Self-Supervised Visual Feature Learning With Deep Neural Networks: A Survey
Self-Supervised Visual Feature Learning With Deep Neural Networks: A Survey
复制标题
基于深度神经网络的自监督视觉特征学习研究综述
DOI：
10.1109/tpami.2020.2992393
复制
发表时间：
2021-11-01
影响因子：
23.6
通讯作者：
Tian, Yingli
中科院分区：
文献类型：
--
作者：
Jing, Longlong;Tian, Yingli
通常需要大规模标记数据来训练深度神经网络，以便在计算机视觉应用的图像或视频视觉特征学习中获得更好的性能。为了避免收集和注释大规模数据集的大量成本，作为无监督学习方法的子集，提出了自监督学习方法，从大规模未标记数据中学习一般图像和视频特征，而不使用任何人工注释标签。本文对基于深度学习的图像或视频的自监督通用视觉特征学习方法进行了广泛的回顾。首先，描述该领域的动机、一般流程和术语。然后总结了用于自监督学习的常见深度神经网络架构。接下来，回顾了自监督学习方法的模式和评估指标，然后介绍了常用的图像、视频、音频和 3D 数据数据集，以及现有的自监督视觉特征学习方法。最后，总结并讨论了图像和视频特征学习所审查方法在基准数据集上的定量性能比较。最后，本文进行了总结，并列出了自监督视觉特征学习的一系列有前途的未来方向。
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 methods from images or videos. First, the motivation, general pipeline, and terminologies of this field are described. Then the common deep neural network architectures that used for self-supervised learning are summarized. Next, the schema and evaluation metrics of self-supervised learning methods are reviewed followed by the commonly used datasets for images, videos, audios, and 3D data, as well as the existing self-supervised visual feature learning methods. Finally, quantitative performance comparisons of the reviewed methods on benchmark datasets are summarized and discussed for both image and video feature learning. At last, this paper is concluded and lists a set of promising future directions for self-supervised visual feature learning.