框架,具有新颖的权重调制层和与类别无关的密度图预测。实验在 COCO、Visual Genome 和 PASCAL 2007 数据集上进行。我们的框架与使用更高级别监督的最先进方法的性能相当。此外,我们展示了我们的 LC 监督密度图对图像级监督实例分割的适用性。RLC 框架扩展了我们的双分支 LC 框架,具有新颖的权重调制层和与类别无关的密度图预测。实验在 COCO、Visual Genome 和 PASCAL 2007 数据集上进行。我们的框架与使用更高级别监督的最先进方法的性能相当。此外,我们展示了我们的 LC 监督密度图对图像级监督实例分割的适用性。
更新日期:2020-09-01
down
wechat
bug