Pixel Deconvolutional Networks

05/18/2017
by   Hongyang Gao, et al.
0

Deconvolutional layers have been widely used in a variety of deep models for up-sampling, including encoder-decoder networks for semantic segmentation and deep generative models for unsupervised learning. One of the key limitations of deconvolutional operations is that they result in the so-called checkerboard problem. This is caused by the fact that no direct relationship exists among adjacent pixels on the output feature map. To address this problem, we propose the pixel deconvolutional layer (PixelDCL) to establish direct relationships among adjacent pixels on the up-sampled feature map. Our method is based on a fresh interpretation of the regular deconvolution operation. The resulting PixelDCL can be used to replace any deconvolutional layer in a plug-and-play manner without compromising the fully trainable capabilities of original models. The proposed PixelDCL may result in slight decrease in efficiency, but this can be overcome by an implementation trick. Experimental results on semantic segmentation demonstrate that PixelDCL can consider spatial features such as edges and shapes and yields more accurate segmentation outputs than deconvolutional layers. When used in image generation tasks, our PixelDCL can largely overcome the checkerboard problem suffered by regular deconvolution operations.

READ FULL TEXT

page 2

page 6

page 7

page 8

research
02/16/2016

Deconvolutional Feature Stacking for Weakly-Supervised Semantic Segmentation

A weakly-supervised semantic segmentation framework with a tied deconvol...
research
10/09/2020

Deep Learning Superpixel Semantic Segmentation with Transparent Initialization and Sparse Encoder

Even though deep learning greatly improves the performance of semantic s...
research
09/20/2023

More complex encoder is not all you need

U-Net and its variants have been widely used in medical image segmentati...
research
05/11/2019

Graph U-Nets

We consider the problem of representation learning for graph data. Convo...
research
02/26/2020

Towards Interpretable Semantic Segmentation via Gradient-weighted Class Activation Mapping

Convolutional neural networks have become state-of-the-art in a wide ran...
research
07/05/2019

RED: A ReRAM-based Deconvolution Accelerator

Deconvolution has been widespread in neural networks. For example, it is...
research
06/30/2017

Superpixel-based Semantic Segmentation Trained by Statistical Process Control

Semantic segmentation, like other fields of computer vision, has seen a ...

Please sign up or login with your details

Forgot password? Click here to reset