Special Issue on Deep Neural Network Representation and Generative Adversarial Learning
摘要截稿:
全文截稿: 2019-09-30
影响因子: 5.535
期刊难度:
CCF分类: B类
中科院JCR分区:
• 大类 : 计算机科学 - 2区
• 小类 : 计算机:人工智能 - 2区
• 小类 : 神经科学 - 2区
Overview
Generative Adversarial Networks (GANs) have proven to be efficient systems for data generation. Their success is achieved by exploiting a minimax learning concept, which has proved to be an effective paradigm in earlier works, such as predictability minimization, in which two networks compete with each other during the learning process. One of the main advantages of GANs over other deep learning methods is their ability to generate new data from noise, as well as their ability to virtually imitate any data distribution. However, generating realistic data using GANs remains a challenge, particularly when specific features are required; for example, constraining the latent aggregate distribution space does not guarantee that the generator will produce an image with a specific attribute. On the other hand, new advancements in deep representation learning (RL) can help improve the learning process in Generative Adversarial Learning (GAL). For instance, RL can help address issues such as dataset bias and network co-adaptation, and identify a set of features that are best suited for a given task.
Despite their obvious advantages and their application to a wide range of domains, GANs have yet to overcome several challenges. They often fail to converge and are very sensitive to parameter and hyper-parameter initialization. Simultaneous learning of a generator and a discriminator network often results in overfitting. Moreover, the generator model is prone to mode collapse, which results in failure to generate data with several variations. Accordingly, new theoretical methods in deep RL and GAL are required to improve the learning process and generalization performance of GANs, as well as to yield new insights into how GANs learn data distributions.
Thisspecial issue on Deep Neural Network Representation and Generative Adversarial Learning invites researchers and practitioners to present novel contributions addressing theoretical and practical aspects of deep representation and generative adversarial learning.The special issue will feature a collection of high quality theoretical articles for improving the learning process and the generalization of generative neural networks. State-of-the-art applications based on deep generative adversarial networks are also very welcome.
Main Topics include:
Topics of interest for this special issue include, but are not limited to:
Representation learning methods and theory;
Adversarial representation learning for domain adaptation;
Network interpretability in adversarial learning;
Adversarial feature learning;
RL and GAL for data augmentation and class imbalance;
New GAN models and new GAN learning criteria;
RL and GAL in classification;
Adversarial reinforcement learning;
GANs for noise reduction;
Recurrent GAN models;
GANs for imitation learning;
GANs for image segmentation and image completion;
GANs for image super-resolution;
GANs for speech and audio processing
GANs for object detection;
GANs for Internet of Things;
RL and GANs for image and video synthesis;
RL and GANs for speech and audio synthesis;
RL and GANs for text to audio or text to image synthesis;