# Label Refinement Network for Coarse-to-Fine Semantic Segmentation

arXiv: https://arxiv.org/abs/1703.00551 · HTML: https://mlsanity.com/paper/1703.00551/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Mar 2017.

## Built on by (most cited first, 11 of 11)

- [A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS](https://mlsanity.com/paper/2304.00501/) (2023)
- [High Quality Segmentation for Ultra High-resolution Images](https://mlsanity.com/paper/2111.14482/) (2021)
- [Position, Padding and Predictions: A Deeper Look at Position Information in CNNs](https://mlsanity.com/paper/2101.12322/) (2021)
- [Semantic Segmentation with Labeling Uncertainty and Class Imbalance](https://mlsanity.com/paper/2102.04566/) (2021)
- [HS3: Learning with Proper Task Complexity in Hierarchically Supervised Semantic Segmentation](https://mlsanity.com/paper/2111.02333/) (2021)
- [SegMix: Co-occurrence Driven Mixup for Semantic Segmentation and Adversarial Robustness](https://mlsanity.com/paper/2108.09929/) (2021)
- [Transmission-Guided Bayesian Generative Model for Smoke Segmentation](https://mlsanity.com/paper/2303.00900/) (2023)
- [Sequential Ensembling for Semantic Segmentation](https://mlsanity.com/paper/2210.05387/) (2022)
- [FoSp: Focus and Separation Network for Early Smoke Segmentation](https://mlsanity.com/paper/2306.04474/) (2023)
- [Simpler Does It: Generating Semantic Labels with Objectness Guidance](https://mlsanity.com/paper/2110.10335/) (2021)
- [Expediting Building Footprint Extraction from High-resolution Remote Sensing Images via progressive lenient supervision](https://mlsanity.com/paper/2307.12220/) (2023)

## Abstract (arXiv)

We consider the problem of semantic image segmentation using deep convolutional neural networks. We propose a novel network architecture called the label refinement network that predicts segmentation labels in a coarse-to-fine fashion at several resolutions. The segmentation labels at a coarse resolution are used together with convolutional features to obtain finer resolution segmentation labels. We define loss functions at several stages in the network to provide supervisions at different stages. Our experimental results on several standard datasets demonstrate that the proposed model provides an effective way of producing pixel-wise dense image labeling.