Learning Transferrable Knowledge for Semantic Segmentation with Deep Convolutional Neural Network

• Published in: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) pp. 3204 - 3212
• Main Authors: Seunghoon Hong, Junhyuk Oh, Honglak Lee, Bohyung Han
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2016
• Subjects: Adaptation models; Computer architecture; Decoding; Feature extraction; Image segmentation; Semantics; Training

We propose a novel weakly-supervised semantic segmentation algorithm based on Deep Convolutional Neural Network (DCNN). Contrary to existing weakly-supervised approaches, our algorithm exploits auxiliary segmentation annotations available for different categories to guide segmentations on images wit...