Weakly-supervised segmentation by combining CNN feature maps and object saliency maps
Wataru Shimoda, Keiji Yanai · 2016
In general, CNN based semantic segmentation methods assume pixel-wise annotation is available, which is costly to obtain in general. On the other hand, image-level annotations is much easier to obtain than pixel-level annotation. Then, in this work, we focus on weakly-supervised semantic segmentation which is known as task of using training data with only image-level annotations. In this paper, we propose a new CNN-based semantic segmentation method which uses both activation features calculated by feed-forwarding and object saliency maps obtained by back-propagation. As a CNN, we use the VGG-16 pre-trained with 1000-class ILSVRC datasets and fine-tuned it with multi-label training using only image-level labeled dataset. By the experiments, we show that the proposed method achieved state-of-the-art results with the PASCAL VOC 2012 dataset.