## (TensorFlow)实时语义分割比较研究

2018 年 3 月 12 日 机器学习研究会

Semantic segmentation benefits robotics related applications especially autonomous driving. Most of the research on semantic segmentation is only on increasing the accuracy of segmentation models with little attention to computationally efficient solutions. The few work conducted in this direction does not provide principled methods to evaluate the different design choices for segmentation. In this paper, we address this gap by presenting a real-time semantic segmentation benchmarking framework with a decoupled design for feature extraction and decoding methods. The framework is comprised of different network architectures for feature extraction such as VGG16, Resnet18, MobileNet, and ShuffleNet. It is also comprised of multiple meta-architectures for segmentation that define the decoding methodology. These include SkipNet, UNet, and Dilation Frontend. Experimental results are presented on the Cityscapes dataset for urban scenes. The modular design allows novel architectures to emerge, that lead to 143x GFLOPs reduction in comparison to SegNet. This benchmarking framework will be made publicly available at 1 .

The repository contains the official TensorFlow code used in the our paper RTSEG: REAL-TIME SEMANTIC SEGMENTATION COMPARATIVE STUDY for comparing different realtime semantic segmentation architectures.

## Description

Semantic segmentation benefits robotics related applications especially autonomous driving. Most of the research on semantic segmentation is only on increasing the accuracy of segmentation models with little attention to computationally efficient solutions. The few work conducted in this direction does not provide principled methods to evaluate the different design choices for segmentation. In this paper, we address this gap by presenting a real-time semantic segmentation benchmarking framework with a decoupled design for feature extraction and decoding methods. The code and the experimental results are presented on the CityScapes dataset for urban scenes.

https://www.arxiv-vanity.com/papers/1803.02758/

https://github.com/MSiam/TFSegmentation

https://m.weibo.cn/1402400261/4216793734309974

“完整内容”请点击【阅读原文】
↓↓↓

### 相关内容

Existing Earth Vision datasets are either suitable for semantic segmentation or object detection. In this work, we introduce the first benchmark dataset for instance segmentation in aerial imagery that combines instance-level object detection and pixel-level segmentation tasks. In comparison to instance segmentation in natural scenes, aerial images present unique challenges e.g., a huge number of instances per image, large object-scale variations and abundant tiny objects. Our large-scale and densely annotated Instance Segmentation in Aerial Images Dataset (iSAID) comes with 655,451 object instances for 15 categories across 2,806 high-resolution images. Such precise per-pixel annotations for each instance ensure accurate localization that is essential for detailed scene analysis. Compared to existing small-scale aerial image based instance segmentation datasets, iSAID contains 15$\times$ the number of object categories and 5$\times$ the number of instances. We benchmark our dataset using two popular instance segmentation approaches for natural images, namely Mask R-CNN and PANet. In our experiments we show that direct application of off-the-shelf Mask R-CNN and PANet on aerial images provide suboptimal instance segmentation results, thus requiring specialized solutions from the research community. The dataset is publicly available at: https://captain-whu.github.io/iSAID/index.html

Semantic segmentation requires both rich spatial information and sizeable receptive field. However, modern approaches usually compromise spatial resolution to achieve real-time inference speed, which leads to poor performance. In this paper, we address this dilemma with a novel Bilateral Segmentation Network (BiSeNet). We first design a Spatial Path with a small stride to preserve the spatial information and generate high-resolution features. Meanwhile, a Context Path with a fast downsampling strategy is employed to obtain sufficient receptive field. On top of the two paths, we introduce a new Feature Fusion Module to combine features efficiently. The proposed architecture makes a right balance between the speed and segmentation performance on Cityscapes, CamVid, and COCO-Stuff datasets. Specifically, for a 2048x1024 input, we achieve 68.4% Mean IOU on the Cityscapes test dataset with speed of 105 FPS on one NVIDIA Titan XP card, which is significantly faster than the existing methods with comparable performance.

In this work, we evaluate the use of superpixel pooling layers in deep network architectures for semantic segmentation. Superpixel pooling is a flexible and efficient replacement for other pooling strategies that incorporates spatial prior information. We propose a simple and efficient GPU-implementation of the layer and explore several designs for the integration of the layer into existing network architectures. We provide experimental results on the IBSR and Cityscapes dataset, demonstrating that superpixel pooling can be leveraged to consistently increase network accuracy with minimal computational overhead. Source code is available at https://github.com/bermanmaxim/superpixPool

AI研习社
9+阅读 · 2019年5月4日

7+阅读 · 2019年2月26日

19+阅读 · 2019年1月28日

35+阅读 · 2018年3月5日

8+阅读 · 2017年12月5日

5+阅读 · 2017年11月16日

16+阅读 · 2017年11月5日

6+阅读 · 2017年10月18日

17+阅读 · 2017年8月31日

38+阅读 · 2020年6月20日

41+阅读 · 2020年3月19日

97+阅读 · 2020年3月12日

97+阅读 · 2020年3月1日

42+阅读 · 2020年2月26日

25+阅读 · 2019年10月11日

41+阅读 · 2019年10月10日

9+阅读 · 2019年10月9日

41+阅读 · 2019年10月9日

54+阅读 · 2019年10月9日

Yanwei Li,Lin Song,Yukang Chen,Zeming Li,Xiangyu Zhang,Xingang Wang,Jian Sun
5+阅读 · 2020年3月23日
Syed Waqas Zamir,Aditya Arora,Akshita Gupta,Salman Khan,Guolei Sun,Fahad Shahbaz Khan,Fan Zhu,Ling Shao,Gui-Song Xia,Xiang Bai
7+阅读 · 2019年8月28日
Ruochen Fan,Ming-Ming Cheng,Qibin Hou,Tai-Jiang Mu,Jingdong Wang,Shi-Min Hu
7+阅读 · 2019年4月10日
Chenxi Liu,Liang-Chieh Chen,Florian Schroff,Hartwig Adam,Wei Hua,Alan Yuille,Li Fei-Fei
5+阅读 · 2019年1月10日
Juntang Zhuang,Junlin Yang
7+阅读 · 2018年12月10日
Ken C. L. Wong,Tanveer Syeda-Mahmood,Mehdi Moradi
4+阅读 · 2018年8月15日
Changqian Yu,Jingbo Wang,Chao Peng,Changxin Gao,Gang Yu,Nong Sang
4+阅读 · 2018年8月2日
Aliasghar Mortazi,Ulas Bagci
9+阅读 · 2018年7月19日
Mathijs Schuurmans,Maxim Berman,Matthew B. Blaschko
5+阅读 · 2018年6月7日
Kaiming He,Georgia Gkioxari,Piotr Dollár,Ross Girshick
7+阅读 · 2018年1月24日
Top