arxivst stuff from arxiv that you should probably bookmark

Deep Contextual Recurrent Residual Networks for Scene Labeling

Abstract · Apr 12, 2017 01:52 ·

crrn hoang residual labeling scene visual beach contextual cs-cv

Arxiv Abstract

  • T. Hoang Ngan Le
  • Chi Nhan Duong
  • Ligong Han
  • Khoa Luu
  • Marios Savvides
  • Dipan Pal

Designed as extremely deep architectures, deep residual networks which provide a rich visual representation and offer robust convergence behaviors have recently achieved exceptional performance in numerous computer vision problems. Being directly applied to a scene labeling problem, however, they were limited to capture long-range contextual dependence, which is a critical aspect. To address this issue, we propose a novel approach, Contextual Recurrent Residual Networks (CRRN) which is able to simultaneously handle rich visual representation learning and long-range context modeling within a fully end-to-end deep network. Furthermore, our proposed end-to-end CRRN is completely trained from scratch, without using any pre-trained models in contrast to most existing methods usually fine-tuned from the state-of-the-art pre-trained models, e.g. VGG-16, ResNet, etc. The experiments are conducted on four challenging scene labeling datasets, i.e. SiftFlow, CamVid, Stanford background and SUN datasets, and compared against various state-of-the-art scene labeling methods.

Read the paper (pdf) »