Learning Transferrable Knowledge for Semantic Segmentation with Deep Convolutional Neural Network

Citations Over TimeTop 1% of 2016 papers

Abstract

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 with only image-level class labels. To make segmentation knowledge transferrable across categories, we design a decoupled encoder-decoder architecture with attention model. In this architecture, the model generates spatial highlights of each category presented in images using an attention model, and subsequently performs binary segmentation for each highlighted region using decoder. Combining attention model, the decoder trained with segmentation annotations in different categories boosts accuracy of weakly-supervised semantic segmentation. The proposed algorithm demonstrates substantially improved performance compared to the state-of-theart weakly-supervised techniques in PASCAL VOC 2012 dataset when our model is trained with the annotations in 60 exclusive categories in Microsoft COCO dataset.

Related Papers

• → Medical Image Segmentation(2013)11 cited
• → A real-time parallel combination segmentation method for aluminum surface defect images(2015)8 cited
• → Application of Convolutional Neural Network for Image Classification on\n Pascal VOC Challenge 2012 dataset(2016)18 cited
• → Application of Convolutional Neural Network for Image Classification on Pascal VOC Challenge 2012 dataset(2016)15 cited
• Application of a new improved image segmentation algorithm in car plate recognition(2010)