Semantic Image Segmentation: Two Decades of Research

Abstract

Semantic image segmentation (SiS) plays a fundamental role in a broad variety of computer vision applications, providing key information for the global understanding of an image. This survey is an effort to summarize two decades of research in the field of SiS, where we propose a literature review of solutions starting from early historical methods followed by an overview of more recent deep learning methods including the latest trend of using transformers. We complement the review by discussing particular cases of the weak supervision and side machine learning techniques that can be used to improve the semantic segmentation such as curriculum, incremental or self-supervised learning.State-of-the-art SiS models rely on a large amount of annotated samples, which are more expensive to obtain than labels for tasks such as image classification. Since unlabeled data is instead significantly cheaper to obtain, it is not surprising that Unsupervised Domain Adaptation (UDA) reached a broad success within the semantic segmentation community. Therefore, a second core contribution of this book is to summarize five years of a rapidly growing field, Domain Adaptation for Semantic Image Segmentation (DASiS) which embraces the importance of semantic segmentation itself and a critical need of adapting segmentation models to new environments. In addition to providing a comprehensive survey on DASiS techniques, we unveil also newer trends

Whole Spine Segmentation Using Object Detection and Semantic Segmentation

“…With an ever increasing number of imaging studies carried out, automated supportive approaches such as ours can be of assistance in clinical practice [ 43 ], and accurate segmentation has the potential to impact clinical practice and efficiency. With inference times per slice of under 0.1 second for both models combined, they are well below the time manual segmentation requires.…”

Performance Comparison of U-Net and Linknet With Different Encoders for Reforestation Detection

“…After five classes are defined, actual problem can be clearly classifiedsemantic segmentation. Semantic segmentation is one of most complex tasks in computer vision field [8,9]. Semantic segmentation is process of mapping each pixel of input image to respective class on output image.…”

Використання Tpu Акселератора На Базі Мікрокомп’ютера Для Прискорення Алгоритмів Розпізнавання Об’єктів На Зображенні

“…Ройко Андрій Олегович ORCID ID: 0009-0000-4264-0012 студент 1-го курсу магістратури Національний університет "Львівська політехніка", Україна Штучний інтелект здійснив революцію в обробці зображень і комп'ютерному зорі, домінуючи в сотнях галузей включаючи розпізнавання об'єктів [1], класифікацію зображень [2], семантичну сегментацію [3] Висновки. Використання TPU акселераторів у зв'язці з мікрокомп'ютерами є перспективним дослідженням, через низьку вартість обладнання, компактність, а також високу енергоефективність.…”