# EfficientSeg: An Efficient Semantic Segmentation Network

Source: [EfficientSeg: An Efficient Semantic Segmentation Network](<https://www.sota2.com/research/paper/68fa68821e209131cea1c8e7>)

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

Data updated: 2026-01-04T03:16:04.581Z

Authors: Vahit Bugra Yesilkaynak, Yusuf H. Sahin, Gozde Unal

Published: 2020-09-14T14:25:19.000Z

## Abstract

Deep neural network training without pre-trained weights and few data is shown to need more training iterations. It is also known that, deeper models are more successful than their shallow counterparts for semantic segmentation task. Thus, we introduce EfficientSeg architecture, a modified and scalable version of U-Net, which can be efficiently trained despite its depth. We evaluated EfficientSeg architecture on Minicity dataset and outperformed U-Net baseline score (40% mIoU) using the same parameter count (51.5% mIoU). Our most successful model obtained 58.1% mIoU score and got the fourth place in semantic segmentation track of ECCV 2020 VIPriors challenge.

## 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/2009.06469>)

[PDF](<https://arxiv.org/pdf/2009.06469.pdf>)

[Implementation](<https://github.com/MrGranddy/EfficientSeg>)