Classification With an Edge: Improving Semantic Image Segmentation with Boundary Detection

12/05/2016
by   Dimitrios Marmanis, et al.
0

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.

READ FULL TEXT

page 3

page 12

page 14

page 25

research
03/31/2016

Object Boundary Guided Semantic Segmentation

Semantic segmentation is critical to image content understanding and obj...
research
07/16/2019

Efficient Segmentation: Learning Downsampling Near Semantic Boundaries

Many automated processes such as auto-piloting rely on a good semantic s...
research
06/27/2019

ELKPPNet: An Edge-aware Neural Network with Large Kernel Pyramid Pooling for Learning Discriminative Features in Semantic Segmentation

Semantic segmentation has been a hot topic across diverse research field...
research
05/20/2019

Boundary Loss for Remote Sensing Imagery Semantic Segmentation

In response to the growing importance of geospatial data, its analysis i...
research
04/08/2021

BEFD: Boundary Enhancement and Feature Denoising for Vessel Segmentation

Blood vessel segmentation is crucial for many diagnostic and research ap...
research
07/26/2018

Learning to predict crisp boundaries

Recent methods for boundary or edge detection built on Deep Convolutiona...
research
07/12/2019

Gated-SCNN: Gated Shape CNNs for Semantic Segmentation

Current state-of-the-art methods for image segmentation form a dense ima...

Please sign up or login with your details

Forgot password? Click here to reset