Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey

TL;DR

This survey reviews self-supervised deep learning methods for visual feature extraction from images and videos, emphasizing architectures, datasets, evaluation metrics, and future research directions.

Contribution

It provides a comprehensive overview of current self-supervised visual feature learning techniques, including architectures, datasets, evaluation, and performance comparisons.

Findings

Self-supervised methods achieve competitive performance without labeled data.

Various neural network architectures are used for self-supervised learning.

Benchmark comparisons highlight strengths and gaps in current methods.

Abstract

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 main components and evaluation metrics of self-supervised learning methods are reviewed followed by the commonly used image and video datasets and 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.