• Home
  • Search
  • RelationNet: Learning Deep-Aligned Representation for Semantic Image Segmentation
  • Cite Icon20
  • https://doi.org/10.1109/icpr.2018.8545708Copy DOI Icon

RelationNet: Learning Deep-Aligned Representation for Semantic Image Segmentation

  • Aug 1, 2018
  • Yueqing Zhuang +6 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Semantic image segmentation, which assigns labels in pixel level, plays a central role in image understanding. Recent approaches have attempted to harness the capabilities of deep learning. However, one central problem of these methods is that deep convolutional neural network gives little consideration to the correlation among pixels. To handle this issue, in this paper, we propose a novel deep neural network named RelationNet, which utilizes CNN and RNN to aggregate context information. Besides, a spatial correlation loss is applied to train RelationNet to align features of spatial pixels belonging to same category. Importantly, since it is expensive to obtain pixel-wise annotations, we exploit a new training method to combine the coarsely and finely labeled data. Experiments show the detailed improvements of each proposal. Experimental results demonstrate the effectiveness of our proposed method to the problem of semantic image segmentation, which obtains state-of-the-art performance on the Cityscapes benchmark and Pascal Context dataset.

Similar Papers
  • Conference Article
  • Citations2704

Conditional Random Fields as Recurrent Neural Networks

  • Dec 01, 2015
  • Shuai Zheng +7
  • Research Article
  • Citations8

Adversarial Robustness of Deep Convolutional Neural Network-based Image Recognition Models: A Review

  • Aug 28, 2021
  • 雷达学报
  • Hao Sun +4
  • Conference Article
  • Citations21

Traffic Scene Semantic Segmentation by Using Several Deep Convolutional Neural Networks

  • Dec 03, 2021
  • Amine Kherraki +2
  • Research Article
  • Citations107

Deep convolutional neural network for automatic fault recognition from 3D seismic datasets

  • Apr 16, 2021
  • Computers & Geosciences
  • Yu An +5
  • Conference Article

Semantic segmentation of rodent burrows using deep convolutional architectures

  • Jan 05, 2023
  • Mikhail Uzdiaev +2
  • Conference Article
  • Citations5

Architecturally Compressed CNN: An Embedded Realtime Classifier (NXP Bluebox2.0 with RTMaps)

  • Jan 01, 2019
  • Durvesh Pathak +1
  • Book Chapter
  • Citations1

Handwritten Digit Recognition Using Very Deep Convolutional Neural Network

  • Jan 01, 2022
  • M Dhilsath Fathima +2
  • Conference Article

Absolute distance measurement based on laser self-mixing interferometry and deep neural network

  • Dec 27, 2022
  • Jinyuan Yuan +2
  • PDF
  • Research Article
  • Citations64

Cursive Text Recognition in Natural Scene Images Using Deep Convolutional Recurrent Neural Network

  • Jan 01, 2022
  • IEEE Access
  • Asghar Ali Chandio +3
  • Conference Article
  • Citations7

Learning Panoptic Segmentation from Instance Contours

  • May 30, 2021
  • Sumanth Chennupati +4
  • Research Article
  • Citations103

Maxout neurons for deep convolutional and LSTM neural networks in speech recognition

  • Dec 17, 2015
  • Speech Communication
  • Meng Cai +1
  • PDF
  • Research Article
  • Citations263

Oil Spill Identification from Satellite Images Using Deep Neural Networks

  • Jul 26, 2019
  • Remote Sensing
  • Marios Krestenitis +5
  • PDF
  • Research Article
  • Citations25

FCN-Based Carrier Signal Detection in Broadband Power Spectrum

  • Jan 01, 2020
  • IEEE Access
  • Hao Huang +3
  • Research Article
  • Citations27

An overview on Meta-learning approaches for Few-shot Weakly-supervised Segmentation

  • May 20, 2023
  • Computers & Graphics
  • Pedro Henrique Targino Gama +3
  • Conference Article
  • Citations39

Multimodal and Crossmodal Representation Learning from Textual and Visual Features with Bidirectional Deep Neural Networks for Video Hyperlinking

  • Oct 16, 2016
  • Vedran Vukotić +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.