Supervised object detection and semantic segmentation require object or even
pixel level annotations. When there exist image level labels only, it is
challenging for weakly supervised algorithms to achieve accurate predictions.
The accuracy achieved by top weakly supervised algorithms is still
significantly lower than their fully supervised counterparts. In this paper, we
propose a novel weakly supervised curriculum learning pipeline for multi-label
object recognition, detection and semantic segmentation. In this pipeline, we
first obtain intermediate object localization and pixel labeling results for
the training images, and then use such results to train task-specific deep
networks in a fully supervised manner. The entire process consists of four
stages, including object localization in the training images, filtering and
fusing object instances, pixel labeling for the training images, and
task-specific network training. To obtain clean object instances in the
training images, we propose a novel algorithm for filtering, fusing and
classifying object instances collected from multiple solution mechanisms. In
this algorithm, we incorporate both metric learning and density-based
clustering to filter detected object instances. Experiments show that our
weakly supervised pipeline achieves state-of-the-art results in multi-label
image classification as well as weakly supervised object detection and very
competitive results in weakly supervised semantic segmentation on MS-COCO,
PASCAL VOC 2007 and PASCAL VOC 2012.

该论文提出了一种弱监督课程学习流程，用于多标签对象识别、检测和语义分割的任务，其中包括四个阶段，包括训练图像的对象定位、筛选和融合对象实例、像素标注以及基于任务的网络训练，通过这种流程，实现了在 MS-COCO、PASCAL VOC 2007 和 PASCAL VOC 2012 数据集上进行多标签图像分类以及弱监督对象检测和语义分割的最新成果。