Explore the vast range of titles available.

Although deep learning algorithms have achieved significant progress in a variety of domains, they require costly annotations on huge datasets. Self-supervised learning (SSL) using unlabeled data has emerged as an alternative, as it eliminates manual annotation. To do this, SSL constructs feature representations using pretext tasks that operate without manual annotation, which allows models trained in these tasks to extract useful latent representations that later improve downstream tasks such as object classification and detection. The early methods of SSL are based on auxiliary pretext tasks as a way to learn representations using pseudo-labels, or labels that were created automatically based on the dataset’s attributes. Furthermore, contrastive learning has also performed well in learning representations via SSL. To succeed, it pushes positive samples closer together, and negative ones further apart, in the latent space. This paper provides a comprehensive literature review of the top-performing SSL methods using auxiliary pretext and contrastive learning techniques. It details the motivation for this research, a general pipeline of SSL, the terminologies of the field, and provides an examination of pretext tasks and self-supervised methods. It also examines how self-supervised methods compare to supervised ones, and then discusses both further considerations and ongoing challenges faced by SSL.

Medical time series are sequential data collected over time that measures health-related signals, such as electroencephalography (EEG), electrocardiography (ECG), and intensive care unit (ICU) readings. Analyzing medical time series and identifying the latent patterns and trends that lead to uncovering highly valuable insights for enhancing diagnosis, treatment, risk assessment, and disease progression. However, data mining in medical time series is heavily limited by the sample annotation which is time-consuming and labor-intensive, and expert-depending. To mitigate this challenge, the emerging self-supervised contrastive learning, which has shown great success since 2020, is a promising solution. Contrastive learning aims to learn representative embeddings by contrasting positive and negative samples without the requirement for explicit labels. Here, we conducted a systematic review of how contrastive learning alleviates the label scarcity in medical time series based on PRISMA standards. We searched the studies in five scientific databases (IEEE, ACM, Scopus, Google Scholar, and PubMed) and retrieved 1908 papers based on the inclusion criteria. After applying excluding criteria, and screening at title, abstract, and full text levels, we carefully reviewed 43 papers in this area. Specifically, this paper outlines the pipeline of contrastive learning, including pre-training, fine-tuning, and testing. We provide a comprehensive summary of the various augmentations applied to medical time series data, the architectures of pre-training encoders, the types of fine-tuning classifiers and clusters, and the popular contrastive loss functions. Moreover, we present an overview of the different data types used in medical time series, highlight the medical applications of interest, and provide a comprehensive table of 51 public datasets that have been utilized in this field. In addition, this paper will provide a discussion on the promising future scopes such as providing guidance for effective augmentation design, developing a unified framework for analyzing hierarchical time series, and investigating methods for processing multimodal data. Despite being in its early stages, self-supervised contrastive learning has shown great potential in overcoming the need for expert-created annotations in the research of medical time series.

The scarcity of high-quality annotated medical imaging datasets is a major problem that collides with machine learning applications in the field of medical imaging analysis and impedes its advancement. Self-supervised learning is a recent training paradigm that enables learning robust representations without the need for human annotation which can be considered an effective solution for the scarcity of annotated medical data. This article reviews the state-of-the-art research directions in self-supervised learning approaches for image data with a concentration on their applications in the field of medical imaging analysis. The article covers a set of the most recent self-supervised learning methods from the computer vision field as they are applicable to the medical imaging analysis and categorize them as predictive, generative, and contrastive approaches. Moreover, the article covers 40 of the most recent research papers in the field of self-supervised learning in medical imaging analysis aiming at shedding the light on the recent innovation in the field. Finally, the article concludes with possible future research directions in the field.

Deep learning and advancements in computer vision offer significant potential for analyzing medical images resulting in better healthcare and improved patient outcomes. Currently, the dominant approaches in the field of machine learning are supervised learning and transfer learning. These methods are not only prevalent in medicine and healthcare but also across various other industries. They rely on large datasets that have been manually annotated to train increasingly sophisticated models. However, the manual labeling process results in a wealth of untapped, unlabeled data that is accessible in both public and private data repositories. Self-supervised learning (SSL), an emerging field within machine learning, provides a solution by leveraging this untapped, unlabeled data. Unlike traditional machine learning paradigms, SSL algorithms pre-train models using artificial supervisory signals generated from the unlabeled data. This comprehensive review article explores the fundamental concepts, approaches, and advancements in self-supervised learning, with a particular emphasis on medical image datasets and their sources. By summarizing and highlighting the main contributions and findings from the article, this analysis and synthesis aim to shed light on the current state of research in self-supervised learning. Through these rigorous efforts, the existing body of knowledge is synthesized, and implementation recommendations are provided for future researchers interested in harnessing self-supervised learning to develop classification models for medical imaging.

In recent years, self-supervised learning has had significant success in applications involving computer vision and natural language processing. The type of pretext task is important to this boost in performance. One common pretext task is the measure of similarity and dissimilarity between pairs of images. In this scenario, the two images that make up the negative pair are visibly different to humans. However, in entomology, species are nearly indistinguishable and thus hard to differentiate. In this study, we explored the performance of a Siamese neural network using contrastive loss by learning to push apart embeddings of bumblebee species pair that are dissimilar, and pull together similar embeddings. Our experimental results show a 61% F1-score on zero-shot instances, a performance showing 11% improvement on samples of classes that share intersections with the training set.

Many research fields, such as urban planning, urban climate and environmental assessment, require information on the distribution of buildings. In this study, we used U-Net to segment buildings from WorldView-3 imagery. To improve the accuracy of building segmentation, we undertook two endeavors. First, we investigated the optimal order of atmospheric correction (AC) and panchromatic sharpening (pan-sharpening) and found that performing AC before pan-sharpening results in higher building segmentation accuracy than after pan-sharpening, increasing the average IoU by 9.4%. Second, we developed a new multi-task self-supervised learning (SSL) network to pre-train VGG19 backbone using 21 unlabeled WorldView images. The new multi-task SSL network includes two pretext tasks specifically designed to take into account the characteristics of buildings in satellite imagery (size, distribution pattern, multispectral, etc.). Performance evaluation shows that U-Net combined with an SSL pre-trained VGG19 backbone improves building segmentation accuracy by 15.3% compared to U-Net combined with a VGG19 backbone trained from scratch. Comparative analysis also shows that the new multi-task SSL network outperforms other existing SSL methods, improving building segmentation accuracy by 3.5–13.7%. Moreover, the proposed method significantly saves computational costs and can effectively work on a personal computer.

Real-world dehazing datasets usually suffer from small scales because of high collection costs. If networks are trained with such insufficient data, it leads to not only low performance on objective metrics, but also visually insufficient contrast enhancement. Self-supervised learning helps networks learn useful knowledge from unlabeled data and further achieve better performance on small-scale data, which has achieved great success on high-level vision tasks. However, there are rare works to develop self-supervised learning on low-level vision tasks, such as dehazing. In this paper, we propose a simple but effective self-supervised learning method for dehazing, to improve networks’ performance on small-scale real-world datasets. Our useful observations are twofold. First, generating visually pleasing haze-free images from real-world hazy images is very difficult, but generating visually pleasing denser hazy images is much easier. Second, forcing networks to reduce dense haze will enhance the contrast enhancement capability of networks, and it is beneficial for further dehazing. Therefore, we generate numerous denser hazy images rehazy from a real-world hazy image. With pretraining on image pairs [ rehazy ,  hazy ], networks learn key capabilities of enhancing contrast. Experiments show that it stably outperforms directly supervised learning by a considerable margin, but only spends a cheap extra pretraining time cost.

This paper describes a method based on a deep neural network (DNN) for estimating the number of tillers on a plant. A tiller is a branch on a grass plant, and the number of tillers is one of the most important determinants of yield. Traditionally, the tiller number is usually counted by hand, and so an automated approach is necessary for high-throughput phenotyping. Conventional methods use heuristic features to estimate the tiller number. Based on the successful application of DNNs in the field of computer vision, the use of DNN-based features instead of heuristic features is expected to improve the estimation accuracy. However, as DNNs generally require large volumes of data for training, it is difficult to apply them to estimation problems for which large training datasets are unavailable. In this paper, we use two strategies to overcome the problem of insufficient training data: the use of a pretrained DNN model and the use of pretext tasks for learning the feature representation. We extract features using the resulting DNNs and estimate the tiller numbers through a regression technique. We conducted experiments using side-view whole plant images taken with plan backgroud. The experimental results show that the proposed methods using a pretrained model and specific pretext tasks achieve better performance than the conventional method.

Reconstructing fine‐grained, detailed spatial structures from time‐evolving coarse‐scale geophysical fields has been a long‐standing challenge. Current deep learning approaches addressing this issue generally require massive fine‐scale fields as supervision, which is often unavailable due to limitations in existing observational systems and the scarcity of widespread high‐precision sensors. Here, we present AdaptDeep, a self‐supervised framework for refined reconstruction of geophysical fields via domain adaptation from the coarse‐scale source domain to the fine‐scale target domain. This method incorporates two pretext tasks, cropped field reconstruction and temporal augmentation‐assisted contrastive learning, to leverage spatial and temporal correlations in the target domain. A global propagation structure is proposed in the feature extraction network to leverage bidirectional information for enhanced long‐range dependencies and robustness against estimation errors. In experiments, AdaptDeep correctly identifies local, fine structures and significantly recovers 81.2% detailed information in sea surface temperature fields. Plain Language Summary In recent years, deep learning has greatly contributed to the field of meteorology and we perform an investigation into the use of convolutional neural networks, to tackle the issue of reconstructing precise spatial structures from coarse‐scale geophysical fields that evolves over time. Right now, techniques using deep learning need highly detailed “ground truth” data to guide them, but this kind of data is often hard to get. This is particularly true in less economically developed areas where there's a lack of high‐quality sensors. To address these concerns, we've developed AdaptDeep, which teaches itself how to reconstruct geophysical fields at a finer scale. It does this by mimicking the process of turning coarse‐scale source data into finer‐scale target data. The backbone of AdaptDeep is a neural network, which uses information from all directions and a global context to increase its understanding of long‐range dependencies and reduce estimation errors. We put AdaptDeep to the test, and found that it could accurately pick out local, detailed structures, recovering an impressive 81.2% of detailed information in sea surface temperature fields. This shows that AdaptDeep could be a powerful new tool in helping us to understand our environment in more detail. Key Points A self‐supervised framework is presented for refined reconstruction of geophysical fields without high‐resolution fields as ground truth Two pretext tasks are designed and incorporated into the model to leverage spatial and temporal correlations in the target domain The feature extraction network employs a global propagation structure to exploit global information

With the increasing visual realism of computer-graphics (CG) images generated by advanced rendering engines, the distinction between CG images and natural images (NIs) has become an important research problem in the image forensics community. Previous research works mainly focused on the conventional supervised learning framework, which usually requires a good quantity of labeled data for training. To our knowledge, we study, for the first time in the literature, the utility of the self-supervised learning mechanism for the forensic classification of CG images and NIs. The idea is to make use of a large number of readily available unlabeled data, along with a self-supervised training procedure on a well-designed pretext task for which labels can be generated in an automatic and convenient way without human manual labeling effort. Differing from existing self-supervised methods, based on pretext tasks targeted at image understanding, or based on contrastive learning, we propose carrying out self-supervised training on a forensics-oriented pretext task of classifying authentic images and their modified versions after applying various manipulations. Experiments and comparisons showed the effectiveness of our method for solving the CG forensics problem under different evaluation scenarios. Our proposed method outperformed existing self-supervised methods in all experiments. It could sometimes achieve comparable, or better, performance. compared with a state-of-the-art fully supervised method under difficult evaluation scenarios with data scarcity and a challenging forensic problem. Our study demonstrates the utility and potential of the self-supervised learning mechanism for image forensics applications.