Review the state-of-the-art technologies of semantic segmentation based on deep learning

Y Mo, Y Wu, X Yang, F Liu, Y Liao - Neurocomputing, 2022 - Elsevier
The goal of semantic segmentation is to segment the input image according to semantic
information and predict the semantic category of each pixel from a given label set. With the …

Recent progress in semantic image segmentation

X Liu, Z Deng, Y Yang - Artificial Intelligence Review, 2019 - Springer
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 …

Weakly-and semi-supervised learning of a deep convolutional network for semantic image segmentation

G Papandreou, LC Chen… - Proceedings of the …, 2015 - openaccess.thecvf.com
Deep convolutional neural networks (DCNNs) trained on a large number of images with
strong pixel-level annotations have recently significantly pushed the state-of-art in semantic …

Boxsup: Exploiting bounding boxes to supervise convolutional networks for semantic segmentation

J Dai, K He, J Sun - … of the IEEE international conference on …, 2015 - openaccess.thecvf.com
Recent leading approaches to semantic segmentation rely on deep convolutional networks
trained with human-annotated, pixel-level segmentation masks. Such pixel-accurate …

HCP: A flexible CNN framework for multi-label image classification

Y Wei, W Xia, M Lin, J Huang, B Ni… - IEEE transactions on …, 2015 - ieeexplore.ieee.org
Convolutional Neural Network (CNN) has demonstrated promising performance in single-
label image classification tasks. However, how CNN best copes with multi-label images still …

Stc: A simple to complex framework for weakly-supervised semantic segmentation

Y Wei, X Liang, Y Chen, X Shen… - IEEE transactions on …, 2016 - ieeexplore.ieee.org
Recently, significant improvement has been made on semantic object segmentation due to
the development of deep convolutional neural networks (DCNNs). Training such a DCNN …

Deepcut: Object segmentation from bounding box annotations using convolutional neural networks

M Rajchl, MCH Lee, O Oktay… - IEEE transactions on …, 2016 - ieeexplore.ieee.org
In this paper, we propose DeepCut, a method to obtain pixelwise object segmentations
given an image dataset labelled weak annotations, in our case bounding boxes. It extends …

Methods and datasets on semantic segmentation: A review

H Yu, Z Yang, L Tan, Y Wang, W Sun, M Sun, Y Tang - Neurocomputing, 2018 - Elsevier
Semantic segmentation, also called scene labeling, refers to the process of assigning a
semantic label (eg car, people, and road) to each pixel of an image. It is an essential data …

Beyond pixels: A comprehensive survey from bottom-up to semantic image segmentation and cosegmentation

H Zhu, F Meng, J Cai, S Lu - Journal of Visual Communication and Image …, 2016 - Elsevier
Image segmentation refers to the process to divide an image into meaningful non-
overlapping regions according to human perception, which has become a classic topic since …

Two-phase learning for weakly supervised object localization

D Kim, D Cho, D Yoo… - Proceedings of the IEEE …, 2017 - openaccess.thecvf.com
Weakly supervised semantic segmentation and localization have a problem of focusing only
on the most important parts of an image since they use only image-level annotations. In this …