What Should We Learn? Deep Learning for Visual Understanding: Part 2

The November 2017 special issue of SPM on deep learning for visual understanding surveyed deep-learning solutions under reinforcement; weakly supervised and multimodal settings, investigated their robustness; and presented overviews of their applications in domain adaptation, hashing, semantic segmentation, metric learning, inverse problems in imaging, image-to-text generation, and picture-quality assessment.

Complementing these topics in this second part of the special issue of SPM in March 2018 on deep learning for visual understanding, the editors continue providing tutorials on deeplearning techniques for understanding face images, salient and category-specific object detection, superresolution, denoising, deblurring, compressive sensing, zero-shot recognition, and conditional random fields. This edition also has three articles on popular areas of GANs, deep regression Bayesian networks, and model compression and acceleration. the editors hope these tutorial articles will foster further discussions and facilitate the application of deep-learning techniques for computer vision to the other areas of signal processing. Once again, welcome you to explore all of these articles as well as the amazing field of deep learning.