# Semi-Supervised Semantic Image Segmentation with Self-correcting Networks

Source: [Semi-Supervised Semantic Image Segmentation with Self-correcting Networks](<https://www.sota2.com/research/paper/68fa67191e209131cea1428d>)

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

Data updated: 2025-10-25T22:06:19.934Z

Authors: Mostafa S. Ibrahim, Arash Vahdat, Mani Ranjbar, William G. Macready

Published: 2018-11-17T01:20:03.000Z

## Abstract

Building a large image dataset with high-quality object masks for semantic segmentation is costly and time consuming. In this paper, we introduce a principled semi-supervised framework that only uses a small set of fully supervised images (having semantic segmentation labels and box labels) and a set of images with only object bounding box labels (we call it the weak set). Our framework trains the primary segmentation model with the aid of an ancillary model that generates initial segmentation labels for the weak set and a self-correction module that improves the generated labels during training using the increasingly accurate primary model. We introduce two variants of the self-correction module using either linear or convolutional functions. Experiments on the PASCAL VOC 2012 and Cityscape datasets show that our models trained with a small fully supervised set perform similar to, or better than, models trained with a large fully supervised set while requiring ~7x less annotation effort.

## 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/1811.07073>)

[PDF](<https://arxiv.org/pdf/1811.07073.pdf>)