Weakly-Supervised Image Parsing via Constructing Semantic Graphs and Hypergraphs
@article{Xie2014WeaklySupervisedIP, title={Weakly-Supervised Image Parsing via Constructing Semantic Graphs and Hypergraphs}, author={Wenxuan Xie and Y. Peng and J. Xiao}, journal={Proceedings of the 22nd ACM international conference on Multimedia}, year={2014} }
In this paper, we address the problem of weakly-supervised image parsing, whose aim is to automatically determine the class labels of image regions given image-level labels only. [...] Key Method We develop two novel graphs by leveraging the weak supervision information carefully: 1) Semantic graph, which is established upon a conventional graph by utilizing the proposed weakly-supervised criteria; 2) Semantic hypergraph, which explores both intra-image and inter-image high-order semantic relevance…Expand Abstract
Figures, Tables, and Topics from this paper
12 Citations
Weakly supervised image parsing via label propagation over discriminatively semantic graph
- Mathematics, Computer Science
- J. Vis. Commun. Image Represent.
- 2016
- 2
Weakly supervised image parsing by discriminatively semantic graph propagation
- Computer Science
- 2016 IEEE International Conference on Multimedia and Expo (ICME)
- 2016
- Highly Influenced
Simultaneous semantic segmentation of a set of partially labeled images
- Computer Science
- 2016 IEEE Winter Conference on Applications of Computer Vision (WACV)
- 2016
- PDF
Saliency Guided Dictionary Learning for Weakly-Supervised Image Parsing
- Computer Science
- 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- 2016
- 20
- Highly Influenced
- PDF
Semantic Segmentation based on Stacked Discriminative Autoencoders and Context-Constrained Weakly Supervised Learning
- Computer Science
- ACM Multimedia
- 2015
- 10
Semi- and Weakly- Supervised Semantic Segmentation with Deep Convolutional Neural Networks
- Computer Science
- ACM Multimedia
- 2015
- 6
Structured sparse graphs using manifold constraints for visual data analysis
- Computer Science
- Neurocomputing
- 2018
- 1
Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentation
- Computer Science
- ECCV
- 2016
- 310
- PDF
References
SHOWING 1-3 OF 3 REFERENCES
Weakly Supervised Graph Propagation Towards Collective Image Parsing
- Computer Science
- IEEE Transactions on Multimedia
- 2012
- 50
- Highly Influential
- PDF
Label to region by bi-layer sparsity priors
- Computer Science
- ACM Multimedia
- 2009
- 89
- Highly Influential
- PDF
Learning with hypergraphs: Clustering
- classification, and embedding. NIPS, 19:1601–1608
- 2007