# Semi-Supervised Semantic Segmentation with High- and Low-level Consistency

## TL;DR

This paper introduces a semi-supervised semantic segmentation method that effectively leverages limited pixel-wise annotations and unlabeled images, achieving state-of-the-art results on multiple benchmarks.

## Contribution

It proposes a dual-branch network architecture that combines semi-supervised classification and segmentation, reducing artifacts and improving performance with few labels.

## Key findings

- Significant improvement over existing methods with limited labeled data.
- Achieves new state-of-the-art on PASCAL VOC 2012, PASCAL-Context, and Cityscapes.
- Effective use of unlabeled images enhances segmentation accuracy.

## Abstract

The ability to understand visual information from limited labeled data is an important aspect of machine learning. While image-level classification has been extensively studied in a semi-supervised setting, dense pixel-level classification with limited data has only drawn attention recently. In this work, we propose an approach for semi-supervised semantic segmentation that learns from limited pixel-wise annotated samples while exploiting additional annotation-free images. It uses two network branches that link semi-supervised classification with semi-supervised segmentation including self-training. The dual-branch approach reduces both the low-level and the high-level artifacts typical when training with few labels. The approach attains significant improvement over existing methods, especially when trained with very few labeled samples. On several standard benchmarks - PASCAL VOC 2012, PASCAL-Context, and Cityscapes - the approach achieves new state-of-the-art in semi-supervised learning.