The source code is publicly available: https://github.com/kulikovv/DeepColoring.
Open resource ↗kulikovv/DeepColoring · pdf-page:1 lines:1-64Unverified paper record
Instance Segmentation by Deep Coloring
arXiv · 26 Jul 2018 · 10.48550/arxiv.1807.10007
Abstract
We propose a new and, arguably, a very simple reduction of instance segmentation to semantic segmentation. This reduction allows to train feed-forward non-recurrent deep instance segmentation systems in an end-to-end fashion using architectures that have been proposed for semantic segmentation. Our approach proceeds by introducing a fixed number of labels (colors) and then dynamically assigning object instances to those labels during training (coloring). A standard semantic segmentation objective is then used to train a network that can color previously unseen images. At test time, individual object instances can be recovered from the output of the trained convolutional network using simple connected component analysis. In the experimental validation, the coloring approach is shown to be capable of solving diverse instance segmentation tasks arising in autonomous driving (the Cityscapes benchmark), plant phenotyping (the CVPPP leaf segmentation challenge), and high-throughput microscopy image analysis. The source code is publicly available: https://github.com/kulikovv/DeepColoring.
Plant phenotyping relevance
インスタンスセグメンテーション手法の開発と実験検証が中心で、植物フェノタイピングの葉セグメンテーション課題に明示的に適用されている。
abstractWe propose a new and, arguably, a very simple reduction of instance segmentation to semantic segmentation.
abstractIn the experimental validation, the coloring approach is shown to be capable of solving diverse instance segmentation tasks arising in autonomous driving (the Cityscapes benchmark), plant phenotyping (the CVPPP leaf segmentation challenge), and high-throughput microscopy image analysis.
Code and data availability
The paper applies its Deep Coloring instance segmentation method to plant phenotyping (CVPPP leaf segmentation) and states its PyTorch implementation is publicly available on GitHub, enabling reproduction of the phenotyping analysis.
This is an automatically classified, unverified record. Curator approval is required before any resource enters the Catalog.