Classification With an Edge: Improving Semantic Image Segmentation with Boundary Detection
Abstract
We present an end-to-end trainable deep convolutional neural network (DCNN) for semantic segmentation with built-in awareness of semantically meaningful boundaries. Semantic segmentation is a fundamental remote sensing task, and most state-of-the-art methods rely on DCNNs as their workhorse. A major reason for their success is that deep networks learn to accumulate contextual information over very large windows (receptive fields). However, this success comes at a cost, since the associated loss of effecive spatial resolution washes out high-frequency details and leads to blurry object boundaries. Here, we propose to counter this effect by combining semantic segmentation with semantically informed edge detection, thus making class-boundaries explicit in the model, First, we construct a comparatively simple, memory-efficient model by adding boundary detection to the Segnet encoder-decoder architecture. Second, we also include boundary detection in FCN-type models and set up a high-end classifier ensemble. We show that boundary detection significantly improves semantic segmentation with CNNs. Our high-end ensemble achieves > 90% overall accuracy on the ISPRS Vaihingen benchmark.
Cite
@article{arxiv.1612.01337,
title = {Classification With an Edge: Improving Semantic Image Segmentation with Boundary Detection},
author = {Dimitrios Marmanis and Konrad Schindler and Jan Dirk Wegner and Silvano Galliani and Mihai Datcu and Uwe Stilla},
journal= {arXiv preprint arXiv:1612.01337},
year = {2017}
}