A Survey on the New Generation of Deep Learning in Image Processing
Обзор нового поколения методов глубокого обучения в обработке изображений
2019-01-01
SCID: 54.1/vf78fe8t
Discuss with AI
class imbalanceconvolutional neural networks (CNNs)deep learninggenerative adversarial networks (GANs)image processing
Figures from the paper
Abstract (AI)
During the past decade, deep learning is one of the essential breakthroughs made in artificial intelligence. In particular, it has achieved great success in image processing. Correspondingly, various applications related to image processing are also promoting the rapid development of deep learning in all aspects of network structure, layer designing, and training tricks. However, the deeper structure makes the back-propagation algorithm more difficult. At the same time, the scale of training images without labels is also rapidly increasing, and class imbalance severely affects the performance of deep learning, these urgently require more novelty deep models and new parallel computing system to more effectively interpret the content of the image and form a suitable analysis mechanism. In this context, this survey provides four deep learning model series, which includes CNN series, GAN series, ELM-RVFL series, and other series, for comprehensive understanding towards the analytical techniques of image processing field, clarify the most important advancements and shed some light on future studies. By further studying the relationship between deep learning and image processing tasks, which can not only help us understand the reasons for the success of deep learning but also inspires new deep models and training methods. More importantly, this survey aims to improve or arouse other researchers to catch a glimpse of the state-of-the-art deep learning methods in the field of image processing and facilitate the applications of these deep learning technologies in their research tasks. Besides, we discuss the open issues and the promising directions of future research in image processing using the new generation of deep learning.
Key Findings
1
Deep learning has achieved substantial success in image processing, while application demands have driven advances in network structures, layer design, and training techniques.
2
Increasing model depth makes back-propagation more difficult, highlighting the need for novel architectures and training methods.
3
Rapid growth of unlabeled training images and severe class imbalance remain major challenges affecting deep-learning performance.
4
The survey identifies open problems and promising future directions, including improved deep models and parallel computing systems for image analysis.
5
The survey organizes image-processing deep learning methods into four model families: CNN, GAN, ELM-RVFL, and other emerging architectures.
Research Object
Deep learning methods applied to image processing
Research Subject
The model architectures, training methods, analytical capabilities, applications, open issues, and future directions of new-generation deep learning for image processing
Publication Details
Publication Date
2019-01-01
Journal
Publisher
ISSN
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai5
FaceNet: A unified embedding for face recognition and clustering2015
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks2015
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation2017
Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising2017
Image Style Transfer Using Convolutional Neural Networks2016