Semi-Supervised and Unsupervised Deep Visual Learning: A Survey
By Yanbei Chen, Massimiliano Mancini, Xiatian Zhu, Zeynep Akata. 2022
210 citations recorded by the source corpus.
State-of-the-art deep learning models are often trained with a large amount of costly labeled training data. However, requiring exhaustive manual annotations may degrade the model's generalizability in the limited-label regime.Semi-supervised learning and unsupervised learning offer promising paradigms to learn from an abundance of unlabeled visual data. Recent progress in these paradigms has indicated the strong benefits of leveraging unlabeled data to improve model generalization and provide better model initialization. In this survey, we review the recent advanced deep learning algorithms on semi-supervised learning (SSL) and unsupervised learning (UL) for visual recognition from a unified perspective. To offer a holistic understanding of the state-of-the-art in these areas, we propose a unified taxonomy. We categorize existing representative SSL and UL with comprehensive and insightful analysis to highlight their design rationales in different learning scenarios and applications in different computer vision tasks. Lastly, we discuss the emerging trends and open challenges in SSL and UL to shed light on future critical research directions.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Elisa Ricci
- Enrico Fini
- Alahari Karteek
- Moin Nabi
- Bharath Hariharan
- Zhiqi Kang
- Qianqian Wang
- Luming Tang
In Computer Vision and Pattern Recognition
- Elisa Ricci
- Luc Van Gool
- Alahari Karteek
- Andrew Zisserman
- Enrico Fini
- Andrea Vedaldi
- Xiaogang Wang
- Trevor Darrell
Citations in the corpus
- A soft nearest-neighbor framework for continual semi-supervised learning (2022, background): “Semi-supervised methods focus on learning models from large-scale datasets where only a few samples have associated annotations [17].”
- A Comprehensive Survey on Test-Time Adaptation Under Distribution Shifts (2023, unknown): “As a prevailing strategy in recent semi-supervised learning literature [99], [232], consistency regularization is primarily”
- Emergent Correspondence from Image Diffusion (2023, background): “For learning from unlabeled data, unsupervised [14] and self-supervised learning [27] algorithms abound.”