DifNet: Semantic Segmentation by DiffusionNetworks

05/21/2018
by   Peng Jiang, et al.
2

Deep Neural Networks (DNNs) have recently shown state of the art performance on semantic segmentation tasks, however they still suffer from problems of poor boundary localization and spatial fragmented predictions. The difficulties lie in the requirement of making dense predictions from a long path model all at once, since details are hard to keep when data goes through deeper layers. Instead, in this work, we decompose this difficult task into two relative simple sub-tasks: seed detection which is required to predict initial predictions without need of wholeness and preciseness, and similarity estimation which measures the possibility of any two nodes belong to the same class without need of knowing which class they are. We use one branch for one sub-task each, and apply a cascade of random walks base on hierarchical semantics to approximate a complex diffusion process which propagates seed information to the whole image according to the estimated similarities. The proposed DifNet consistently produces improvements over the baseline models with the same depth and with equivalent number of parameters, and also achieves promising performance on Pascal VOC and Pascal Context dataset. Our DifNet is trained end-to-end without complex loss functions.

READ FULL TEXT

page 5

page 7

page 8

research
05/21/2018

DifNet: Semantic Segmentation by Diffusion Networks

Deep Neural Networks (DNNs) have recently shown state of the art perform...
research
07/29/2021

A Unified Efficient Pyramid Transformer for Semantic Segmentation

Semantic segmentation is a challenging problem due to difficulties in mo...
research
07/20/2017

Semantic Segmentation with Reverse Attention

Recent development in fully convolutional neural network enables efficie...
research
04/05/2017

Not All Pixels Are Equal: Difficulty-aware Semantic Segmentation via Deep Layer Cascade

We propose a novel deep layer cascade (LC) method to improve the accurac...
research
01/27/2019

Pixelated Semantic Colorization

While many image colorization algorithms have recently shown the capabil...
research
09/16/2020

DAER to Reject Seeds with Dual-loss Additional Error Regression

Many vision tasks require side information at inference time—a seed—to f...
research
01/10/2023

Explaining Deep Models through Forgettable Learning Dynamics

Even though deep neural networks have shown tremendous success in countl...

Please sign up or login with your details

Forgot password? Click here to reset