Pixel-Level Encoding and Depth Layering for Instance-Level Semantic Labeling
@inproceedings{Uhrig2016PixelLevelEA, title={Pixel-Level Encoding and Depth Layering for Instance-Level Semantic Labeling}, author={J. Uhrig and Marius Cordts and Uwe Franke and T. Brox}, booktitle={GCPR}, year={2016} }
Recent approaches for instance-aware semantic labeling have augmented convolutional neural networks (CNNs) with complex multi-task architectures or computationally expensive graphical models. We present a method that leverages a fully convolutional network (FCN) to predict semantic labels, depth and an instance-based encoding using each pixel’s direction towards its corresponding instance center. Subsequently, we apply low-level computer vision techniques to generate state-of-the-art instance… CONTINUE READING
Figures, Tables, and Topics from this paper
134 Citations
Bridging Category-level and Instance-level Semantic Image Segmentation
- Computer Science
- ArXiv
- 2016
- 93
- Highly Influenced
- PDF
Deep Watershed Transform for Instance Segmentation
- Computer Science
- 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- 2017
- 297
- Highly Influenced
- PDF
Laplacian Pyramid Reconstruction and Refinement for Semantic Segmentation
- Computer Science
- ECCV
- 2016
- 283
- PDF
Understanding Convolution for Semantic Segmentation
- Computer Science
- 2018 IEEE Winter Conference on Applications of Computer Vision (WACV)
- 2018
- 570
- PDF
Proposal-Based Instance Segmentation With Point Supervision
- Computer Science
- 2020 IEEE International Conference on Image Processing (ICIP)
- 2020
- 1
End-to-End Training of Hybrid CNN-CRF Models for Semantic Segmentation using Structured Learning
- 2017
- PDF
Semantic Instance Segmentation for Autonomous Driving
- Computer Science
- 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
- 2017
- 46
References
SHOWING 1-10 OF 45 REFERENCES
Monocular Object Instance Segmentation and Depth Ordering with CNNs
- Computer Science, Mathematics
- 2015 IEEE International Conference on Computer Vision (ICCV)
- 2015
- 128
- Highly Influential
- PDF
Instance-Level Segmentation with Deep Densely Connected MRFs
- Computer Science
- ArXiv
- 2015
- 28
- Highly Influential
- PDF
Towards unified depth and semantic prediction from a single image
- Computer Science
- 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- 2015
- 298
- PDF
Efficient Piecewise Training of Deep Structured Models for Semantic Segmentation
- Computer Science
- 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- 2016
- 688
- PDF
Fully Convolutional Networks for Semantic Segmentation
- Computer Science, Medicine
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- 2017
- 9,047
- Highly Influential
- PDF
Weakly-and Semi-Supervised Learning of a Deep Convolutional Network for Semantic Image Segmentation
- Computer Science
- 2015 IEEE International Conference on Computer Vision (ICCV)
- 2015
- 488
- PDF
Instance-Aware Semantic Segmentation via Multi-task Network Cascades
- Computer Science
- 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- 2016
- 795
- PDF
Instance-Level Segmentation for Autonomous Driving with Deep Densely Connected MRFs
- Computer Science
- 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- 2016
- 128
- PDF
Proposal-Free Network for Instance-Level Object Segmentation
- Computer Science, Medicine
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- 2018
- 178
- PDF