发布于44个月以前
- 1
- 0
- 823
Fast-SCNN: Fast Semantic Segmentation Network
The encoder-decoder framework is state-of-the-art for offline semantic image segmentation. Since the rise in autonomous systems, real-time computation is increasingly desirable. In this paper, we introduce fast segmentation convolutional neural network (Fast-SCNN), an above realtime semantic segmentation model on high resolution image data (1024 × 2048px) suited to efficient computation on embedded devices with low memory. Building on existing two-branch methods for fast segmentation, we introduce our ‘learning to downsample’ module which computes lowlevel features for multiple resolution branches simultaneously. Our network combines spatial detail at high resolution with deep features extracted at lower resolution, yielding an accuracy of 68.0% mean intersection over union at 123.5 frames per second on Cityscapes. We also show that large scale pre-training is unnecessary. We thoroughly validate our metric in experiments with ImageNet pre-training and the coarse labeled data of Cityscapes. Finally, we show even faster computation with competitive results on subsampled inputs, without any network modifications.
论文下载
论文地址:https://arxiv.org/pdf/1902.04502.pdf
算法链接
算法:https://marketplace.huaweicloud.com/markets/aihub/modelhub/detail/?id=3c570119-69c1-40ec-9d41-2ab3ff0f6de7
Notebook:https://marketplace.huaweicloud.com/markets/aihub/notebook/detail/?id=9b6ab7a9-9b05-4751-8473-e6e134f830e8
算法指南
算法指南:https://bbs.huaweicloud.com/forum/thread-86880-1-1.html
论文精读
评论 0

作者相关内容
热门内容推荐




