On the use of supervised features for unsupervised image categorization: An evaluation

Ciocca, Gianluigi; Cusano, Claudio; Santini, Simone; Schettini, Raimondo

doi:10.1016/j.cviu.2014.01.010

Cited by 8 publications

(2 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The research of semi-and unsupervised techniques in computer vision has a long history. A variety of research, surveys, and books has been published on this topic [17]- [21]. Unsupervised cluster algorithms were researched before the breakthrough of deep learning and are still widely used [22].…”

Section: A Related Workmentioning

confidence: 99%

“…We will investigate the different learning strategies with a spotlight on loss functions. We concentrate on recent methods because older one are already adequately addressed in previous literature [17]- [21]. Keep-FIGURE 2: Overview of the structure of this survey -The learning strategies unsupervised, semi-supervised and supervised are commonly used in the literature.…”

Section: A Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A Survey on Semi-, Self- and Unsupervised Learning for Image Classification

et al. 2021

View full text Add to dashboard Cite

While deep learning strategies achieve outstanding results in computer vision tasks, one issue remains: The current strategies rely heavily on a huge amount of labeled data. In many real-world problems, it is not feasible to create such an amount of labeled training data. Therefore, it is common to incorporate unlabeled data into the training process to reach equal results with fewer labels. Due to a lot of concurrent research, it is difficult to keep track of recent developments. In this survey, we provide an overview of often used ideas and methods in image classification with fewer labels. We compare 34 methods in detail based on their performance and their commonly used ideas rather than a fine-grained taxonomy. In our analysis, we identify three major trends that lead to future research opportunities. 1. State-of-the-art methods are scaleable to real-world applications in theory but issues like class imbalance, robustness, or fuzzy labels are not considered. 2. The degree of supervision which is needed to achieve comparable results to the usage of all labels is decreasing and therefore methods need to be extended to settings with a variable number of classes. 3. All methods share some common ideas but we identify clusters of methods that do not share many ideas. We show that combining ideas from different clusters can lead to better performance.

show abstract

Section: A Related Workmentioning

confidence: 99%

Section: A Related Workmentioning

confidence: 99%