语义分割--DeconvNet--Learning Deconvolution Network for Semantic Segmentation

Learning Deconvolution Network for Semantic Segmentation
ICCV2015
http://cvlab.postech.ac.kr/research/deconvnet/
https://devhub.io/zh/repos/myungsub-DeconvNet

本文提出了一个 deconvolution network 用于语义分割，还是针对 FCN 改善的。在pooling operation 记录 the locations of maximum activations ，将这些位置用于 unpooling
这一点和 SegNet 是一样的。

首先来说说FCN 有什么问题？

FCN 的 limitations：
1）FCN 因为其固定尺寸receptive field只能解决单尺度的semantics ，对于过大过小的目标分割都有可能有问题
the network can handle only a single scale semantics within image due to the fixed-size receptive field. Therefore, the object that is substantially larger or smaller than the receptive field may be fragmented or mislabeled.
2）FCN 的 deconvolution procedure 太粗糙太简单，FCN 的 deconvolution procedure输入尺寸只有16 × 16，将这个尺寸通过 bilinear interpolation 放大到输入图像尺寸。目标很多细节信息丢失

3 System Architecture

我们的网络包括两个部分：convolution and deconvolution networks

卷积网络用于提取特征，使用 VGG 16-layer net
convolution network corresponds to feature extractor

反卷积网络根据特征产生分割结果
deconvolution network is a shape generator that produces object segmentation from the feature extracted from the convolution network.

3.2. Deconvolution Network for Segmentation
反卷积网络中主要有两个操作步骤： unpooling and deconvolution

3.2.1 Unpooling
Pooling 会产生降采样的效果，导致一些细节丢失。 spatial information within a receptive field is lost during pooling，这些信息对于语义分割很重要。为了解决这个问题，我们在反卷积网络中使用 unpooling layers， It
records the locations of maximum activations selected during pooling operation in switch variables, which are employed to place each activation back to its original pooled location.

3.2.2 Deconvolution
unpooling layers 得到一个放大的但是稀疏的响应特征图，这里通过deconvolution layers 来将稀疏的特征变为稠密的特征
The deconvolution layers densify the sparse activations obtained by unpooling through convolution-like operations with multiple learned filters.

The learned filters in deconvolutional layers correspond to bases to reconstruct shape of an input object.

Unpooling captures example-specific structures
learned filters in deconvolutional layers tend to capture class-specific shapes

与FCN 效果对比：

PASCAL VOC 2012 test set

instance-wise prediction 的好处

本文算法较FCN的细节要好些

FCN 的全局观要好一些

与FCN的结合

语义分割--DeconvNet--Learning Deconvolution Network for Semantic Segmentation相关推荐

【语义分割】Fully Attentional Network for Semantic Segmentation
文章目录一.背景和动机二.方法三.效果本文收录于 AAAI2022 一.背景和动机语义分割中,non-local (NL)的方法起到了很好了捕捉 long-range 信息的作用,大致可分为 ...
ECCV2020语义分割——Self-Prediction for Joint Instance and Semantic Segmentation of Point Clouds
Self-Prediction for Joint Instance and Semantic Segmentation of Point Clouds Abstract (一) Introducti ...
【语义分割】CVPR2021_Rethinking BiSeNet For Real-time Semantic Segmentation
文章目录一.背景二.动机三.方法 3.1 Design of Encoding Network 3.2 Decoder 四.实验 4.1 消融实验 4.2 和 SOTA 方法对比 Paper: ...
【语义分割】DUC -- Understand Convolution for Semantic Segmentation
参考:Understand Convolution for Semantic Segmentation
语义分割--(DFN)Learning a Discriminative Feature Network for Semantic Segmentation
Learning a Discriminative Feature Network for Semantic Segmentation Learning a Discriminative Featur ...
[分割]Learning a Discriminative Feature Network for Semantic Segmentation(DFN)
本文转自3篇文章当作自己的笔记. 文章1:链接 Learning a Discriminative Feature Network for Semantic Segmentation Learning ...
轻量级实时语义分割：Guided Upsampling Network for Real-Time Semantic Segmentation
轻量级实时语义分割:Guided Upsampling Network for Real-Time Semantic Segmentation 介绍网络设计 Guided unsampling mo ...
CGNet: A Light-weight Context Guided Network for Semantic Segmentation
CGNet: A Light-weight Context Guided Network for Semantic Segmentation 0.摘要移动设备中语义分割模型应用增加,然大部分网络的参 ...
Pyramid Attention Network for Semantic Segmentation
翻译 | 林椿眄出品 | 人工智能头条(公众号ID:AI_Thinker) 近日,北京理工大学.旷视科技.北京大学联手,发表了一篇名为 Pyramid Attention Network for S ...

语义分割--DeconvNet--Learning Deconvolution Network for Semantic Segmentation

语义分割--DeconvNet--Learning Deconvolution Network for Semantic Segmentation相关推荐

最新文章

热门文章