# Semantic Binary Segmentation using Convolutional Networks without Decoders

Source: [Semantic Binary Segmentation using Convolutional Networks without Decoders](<https://www.sota2.com/research/paper/68fa64671e209131cea046db>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:03:11.991Z

Authors: Shubhra Aich, William van der Kamp, Ian Stavness

Published: 2018-05-01T00:10:12.000Z

## Abstract

In this paper, we propose an efficient architecture for semantic image segmentation using the depth-to-space (D2S) operation. Our D2S model is comprised of a standard CNN encoder followed by a depth-to-space reordering of the final convolutional feature maps. Our approach eliminates the decoder portion of traditional encoder-decoder segmentation models and reduces the amount of computation almost by half. As a participant of the DeepGlobe Road Extraction competition, we evaluate our models on the corresponding road segmentation dataset. Our highly efficient D2S models exhibit comparable performance to standard segmentation models with much lower computational cost.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1805.00138>)

[PDF](<https://arxiv.org/pdf/1805.00138.pdf>)
