Image semantic segmentation语义分割(Semantic Segmentation)是在像素级别上的分类,属于同一类的像素都要被归为一类,因此语义分割是从像素级别来理解图像的。注意语义分割不同于实例分割,举例来说,如果一张照片中有多个人,对于语义分割来说,只要将所由人的像素都归为一类,但是实例分割还要将不同人的像素归为不同的类。也就是说实例分割比语义分割更进一步。
Serban Stan, Mohammad Rostami
We developed a novel algorithm for performing unsupervised domain adaptation of semantic segmentation models in a source-free learning setting to preserve privacy for the source domain
Cited by0BibtexViews6DOI
0
0
AAAI, pp.10762-10769, (2020)
Our approach achieves the new state-of-the-art on VOC 2012 dataset for imagelevel label based semantic segmentation
Cited by6BibtexViews190DOI
3
0
Guolei Sun, Wenguan Wang, Jifeng Dai, Luc Van Gool
european conference on computer vision, pp.347-365, (2020)
Experimental Results: The final results with the standard mean intersection over union criterion for weakly supervised semantic segmentation track of both LID19 and LID20 challenges are shown in Table 3
Cited by0BibtexViews41DOI
0
0
CVPR, pp.548-557, (2019)
To further utilize co-occurrent features in semantic segmentation, we introduce an Aggregated Cooccurrent Feature Module to aggregate the co-occurrent context of the co-occurrent features
Cited by46BibtexViews23DOI
0
0
CVPR, pp.6936-6945, (2019)
We propose a bidirectional learning method with self-supervised learning for segmentation adaptation problem
Cited by45BibtexViews34DOI
0
0
arXiv: Computer Vision and Pattern Recognition, (2019)
We propose a fast segmentation network for above realtime scene understanding
Cited by40BibtexViews46DOI
0
0
CVPR, (2019): 12416-12425
We have introduced two effective network modules, namely the spatial relation module and the channel relation module, to enable relational reasoning in networks for semantic segmentation in aerial scenes
Cited by38BibtexViews6DOI
0
0
CVPR, (2019): 413-422
We have proposed to directly decompose the full-precision network into multiple groups and each group is approximated using a set of binary bases which can be optimized in an end-to-end manner
Cited by38BibtexViews50DOI
0
0
CVPR, (2019)
We propose a Domain Invariant Structure Extraction framework to address unsupervised domain adaptation for semantic segmentation
Cited by36BibtexViews11DOI
0
0
CVPR, (2019): 1841-1850
We have introduced Geometrically Guided Input-Output Adaptation approach, which effectively leverages the geometric information in synthetic data to tackle the cross-domain semantic segmentation problem
Cited by36BibtexViews57DOI
0
0
Yifan Liu, Ke Chen, Chris Liu,Zengchang Qin, Zhenbo Luo,Jingdong Wang
CVPR, (2019): 2604-2613
We study knowledge distillation for training compact semantic segmentation networks with the help of cumbersome networks
Cited by29BibtexViews42DOI
0
0
international conference on acoustics, speech, and signal processing, (2019)
We proposed a deep semantic segmentation-based layered image compression framework in which the semantic segmentation map of the input image was used to synthesize the image, and the residual was encoded as an enhancement layer in the bit-stream
Cited by17BibtexViews4DOI
0
0
arXiv: Computer Vision and Pattern Recognition, (2019)
Our experiments showed that adding the correspondences as extra supervision during training improves the segmentation performance of the network, making it more robust to seasonal changes and weather conditions
Cited by13BibtexViews37DOI
0
0
Kaixin Wang,Jun Hao Liew, Yingtian Zou, Daquan Zhou,Jiashi Feng
2990230185, pp.9197-9206, (2019)
We propose a novel Prototype Alignment Network for few-shot segmentation based on metric learning
Cited by11BibtexViews15
0
0
national conference on artificial intelligence, (2019)
We have presented the fully dense neural network with an encoder-decoder structure for semantic segmentation
Cited by7BibtexViews25DOI
0
0
Li Chenglong, Xia Wei, Yan Yan,Luo Bin,Tang Jin
IEEE transactions on neural networks and learning systems, (2019): 1-14
We presented a newly dataset Segment Objects in Day And night for a new vision task of thermal image semantic segmentation
Cited by5BibtexViews9DOI
0
0
pp.97-105 (2019)
By adding the graph convolutional network parts as an additional loss the model the semantic segmentation mean intersection over union has improved 1.34%
Cited by2BibtexViews22DOI
0
0
International Journal of Computer Vision, pp.1-24, (2019)
This paper is the first to analyze whether state-of-the-art methods developed for natural scene images still perform acceptably on histopathology and satellite images and compares their performances against a method developed for histopathology images
Cited by0BibtexViews2DOI
0
0
Taghanaki Saed Asgari, Abhishek Kumar, Cohen Joseph Paul, Cohen-Adad Julien,Hamarneh Ghassan
Artificial Intelligence Review, pp.1-42, (2019)
We provide comprehensive coverage of research contributions in the field of natural and medical image semantic segmentation
Cited by0BibtexViews5DOI
0
0