Recent progress in semantic image segmentation

By Xiaolong Liu, Zhidong Deng, Yuhan Yang. 2018

488 citations recorded by the source corpus.

Semantic image segmentation, which becomes one of the key applications in image processing and computer vision domain, has been used in multiple domains such as medical area and intelligent transportation. Lots of benchmark datasets are released for researchers to verify their algorithms. Semantic segmentation has been studied for many years. Since the emergence of Deep Neural Network (DNN), segmentation has made a tremendous progress. In this paper, we divide semantic image segmentation methods into two categories: traditional and recent DNN method. Firstly, we briefly summarize the traditional method as well as datasets released for segmentation, then we comprehensively investigate recent methods based on DNN which are described in the eight aspects: fully convolutional network, up-sample ways, FCN joint with CRF methods, dilated convolution approaches, progresses in backbone network, pyramid methods, Multi-level feature and multi-stage method, supervised, weakly-supervised and unsupervised methods. Finally, a conclusion in this area is drawn.

Subfields: Computer Vision and Pattern Recognition, Information Systems, Urban Studies

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Information Systems

In Urban Studies

Citations in the corpus

Knowledge Distillation for Incremental Learning in Semantic Segmentation (2019, neutral): “Recent reviews on this topic are [18, 19, 20].”
Stacked Autoencoders Driven by Semi-Supervised Learning for Building Extraction from near Infrared Remote Sensing Imagery (2021, background): “…employed, building extraction techniques can be classiﬁed into three groups: (i) the ones that use radiometric information, i.e., airborne or satellite imagery data [13–15], (ii) the ones that exploit height information (LiDAR) [16,17], and (iii) those that combine both of data sources [18,19].”
A review of deep learning methods for semantic segmentation of remote sensing imagery (2021, methodology): “…deep learning methods have demonstrated much superior performance in many traditional computer vision applications including object classification (Liu, Deng, & Yang, 2018; Shi, Yuan, Elhoseny, & Yuan, 2020), detection (Yuan, Xie, & Abouelenien, 2018), and semantic segmentation (Long, Shelhamer,…”
A survey of the recent architectures of deep convolutional neural networks (2019, background): “s) [9]. CNNs are one of the best learning algorithms for understanding image content and have shown exemplary performance in image segmentation, classification, detection, and retrieval related tasks [10], [11]. The success of CNNs has captured attention beyond academia. In industry, companies such ”
COVID-19 detection using deep learning models to exploit Social Mimic Optimization and structured chest X-ray images using fuzzy color and stacking approaches (2020, unknown): “Using deep learning approaches, AI has been used in many applications such as image detection, data classification, image segmentation [5,6].”
One-Shot Instance Segmentation (2018, background): “ Feature Pyramid Networks [42] are a popular extension that uses feature maps at multiple spatial resolutions to increase scale invariance. Instance segmentation. In contrast to semantic segmentation [49, 55, 73, 60, 90, 9, 15, 48], where every pixel is classiﬁed into a category, instance segmentati”
Thin MobileNet: An Enhanced MobileNet Architecture (2019, background): “In realtime applications such as image classification [8], captioning [9], object detection [10,23,33] and semantic segmentation [34] in autonomous driving, the inference time and accuracy are very important factors to one's safety.”