# Semantic Binary Segmentation using Convolutional Networks without Decoders

arXiv: https://arxiv.org/abs/1805.00138 · HTML: https://mlsanity.com/paper/1805.00138/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 May 2018.

## Built on by (most cited first, 3 of 3)

- [A Novel Benchmark for Few-Shot Semantic Segmentation in the Era of Foundation Models](https://mlsanity.com/paper/2401.11311/) (2024)
- [Urban Change Detection by Fully Convolutional Siamese Concatenate Network with Attention](https://mlsanity.com/paper/2102.00501/) (2021)
- [Robust Visual Tracking by Motion Analyzing](https://mlsanity.com/paper/2309.03247/) (2023)

## Abstract (arXiv)

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.