SPGNet: Semantic Prediction Guidance for Scene Parsing

Abstract

Multi-scale context module and single-stage encoder-decoder structure are commonly employed for semantic segmentation. Multi-scale context module aggregates feature responses from a large spatial extent, while the single-stage encoder-decoder structure encodes the high-level semantic information in the encoder path and recovers the boundary information in the decoder path. In contrast, multi-stage encoder-decoder networks have been widely used in human pose estimation and shown superior performance than their single-stage counterpart. However, few efforts have been attempted to bring this effective design to semantic segmentation. In this work, we propose a Semantic Prediction Guidance (SPG) module which learns to re-weight the local features through the guidance from pixel-wise semantic prediction. We find that by carefully re-weighting features across stages, a two-stage encoder-decoder network coupled with our proposed SPG module can significantly outperform its one-stage counterpart with similar parameters and computations. Finally, we report experimental results on the semantic segmentation benchmark Cityscapes, in which our SPGNet attains 81.1% on the test set using only fine annotations.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Oct 27, 2019
Accession Number
AD1153030

Entities

People

  • Bowen Cheng
  • Honghui Shi
  • Jinjun Xiong
  • Liang-Chieh Chen
  • Thomas Huang
  • Wen-mei Hwu
  • Yukun Zhu
  • Yunchao Wei
  • Zilong Huang

Organizations

  • IBM Research
  • University of Illinois Urbana–Champaign
  • University of Oregon

Tags

DTIC Thesaurus Topics

  • Ablation
  • Artificial Intelligence
  • Artificial Intelligence Computing
  • Artificial Intelligence Software
  • Classification
  • Coders
  • Computations
  • Computer Vision
  • Computers
  • Contrast
  • Convolution
  • Convolutional Neural Networks
  • Detection
  • Detectors
  • Guidance
  • High Resolution
  • Identities
  • Image Recognition
  • Image Segmentation
  • Neural Networks
  • Recognition
  • Test Sets

Fields of Study

  • Computer science

Readers

  • Computational Linguistics
  • Computer Programming and Software Development.
  • Computer Vision.