• Home
  • Search
  • DTS-Net: Depth-to-Space Networks for Fast and Accurate Semantic Object Segmentation
  • Open Access IconOpen Access
  • Cite Icon11
  • https://doi.org/10.3390/s22010337Copy DOI Icon

DTS-Net: Depth-to-Space Networks for Fast and Accurate Semantic Object Segmentation

Show More
  • Abstract
  • Highlights & Summary
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

We propose Depth-to-Space Net (DTS-Net), an effective technique for semantic segmentation using the efficient sub-pixel convolutional neural network. This technique is inspired by depth-to-space (DTS) image reconstruction, which was originally used for image and video super-resolution tasks, combined with a mask enhancement filtration technique based on multi-label classification, namely, Nearest Label Filtration. In the proposed technique, we employ depth-wise separable convolution-based architectures. We propose both a deep network, that is, DTS-Net, and a lightweight network, DTS-Net-Lite, for real-time semantic segmentation; these networks employ Xception and MobileNetV2 architectures as the feature extractors, respectively. In addition, we explore the joint semantic segmentation and depth estimation task and demonstrate that the proposed technique can efficiently perform both tasks simultaneously, outperforming state-of-art (SOTA) methods. We train and evaluate the performance of the proposed method on the PASCAL VOC2012, NYUV2, and CITYSCAPES benchmarks. Hence, we obtain high mean intersection over union (mIOU) and mean pixel accuracy (Pix.acc.) values using simple and lightweight convolutional neural network architectures of the developed networks. Notably, the proposed method outperforms SOTA methods that depend on encoder–decoder architectures, although our implementation and computations are far simpler.

Loading PDF

Similar Papers
  • Conference Article

A Novel Framework for Semantic Image Segmentation using Generative Adversarial Networks and Neural Architecture Search

  • Aug 11, 2021
  • Vayangi Vishmi Vishara Ganepola +1
  • Research Article
  • Citations1

CSA − HRNet: Channel and Spatial Attention High-Resolution Networks for Semantic Segmentation

  • Dec 10, 2025
  • Journal of Signal Processing Systems
  • Jin-Seong Kim +4
  • PDF
  • Research Article
  • Citations13

Real-Time Semantic Understanding and Segmentation of Urban Scenes for Vehicle Visual Sensors by Optimized DCNN Algorithm

  • Aug 03, 2022
  • Applied Sciences
  • Yanyi Li +2
  • Research Article
  • Citations699

Classification with an edge: Improving semantic image segmentation with boundary detection

  • Dec 05, 2017
  • ISPRS Journal of Photogrammetry and Remote Sensing
  • D Marmanis +5
  • PDF
  • Research Article
  • Citations93

A Lightweight Complex-Valued DeepLabv3+ for Semantic Segmentation of PolSAR Image

  • Jan 01, 2022
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • Lingjuan Yu +6
  • Research Article
  • Citations38

Semantic segmentation of point cloud data using raw laser scanner measurements and deep neural networks

  • Dec 16, 2021
  • ISPRS Open Journal of Photogrammetry and Remote Sensing
  • Risto Kaijaluoto +4
  • Conference Article
  • Citations141

Multi-Scale Multi-Task FCN for Semantic Page Segmentation and Table Detection

  • Nov 01, 2017
  • Dafang He +4
  • PDF
  • Research Article
  • Citations43

Semantic Image Segmentation with Deep Convolutional Neural Networks and Quick Shift

  • Mar 06, 2020
  • Symmetry
  • Sanxing Zhang +5
  • Research Article
  • Citations131

Densely Based Multi-Scale and Multi-Modal Fully Convolutional Networks for High-Resolution Remote-Sensing Image Semantic Segmentation

  • Aug 01, 2019
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • Cheng Peng +4
  • Conference Article

Generative Adversarial Networks Using Neural Architecture Search for Semantic Image Segmentation

  • Jul 02, 2021
  • Vayangi Vishmi Vishara Ganepola +1
  • Research Article

MPSS: A Model Pruning Method for Semantic Image Segmentation Networks

  • Jan 01, 2026
  • IEEE Transactions on Multimedia
  • Yeqiang Qian +3
  • Research Article
  • Citations48

Improving RGB-D SLAM accuracy in dynamic environments based on semantic and geometric constraints

  • May 26, 2023
  • Measurement
  • Xiqi Wang +3
  • PDF
  • Book Chapter
  • Citations42

NNV 2.0: The Neural Network Verification Tool

  • Jan 01, 2023
  • Diego Manzanas Lopez +3
  • Research Article
  • Citations6

Weakly supervised semantic segmentation by knowledge graph inference

  • Sep 11, 2024
  • Engineering Applications of Artificial Intelligence
  • Jia Zhang +3
  • Research Article
  • Citations11

Multi-scale dense and attention mechanism for image semantic segmentation based on improved DeepLabv3+

  • Sep 08, 2022
  • Journal of Electronic Imaging
  • Zuoshuai Wang +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.