Decoupled Spatial Neural Attention for Weakly Supervised Semantic Segmentation
- 3 May 2019
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 21 (11) , 2930-2941
Abstract
Weakly supervised semantic segmentation receives much research attention since it alleviates the need to obtain a large amount of dense pixel-wise ground-truth annotations for the training images. Compared with other forms of weak supervision, image labels are quite efficient to obtain. In our work, we focus on the weakly supervised semantic segmentation with image label annotations. Recent progress for this task has been largely dependent on the quality of generated pseudo-annotations. In this work, inspired by spatial neural-attention for image captioning, we propose a decoupled spatial neural attention network for generating pseudo-annotations. Our decoupled attention structure could simultaneously identify the object regions and localize the discriminative parts which generates high-quality pseudo-annotations in one forward path. The generated pseudo-annotations lead to the segmentation results which achieve the state-of-the-art in weakly-supervised semantic segmentation.Keywords
All Related Versions
Funding Information
- National Research Foundation Singapore
- Infocomm Media Development Authority, Singapore
- National Research Foundation Singapore
- AI Singapore Programme (AISG-RP-2018-003)
This publication has 48 references indexed in Scilit:
- Built-in Foreground/Background Prior for Weakly-Supervised Semantic Segmentation2016
- Clothes Co-Parsing Via Joint Image Segmentation and Labeling With Application to Clothing RetrievalIEEE Transactions on Multimedia, 2016
- BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation2015
- Weakly-and Semi-Supervised Learning of a Deep Convolutional Network for Semantic Image Segmentation2015
- Conditional Random Fields as Recurrent Neural Networks2015
- Learning Deconvolution Network for Semantic Segmentation2015
- Fashion Parsing With Video ContextIEEE Transactions on Multimedia, 2015
- From image-level to pixel-level labeling with Convolutional Networks2015
- Fully convolutional networks for semantic segmentation2015
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009