Multi-Generator Discriminator Network Using Texture-Edge Information
Source abstract
Abstract
In the proposed paper, a parallel structure type Generative Adversarial Network (GAN) using edge and texture information is proposed. In the existing GAN-based model, many learning iterations had to be given to obtaining an output that was somewhat close to the original data, and noise and distortion occurred in the output image even when learning was performed. To solve this problem, the proposed model consists of two generators and three discriminators to propose a network in the form of a parallel structure. In the network, each edge information and texture information were received as inputs, learning was performed, and each character was combined and outputted through the Combine Discriminator. Through this, edge information and distortion of the output image were improved even with fewer iterations than DCGAN, which is the existing GAN-based model. As a result of learning on the network of the proposed model, a clear image with improved contour and distortion of objects in the image was output from about 50,000 iterations.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Face and Expression Recognition · Industrial Vision Systems and Defect Detection · Image Retrieval and Classification Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (34)
Show source-provided references
1. Instance retrieval using region of interest based cnn features10.32604/jnm.2019.06582 ↗
2. Self-repair of smart manufacturing systems by deep reinforcement learning10.1016/j.cirp.2020.04.008 ↗
3. Applying deep neural network (DNN) for robust indoor localization in multi-building environment10.3390/app8071062 ↗
4. Influence of multimedia and seating location in academic engagement and grade performance of students10.1002/cae.22190 ↗
5. Personal authentication application using deep learning neural network
6. Malware classification using simhash encoding and PCA (MCSP)10.3390/sym12050830 ↗
7. Deep learning in medical image analysis
8. FPGA architecture for deep learning and its application to planetary robotics
9. Trajectory tracking optimization of mobile robot using artificial immune system10.1007/s11042-018-6413-7 ↗
10. A gentle introduction to deep learning in medical image processing10.1016/j.zemedi.2018.12.003 ↗
11. Goodfellow · Advances in Neural Information Processing Systems · 2014 · 2672
12. Unsupervised representation learning with deep convolutional generative adversarial networks
13. Least squares generative adversarial networks
14. Unpaired image-to-image translation using cycle-consistent adversarial networks
15. Stargan: Unified generative adversarial networks for multi-domain image-to-image translation
16. Large scale gan training for high fidelity natural image synthesis
17. Edge-labeling graph neural network for few-shot learning
18. Semantic and generalized entropy loss functions for semi-supervised deep learning
19. DCGAN-Based data augmentation for tomato leaf disease identification10.1109/ACCESS.2020.2997001 ↗
20. Deep learning face attributes in the wild
21. A simple recurrent unit model based intrusion detection system with dcgan10.1109/ACCESS.2019.2922692 ↗
22. Gradient-based learning applied to document recognition10.1109/5.726791 ↗
23. Artificial neural networks: A tutorial10.1109/2.485891 ↗
24. Krizhevsky · Advances in Neural Information Processing Systems · 2012 · 1097
25. Max-pooling dropout for regularization of convolutional neural networks
26. Efficientnet: Rethinking model scaling for convolutional neural networks
27. M2det: A single-shot object detector based on multi-level feature pyramid network
28. Progressive growing of gans for improved quality, stability and variation
29. Evaluation of sentimental texts automatically generated by a generative adversarial network
30. Nair · ICML · 2010 · 807
31. Striving for simplicity: The all convolutional net
32. Infrared image colorization based on a triplet dcgan architecture
33. Automatic sketch colorization using DCGAN
34. An efficient hyperspectral image retrieval method: Deep spectral-spatial feature extraction with DCGAN and dimensionality reduction using t-SNE-based NM hashing10.3390/rs10020271 ↗