图像每像素场景标记输出问题(使用 FCN-32s 语义分割) [英] Image per-pixel Scene labeling output issue (using FCN-32s Semantic Segmentation)

问题描述

我正在寻找一种方法，在给定输入图像和神经网络的情况下，它会为图像中的每个像素(天空、草、山、人、汽车等)输出一个标记类.

我已经设置了 Caffe(未来分支)并成功运行了 ，它似乎对分辨率降低的影响较小.
查看 J Long、E Shelhamer、T Darrell 用于语义分割的全卷积网络, CVPR 2015(尤其是图 4)似乎 32s 模型并不是为捕捉分割的细节而设计的.

I'm looking for a way that, given an input image and a neural network, it will output a labeled class for each pixel in the image (sky, grass, mountain, person, car etc).

I've set up Caffe (the future-branch) and successfully run the FCN-32s Fully Convolutional Semantic Segmentation on PASCAL-Context model. However, I'm unable to produce clear labeled images with it.

Images that visualizes my problem:
Input image

ground truth

And my result:

This might be some resolution issue. Any idea of where I'm going wrong?

解决方案

It seems like the 32s model is making large strides and thus working at a coarse resolution. Can you try the 8s model that seems to perform less resolution reduction.
Looking at J Long, E Shelhamer, T Darrell Fully Convolutional Networks for Semantic Segmentation, CVPR 2015 (especially at figure 4) it seems like the 32s model is not designed for capturing fine details of the segmentation.

这篇关于图像每像素场景标记输出问题(使用 FCN-32s 语义分割)的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！