Özet
In this study, we tried to find a solution for inpainting problem using deep convolutional autoencoders. A new training approach has been proposed as an alternative to the Generative Adversarial Networks. The neural network that designed for inpainting takes an image, which the certain part of its center is extracted, as an input then it attempts to fill the blank region. During the training phase, a distinct deep convolutional neural network is used and it is called Advisor Network. We show that the features extracted from intermediate layers of the Advisor Network, which is trained on a different dataset for classification, improves the performance of the autoencoder.
| Tercüme edilen katkı başlığı | Inpainting by deep autoencoders using an advisor network |
|---|---|
| Orijinal dil | Türkçe |
| Ana bilgisayar yayını başlığı | 2017 25th Signal Processing and Communications Applications Conference, SIU 2017 |
| Yayınlayan | Institute of Electrical and Electronics Engineers Inc. |
| ISBN (Elektronik) | 9781509064946 |
| DOI'lar | |
| Yayın durumu | Yayınlandı - 27 Haz 2017 |
| Etkinlik | 25th Signal Processing and Communications Applications Conference, SIU 2017 - Antalya, Turkey Süre: 15 May 2017 → 18 May 2017 |
Yayın serisi
| Adı | 2017 25th Signal Processing and Communications Applications Conference, SIU 2017 |
|---|
???event.eventtypes.event.conference???
| ???event.eventtypes.event.conference??? | 25th Signal Processing and Communications Applications Conference, SIU 2017 |
|---|---|
| Ülke/Bölge | Turkey |
| Şehir | Antalya |
| Periyot | 15/05/17 → 18/05/17 |
Bibliyografik not
Publisher Copyright:© 2017 IEEE.
Keywords
- auto-encoder
- convolutional neural network
- deep learning
- inpainting