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

arXiv: https://arxiv.org/abs/1811.07073 · HTML: https://mlsanity.com/paper/1811.07073/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Nov 2018.

## Built on by (most cited first, 30 of 37)

- [Extract Free Dense Labels from CLIP](https://mlsanity.com/paper/2112.01071/) (2021)
- [Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision](https://mlsanity.com/paper/2106.01226/) (2021)
- [A Survey on Deep Semi-supervised Learning](https://mlsanity.com/paper/2103.00550/) (2021)
- [Augmentation Matters: A Simple-yet-Effective Approach to Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2212.04976/) (2022)
- [Semi-Supervised and Unsupervised Deep Visual Learning: A Survey](https://mlsanity.com/paper/2208.11296/) (2022)
- [Enhancing Pseudo Label Quality for Semi-Supervised Domain-Generalized Medical Image Segmentation](https://mlsanity.com/paper/2201.08657/) (2022)
- [Every Annotation Counts: Multi-label Deep Supervision for Medical Image Segmentation](https://mlsanity.com/paper/2104.13243/) (2021)
- [Conflict-Based Cross-View Consistency for Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2303.01276/) (2023)
- [Semi-Supervised Semantic Segmentation via Gentle Teaching Assistant](https://mlsanity.com/paper/2301.07340/) (2023)
- [Unbiased Subclass Regularization for Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2203.10026/) (2022)
- [Instance-specific and Model-adaptive Supervision for Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2211.11335/) (2022)
- [Fuzzy Positive Learning for Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2210.08519/) (2022)
- [Learning from Pixel-Level Label Noise: A New Perspective for Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2103.14242/) (2021)
- [Transformer-CNN Cohort: Semi-supervised Semantic Segmentation by the Best of Both Students](https://mlsanity.com/paper/2209.02178/) (2022)
- [Conservative-Progressive Collaborative Learning for Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2211.16701/) (2022)
- [When CNN Meet with ViT: Towards Semi-Supervised Learning for Multi-Class Medical Image Semantic Segmentation](https://mlsanity.com/paper/2208.06449/) (2022)
- [Semi-Supervised Semantic Segmentation Based on Pseudo-Labels: A Survey](https://mlsanity.com/paper/2403.01909/) (2024)
- [Semi-Supervised Semantic Segmentation with Cross Teacher Training](https://mlsanity.com/paper/2209.01327/) (2022)
- [Label-efficient Hybrid-supervised Learning for Medical Image Segmentation](https://mlsanity.com/paper/2203.05956/) (2022)
- [Semi-Supervised Temporal Action Detection with Proposal-Free Masking](https://mlsanity.com/paper/2207.07059/) (2022)
- [Adversarial Dual-Student with Differentiable Spatial Warping for Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2203.02792/) (2022)
- [Semi-supervised Semantic Segmentation with Multi-Constraint Consistency Learning](https://mlsanity.com/paper/2503.17914/) (2025)
- [Weak-shot Semantic Segmentation by Transferring Semantic Affinity and Boundary](https://mlsanity.com/paper/2110.01519/) (2021)
- [EVIL: Evidential Inference Learning for Trustworthy Semi-supervised Medical Image Segmentation](https://mlsanity.com/paper/2307.08988/) (2023)
- [STEdge: Self-training Edge Detection with Multi-layer Teaching and Regularization](https://mlsanity.com/paper/2201.05121/) (2022)
- [Automatic segmentation of meniscus based on MAE self-supervision and point-line weak supervision paradigm](https://mlsanity.com/paper/2205.03525/) (2022)
- [Weakly Supervised Medical Image Segmentation With Soft Labels and Noise Robust Loss](https://mlsanity.com/paper/2209.08172/) (2022)
- [Training Semantic Segmentation on Heterogeneous Datasets](https://mlsanity.com/paper/2301.07634/) (2023)
- [MetaSeg: Content-Aware Meta-Net for Omni-Supervised Semantic Segmentation](https://mlsanity.com/paper/2401.11738/) (2024)
- [Weighting Pseudo-Labels via High-Activation Feature Index Similarity and Object Detection for Semi-Supervised Segmentation](https://mlsanity.com/paper/2407.12630/) (2024)

## Abstract (arXiv)

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.