Fast Semantic Segmentation for Scene Perception

2024-05-13 11:22:21

Abstract:

当前大部分的语义分割方法关注精度，而不是效率。本文提出了一种更有 efficient 的神经网络结构，有更少的参数。模型是基于 Resnet 的不对称编解码结构。在编码器的第一阶段，使用 continuous factorized block 提取 low-level features。第二阶段使用连续的 dilated block，确保模型有更大的感受野，保持模型 small-scale and shallow。
The parametersof our model are only 0.2M , 100× less than those of otherssuch as SegNet, etc.

Network

原文对于Initial Block 描述：
On the one hand, the initial block uses the convolution filter to obtain the features.On the other hand, the maxpooling reserves the original information and helps to train faster.

连续的空洞卷积CDB 使模型可能看起来更宽，这将导致一些更小和更薄的类，如标识，栅栏和杆，很难分割，但在一些更大的类，如道路，天空和树，表现得更好。

连续的分离模块CFB It greatly reduces the number of parameters and speeds up the training. （不对称卷积）
down-sampling block 和 up-sampling block

Fast Semantic Segmentation for Scene Perception相关推荐

ICCV2019(Segmentation)：ShelfNet-论文解读《ShelfNet for Fast Semantic Segmentation》
文章目录原文地址论文阅读方法初识(Abstract & Introduction & Conclusion) 相知(Body) 2. Related Work 2.1 Seman ...
Fully Convolutional Networks for Semantic Segmentation (FCN)论文翻译和理解
论文题目:Fully Convolutional Networks for Semantic Segmentation 论文来源:Fully Convolutional Networks for Se ...
Deep Projective 3D Semantic Segmentation
Deep Projective 3D Semantic Segmentation 原文:https://arxiv.org/abs/1705.03428 深度投影3D语义分割摘要三维点云的语义分割 ...
【论文翻译】Fully Convolutional Networks for Semantic Segmentation
论文题目:Fully Convolutional Networks for Semantic Segmentation 论文来源:Fully Convolutional Networks for Se ...
【ESANet2021】Efficient RGB-D Semantic Segmentation for Indoor Scene Analysis
Efficient RGB-D Semantic Segmentation for Indoor Scene Analysis 室内场景分析的高效RGB-D语义分割 arXiv:2011.06961v ...
Fully Convolutional Networks for semantic Segmentation（深度学习经典论文翻译）
原文链接:https://www.cnblogs.com/xuanxufeng/p/6249834.html 摘要卷积网络在特征分层领域是非常强大的视觉模型.我们证明了经过端到端.像素到像素训练的卷 ...
目标检测经典论文——R-CNN论文翻译：Rich feature hierarchies for accurate object detection and semantic segmentation
Rich feature hierarchies for accurate object detection and semantic segmentation--Tech report (v5) 用 ...
【FCN2015】Fully Convolutional Networks for Semantic Segmentation
Fully Convolutional Networks for Semantic Segmentation 用于语义分割的全卷积网络 arXiv:1411.4038v2 [cs.CV] 8 Mar ...
【ACNET2019】：ATTENTION BASED NETWORK TO EXPLOIT COMPLEMENTARY FEATURES FOR RGBD SEMANTIC SEGMENTATION
ACNET: ATTENTION BASED NETWORK TO EXPLOIT COMPLEMENTARY FEATURES FOR RGBD SEMANTIC SEGMENTATION ACNE ...

最新文章

热门文章