Weakly supervised semantic segmentation using superpixel pooling network

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 38
  • Download : 0
We propose a weakly supervised semantic segmentation algorithm based on deep neural networks, which relies on imagelevel class labels only. The proposed algorithm alternates between generating segmentation annotations and learning a semantic segmentation network using the generated annotations. A key determinant of success in this framework is the capability to construct reliable initial annotations given image-level labels only. To this end, we propose Superpixel Pooling Network (SPN), which utilizes superpixel segmentation of input image as a pooling layout to reflect low-level image structure for learning and inferring semantic segmentation. The initial annotations generated by SPN are then used to learn another neural network that estimates pixelwise semantic labels. The architecture of the segmentation network decouples semantic segmentation task into classification and segmentation so that the network learns classagnostic shape prior from the noisy annotations. It turns out that both networks are critical to improve semantic segmentation accuracy. The proposed algorithm achieves outstanding performance in weakly supervised semantic segmentation task compared to existing techniques on the challenging PASCAL VOC 2012 segmentation benchmark.
Association for the Advancement of Artificial Intelligence (AAAI)
Issue Date

31st AAAI Conference on Artificial Intelligence, AAAI 2017, pp.4111 - 4117

Appears in Collection
RIMS Conference Papers
Files in This Item
There are no files associated with this item.


  • mendeley


rss_1.0 rss_2.0 atom_1.0