Self-Supervised Visual Feature Learning With Deep Neural Networks: A Survey

Longlong Jing, Yingli Tian

2020 · IEEE Transactions on Pattern Analysis and Machine Intelligence · 1,950 citations

Large-scale labeled data are generally required to train deep neural networks in order to obtain better performance in visual feature learning from images or videos for computer vision applications. To avoid extensive cost of collecting and annotating large-scale datasets, as a subset of unsupervised learning methods, self-supervised learning methods are proposed to learn general image and video features from large-scale unlabeled data without using any human-annotated labels. This paper provides an extensive review of deep learning-based self-supervised general visual feature learning method…

Read the paper →

Explore this paper's citation graph on Constellation.