Entropy-Based Feature Extraction For Real-Time Semantic Segmentation

07/07/2022
by   Lusine Abrahamyan, et al.
0

This paper introduces an efficient patch-based computational module, coined Entropy-based Patch Encoder (EPE) module, for resource-constrained semantic segmentation. The EPE module consists of three lightweight fully-convolutional encoders, each extracting features from image patches with a different amount of entropy. Patches with high entropy are being processed by the encoder with the largest number of parameters, patches with moderate entropy are processed by the encoder with a moderate number of parameters, and patches with low entropy are processed by the smallest encoder. The intuition behind the module is the following: as patches with high entropy contain more information, they need an encoder with more parameters, unlike low entropy patches, which can be processed using a small encoder. Consequently, processing part of the patches via the smaller encoder can significantly reduce the computational cost of the module. Experiments show that EPE can boost the performance of existing real-time semantic segmentation models with a slight increase in the computational cost. Specifically, EPE increases the mIOU performance of DFANet A by 0.9 performance of EDANet by 1

READ FULL TEXT

page 3

page 4

research
03/16/2021

EADNet: Efficient Asymmetric Dilated Network for Semantic Segmentation

Due to real-time image semantic segmentation needs on power constrained ...
research
05/01/2023

PRSeg: A Lightweight Patch Rotate MLP Decoder for Semantic Segmentation

The lightweight MLP-based decoder has become increasingly promising for ...
research
06/27/2022

Patch Selection for Melanoma Classification

In medical image processing, the most important information is often loc...
research
06/04/2020

LRNNet: A Light-Weighted Network with Efficient Reduced Non-Local Operation for Real-Time Semantic Segmentation

The recent development of light-weighted neural networks has promoted th...
research
06/03/2023

Content-aware Token Sharing for Efficient Semantic Segmentation with Vision Transformers

This paper introduces Content-aware Token Sharing (CTS), a token reducti...
research
04/11/2018

Dynamic Multi-Scale Semantic Segmentation based on Dilated Convolutional Networks

Semantic segmentation requires methods capable of learning high-level fe...
research
10/27/2022

Class Based Thresholding in Early Exit Semantic Segmentation Networks

We propose Class Based Thresholding (CBT) to reduce the computational co...

Please sign up or login with your details

Forgot password? Click here to reset