Deep learning algorithms have exhibited impressive performance across various computer vision tasks; however, the challenge of overfitting persists, especially when dealing with limited labeled data. This survey explores the mitigation of the overfitting issue through a comprehensive examination of image data augmentation techniques, which aim to enhance dataset size and diversity by introducing varied samples. The survey exclusively focuses on these techniques, presenting an insightful overview and introducing a novel taxonomy. The discussion encompasses the strengths and limitations of these techniques. Additionally, the paper provides extensive results evaluating the impact of these techniques on prevalent computer vision tasks: image classification, object detection, and semantic segmentation. The survey concludes with an examination of challenges, limitations, and potential future research directions.
An increasing number of cities are confronted with challenges resulting from the rapid urbanisation and new demands that a rapidly growing digital economy imposes on current applications and information systems. Smart city applications enable city authorities to monitor, manage and provide plans for public resources and infrastructures in city environments, while offering citizens and businesses to develop and use intelligent services in cities. However, providing such smart city applications gives rise to several issues such as semantic heterogeneity and trustworthiness of data sources, and extracting up-to-date information in real time from large-scale dynamic data streams. In order to address these issues, we propose a novel framework with an efficient semantic data processing pipeline, allowing for real-time observation of the pulse of a city. The proposed framework enables efficient semantic integration of data streams and complex event processing on top of real-time data aggregation and quality analysis in a Semantic Web environment. To evaluate our system, we use real-time sensor observations that have been published via an open platform called Open Data Aarhus by the City of Aarhus. We examine the framework utilising Symbolic Aggregate Approximation to reduce the size of data streams, and perform quality analysis taking into account both single and multiple data streams. We also investigate the optimisation of the semantic data discovery and integration based on the proposed stream quality analysis and data aggregation techniques.
6 December 2016 in Semantic Web: – Interoperability, Usability, Applicability
In recent years we have seen significant advances in the technology used to both publish and consume structured data using the existing web infrastructure, commonly referred to as the Linked Data Web. However, in order to support the next generation
Advanced data augmentation techniques have demonstrated great success in deep learning algorithms. Among these techniques, single-image-based data augmentation (SIBDA), in which a single image’s regions are randomly erased in different ways, has shown promising results. However, randomly erasing image regions in SIBDA can cause a loss of the key discriminating features, consequently misleading neural networks and lowering their performance. To alleviate this issue, in this paper, we propose the random slices mixing data augmentation (RSMDA) technique, in which slices of one image are placed onto another image to create a third image that enriches the diversity of the data. RSMDA also mixes the labels of the original images to create an augmented label for the new image to exploit label smoothing. Furthermore, we propose and investigate three strategies for RSMDA: (i) the vertical slices mixing strategy, (ii) the horizontal slices mixing strategy, and (iii) a random mix of both strategies. Of these strategies, the horizontal slice mixing strategy shows the best performance. To validate the proposed technique, we perform several experiments using different neural networks across four datasets: fashion-MNIST, CIFAR10, CIFAR100, and STL10. The experimental results of the image classification with RSMDA showed better accuracy and robustness than the state-of-the-art (SOTA) single-image-based and multi-image-based methods. Finally, class activation maps are employed to visualize the focus of the neural network and compare maps using the SOTA data augmentation methods.