Details
| Original language | English |
|---|---|
| Title of host publication | 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) |
| Subtitle of host publication | Proceedings |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 560-568 |
| Number of pages | 9 |
| ISBN (electronic) | 978-1-7281-5023-9 |
| ISBN (print) | 978-1-7281-5024-6 |
| Publication status | Published - Oct 2019 |
| Event | 2019 IEEE/CVF 17th International Conference on Computer Vision Workshop (ICCVW) - Seoul, Korea, Republic of Duration: 27 Oct 2019 → 28 Oct 2019 |
Publication series
| Name | IEEE International Conference on Computer Vision Workshops |
|---|---|
| ISSN (Print) | 2473-9936 |
| ISSN (electronic) | 2473-9944 |
Abstract
Image generating neural networks are mostly viewed as black boxes, where any change in the input can have a number of globally effective changes on the output. In this work, we propose a method for learning disentangled representations to allow for localized image manipulations. We use face images as our example of choice. Depending on the image region, identity and other facial attributes can be modified. The proposed network can transfer parts of a face such as shape and color of eyes, hair, mouth, etc.directly between persons while all other parts of the face remain unchanged. The network allows to generate modified images which appear like realistic images. Our model learns disentangled representations by weak supervision. We propose a localized resnet autoencoder optimized using several loss functions including a loss based on the semantic segmentation, which we interpret as masks, and a loss which enforces disentanglement by decomposition of the latent space into statistically independent subspaces. We evaluate the proposed solution w.r.t. disentanglement and generated image quality. Convincing results are demonstrated using the CelebA dataset.
Keywords
- Autoencoders, Face image editing, Independent subspace analysis, Latent space editing, Machine learning
ASJC Scopus subject areas
- Computer Science(all)
- Computer Science Applications
- Computer Science(all)
- Computer Vision and Pattern Recognition
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW): Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. p. 560-568 9022161 (IEEE International Conference on Computer Vision Workshops).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Learning disentangled representations via independent subspaces
AU - Awiszus, Maren
AU - Ackermann, Hanno
AU - Rosenhahn, Bodo
N1 - Funding information: The work is inspired by BIAS (”Bias and Discrimination in Big Data and Algorithmic Processing. Philosophical Assessments, Legal Dimensions, and Technical Solutions”), a project funded by the Volkswagen Foundation within the initiative ”AI and the Society of the Future” for which the last author is a Principal Investigator.
PY - 2019/10
Y1 - 2019/10
N2 - Image generating neural networks are mostly viewed as black boxes, where any change in the input can have a number of globally effective changes on the output. In this work, we propose a method for learning disentangled representations to allow for localized image manipulations. We use face images as our example of choice. Depending on the image region, identity and other facial attributes can be modified. The proposed network can transfer parts of a face such as shape and color of eyes, hair, mouth, etc.directly between persons while all other parts of the face remain unchanged. The network allows to generate modified images which appear like realistic images. Our model learns disentangled representations by weak supervision. We propose a localized resnet autoencoder optimized using several loss functions including a loss based on the semantic segmentation, which we interpret as masks, and a loss which enforces disentanglement by decomposition of the latent space into statistically independent subspaces. We evaluate the proposed solution w.r.t. disentanglement and generated image quality. Convincing results are demonstrated using the CelebA dataset.
AB - Image generating neural networks are mostly viewed as black boxes, where any change in the input can have a number of globally effective changes on the output. In this work, we propose a method for learning disentangled representations to allow for localized image manipulations. We use face images as our example of choice. Depending on the image region, identity and other facial attributes can be modified. The proposed network can transfer parts of a face such as shape and color of eyes, hair, mouth, etc.directly between persons while all other parts of the face remain unchanged. The network allows to generate modified images which appear like realistic images. Our model learns disentangled representations by weak supervision. We propose a localized resnet autoencoder optimized using several loss functions including a loss based on the semantic segmentation, which we interpret as masks, and a loss which enforces disentanglement by decomposition of the latent space into statistically independent subspaces. We evaluate the proposed solution w.r.t. disentanglement and generated image quality. Convincing results are demonstrated using the CelebA dataset.
KW - Autoencoders
KW - Face image editing
KW - Independent subspace analysis
KW - Latent space editing
KW - Machine learning
UR - http://www.scopus.com/inward/record.url?scp=85082453249&partnerID=8YFLogxK
U2 - 10.48550/arXiv.1908.08989
DO - 10.48550/arXiv.1908.08989
M3 - Conference contribution
AN - SCOPUS:85082453249
SN - 978-1-7281-5024-6
T3 - IEEE International Conference on Computer Vision Workshops
SP - 560
EP - 568
BT - 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2019 IEEE/CVF 17th International Conference on Computer Vision Workshop (ICCVW)
Y2 - 27 October 2019 through 28 October 2019
ER -