Projects per year
Abstract / Description of output
Deep learning approaches heavily rely on high-quality human supervision which is nonetheless expensive, time-consuming, and error-prone, especially for image segmentation task. In this paper, we propose a method to automatically synthesize paired photo-realistic images and segmentation masks for the use of training a foreground-background segmentation network. In particular, we learn a generative adversarial network that decomposes an image into foreground and background layers, and avoid trivial decompositions by maximizing mutual information between generated images and latent variables. The improved layered GANs can synthesize higher quality datasets from which segmentation networks of higher performance can be learned. Moreover, the segmentation networks are employed to stabilize the training of layered GANs in return, which are further alternately trained with Layered GANs. Experiments on a variety of single-object datasets show that our method achieves competitive generation quality and segmentation performance compared to related methods.
Original language | English |
---|---|
Title of host publication | Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision |
Publisher | Institute of Electrical and Electronics Engineers |
Pages | 366-375 |
Number of pages | 10 |
ISBN (Electronic) | 978-1-6654-0915-5 |
ISBN (Print) | 978-1-6654-0916-2 |
DOIs | |
Publication status | Published - 15 Feb 2022 |
Event | 2022 IEEE Winter Conference on Applications of Computer Vision - Waikoloa, United States Duration: 4 Jan 2022 → 8 Jan 2022 https://wacv2022.thecvf.com/ |
Publication series
Name | IEEE Workshop on Applications of Computer Vision (WACV) |
---|---|
Publisher | IEEE |
ISSN (Print) | 2472-6737 |
ISSN (Electronic) | 2642-9381 |
Conference
Conference | 2022 IEEE Winter Conference on Applications of Computer Vision |
---|---|
Abbreviated title | WACV 2022 |
Country/Territory | United States |
City | Waikoloa |
Period | 4/01/22 → 8/01/22 |
Internet address |
Keywords / Materials (for Non-textual outputs)
- Machine learning
- Computer Vision
- Unsupervised Learning
- Generative adversarial network
Fingerprint
Dive into the research topics of 'Learning Foreground-Background Segmentation from Improved Layered GANs'. Together they form a unique fingerprint.Projects
- 1 Active
-
Visual AI: An Open World Interpretable Visual Transformer
Engineering and Physical Sciences Research Council
1/12/20 → 30/11/26
Project: Research