# Semi-Supervised Semantic Segmentation With Region Relevance

arXiv: https://arxiv.org/abs/2304.11539 · HTML: https://mlsanity.com/paper/2304.11539/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 26 references that are in the map.
- First posted on arXiv 23 Apr 2023.

## Builds on (most cited first, 19 of 19)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [Temporal Ensembling for Semi-Supervised Learning](https://mlsanity.com/paper/1610.02242/) (2016)
- [Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision](https://mlsanity.com/paper/2106.01226/) (2021)
- [Semi-Supervised Semantic Segmentation with Cross-Consistency Training](https://mlsanity.com/paper/2003.09005/) (2020)
- [ST++: Make Self-training Work Better for Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2106.05095/) (2021)
- [Semi-Supervised Semantic Segmentation with High- and Low-level Consistency](https://mlsanity.com/paper/1908.05724/) (2019)
- [Guided Collaborative Training for Pixel-wise Semi-Supervised Learning](https://mlsanity.com/paper/2008.05258/) (2020)
- [Semi-supervised Semantic Segmentation with Directional Context-aware Consistency](https://mlsanity.com/paper/2106.14133/) (2021)
- [Non-Salient Region Object Mining for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2103.14581/) (2021)
- [Structured Consistency Loss for semi-supervised semantic segmentation](https://mlsanity.com/paper/2001.04647/) (2020)
- [Hierarchical Feature Alignment Network for Unsupervised Video Object Segmentation](https://mlsanity.com/paper/2207.08485/) (2022)
- [Exploiting Web Images for Dataset Construction: A Domain Robust Approach](https://mlsanity.com/paper/1611.07156/) (2016)
- [FECANet: Boosting Few-Shot Semantic Segmentation with Feature-Enhanced Context-Aware Network](https://mlsanity.com/paper/2301.08160/) (2023)
- [Saliency Guided Inter- and Intra-Class Relation Constraints for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2206.09554/) (2022)
- [Semantically Meaningful Class Prototype Learning for One-Shot Image Semantic Segmentation](https://mlsanity.com/paper/2102.10935/) (2021)
- [Towards Automatic Construction of Diverse, High-quality Image Dataset](https://mlsanity.com/paper/1708.06495/) (2017)

## Built on by (most cited first, 4 of 4)

- [Semi-Supervised Semantic Segmentation Based on Pseudo-Labels: A Survey](https://mlsanity.com/paper/2403.01909/) (2024)
- [RESMatch: Referring Expression Segmentation in a Semi-Supervised Manner](https://mlsanity.com/paper/2402.05589/) (2024)
- [Boundary-Refined Prototype Generation: A General End-to-End Paradigm for Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2307.10097/) (2023)
- [Source-Free Domain Adaptive Semantic Segmentation of Remote Sensing Images with Diffusion-Guided Label Enrichment](https://mlsanity.com/paper/2509.18502/) (2025)

## Abstract (arXiv)

Semi-supervised semantic segmentation aims to learn from a small amount of labeled data and plenty of unlabeled ones for the segmentation task. The most common approach is to generate pseudo-labels for unlabeled images to augment the training data. However, the noisy pseudo-labels will lead to cumulative classification errors and aggravate the local inconsistency in prediction. This paper proposes a Region Relevance Network (RRN) to alleviate the problem mentioned above. Specifically, we first introduce a local pseudo-label filtering module that leverages discriminator networks to assess the accuracy of the pseudo-label at the region level. A local selection loss is proposed to mitigate the negative impact of wrong pseudo-labels in consistency regularization training. In addition, we propose a dynamic region-loss correction module, which takes the merit of network diversity to further rate the reliability of pseudo-labels and correct the convergence direction of the segmentation network with a dynamic region loss. Extensive experiments are conducted on PASCAL VOC 2012 and Cityscapes datasets with varying amounts of labeled data, demonstrating that our proposed approach achieves state-of-the-art performance compared to current counterparts.