# NoPeopleAllowed: The Three-Step Approach to Weakly Supervised Semantic Segmentation

Source: [NoPeopleAllowed: The Three-Step Approach to Weakly Supervised Semantic Segmentation](<https://www.sota2.com/research/paper/68fa67b31e209131cea17e26>)

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

Data updated: 2025-10-25T22:20:05.971Z

Authors: Mariia Dobko, Ostap Viniavskyi, Oles Dobosevych

Published: 2020-06-13T09:56:18.000Z

## Abstract

We propose a novel approach to weakly supervised semantic segmentation, which consists of three consecutive steps. The first two steps extract high-quality pseudo masks from image-level annotated data, which are then used to train a segmentation model on the third step. The presented approach also addresses two problems in the data: class imbalance and missing labels. Using only image-level annotations as supervision, our method is capable of segmenting various classes and complex objects. It achieves 37.34 mean IoU on the test set, placing 3rd at the LID Challenge in the task of weakly supervised semantic segmentation.

## 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/2006.07601>)

[PDF](<https://arxiv.org/pdf/2006.07601.pdf>)