MiniNet: An Efficient Semantic Segmentation ConvNet for Real-Time Robotic Applications
- 3 March 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Robotics
- Vol. 36 (4) , 1340-1347
Abstract
Efficient models for semantic segmentation, in terms of memory, speed, and computation, could boost many robotic applications with strong computational and temporal restrictions. This article presents a detailed analysis of different techniques for efficient semantic segmentation. Following this analysis, we have developed a novel architecture, MiniNet-v2, an enhanced version of MiniNet. MiniNet-v2 is built considering the best option depending on CPU or GPU availability. It reaches comparable accuracy to the state-of-the-art models but uses less memory and computational resources. We validate and analyze the details of our architecture through a comprehensive set of experiments on public benchmarks (Cityscapes, Camvid, and COCO-Text datasets), showing its benefits over relevant prior work. Our experiments include a sample application where these models can boost existing robotic applications.Keywords
This publication has 17 references indexed in Scilit:
- Train Here, Deploy There: Robust Segmentation in Unseen Domains2018
- ERFNet: Efficient Residual Factorized ConvNet for Real-Time Semantic SegmentationIEEE Transactions on Intelligent Transportation Systems, 2017
- Densely Connected Convolutional Networks2017
- Pyramid Scene Parsing Network2017
- The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation2017
- SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image SegmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- Deep Residual Learning for Image Recognition2016
- The Cityscapes Dataset for Semantic Urban Scene Understanding2016
- Fully convolutional networks for semantic segmentation2015
- Semantic object classes in video: A high-definition ground truth databasePattern Recognition Letters, 2009