2022/10/06 by Zhenyuan Lu, Lu, Zhenyuan
Computer Science · #Advanced Image and Video Retrieval Techniques #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #FOS: Electrical engineering #Multimodal Machine Learning Applications #Signal Processing (eess.SP) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2210.03163
openalex publication_date 2022/10/06 · openalex created_date 2022/10/11 · openalex updated_date 2026/07/28
To improve performance in visual feature representation from photos or videos for practical applications, we generally require large-scale human-annotated labeled data while training deep neural networks. However, the cost of gathering and annotating human-annotated labeled data is expensive. Given that there is a lot of unlabeled data in the actual world, it is possible to introduce self-defined pseudo labels as supervisions to prevent this issue. Self-supervised learning, specifically contrastive learning, is a subset of unsupervised learning methods that has grown popular in computer vision, natural language processing, and other domains. The purpose of contrastive learning is to embed augmented samples from the same sample near to each other while pushing away those that are not. In the following sections, we will introduce the regular formulation among different learnings. In the next sections, we will discuss the regular formulation of various learnings. Furthermore, we offer some strategies from contrastive learning that have recently been published and are focused on pretext tasks for visual representation.