Coupled Adversarial Learning for Single Image Super-Resolution
ID:174 View Protection:ATTENDEE Updated Time:2020-08-05 10:17:28 Hits:473 Oral Presentation

Start Time:2020-06-08 14:00(Asia/Shanghai)


Session:S Special Session » SS13Unsupervised Computing And Large-Scale Optimization For Multi-Dimensional Data Processing

Video No Permission

Tips: Only the registered participant can access the file. Please sign in first.

Generative adversarial nets (GAN) have been widely used in several image restoration tasks such as image denoise, enhancement, and super-resolution. The objective functions of an image super-resolution problem based on GANs usually are reconstruction error, semantic feature distance, and GAN loss. In general, semantic feature distance was used to measure the feature similarity between the super-resolved and ground-truth images, to ensure they have similar feature representations. However, the feature is usually extracted by the pre-trained model, in which the feature representation is not designed for distinguishing the extracted features from low-resolution and high-resolution images. In this study, a coupled adversarial net (CAN) based on Siamese Network Structure is proposed, to improve the effectiveness of the feature extraction. In the proposed CAN, we offer GAN loss and semantic feature distances simultaneously, reducing the training complexity as well as improving the performance. Extensive experiments conducted that the proposed CAN is effective and efficient, compared to state-of-the-art image super-resolution schemes.
Adversarial Generative Nets; Super-Resolution; coupled Nets; Siamese Nets
Chih-Chung Hsu
National Pingtung University of Science and Technology, Taiwan

Submission Author
Chih-Chung Hsu National Pingtung University of Science and Technology, Taiwan
Kuan-Yu Huang Informal Researcher, Taiwan
Submit Comment
Verify Code Change Another
All Comments
Important Date
  • Conference Date

    Jun 08



    Jun 11


  • Jan 12 2020

    Draft paper submission deadline

  • Apr 15 2020

    Early Bird Registration

  • Dec 31 2020

    Registration deadline

Sponsored By
IEEE Signal Processing Society
Contact Information