# Semantic Segmentation Refinement by Monte Carlo Region Growing of High Confidence Detections

arXiv: https://arxiv.org/abs/1802.07789 · HTML: https://mlsanity.com/paper/1802.07789/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Feb 2018.

## Built on by (most cited first, 14 of 14)

- [Segment Anything in High Quality](https://mlsanity.com/paper/2306.01567/) (2023)
- [Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future](https://mlsanity.com/paper/2105.13137/) (2021)
- [Mining Contextual Information Beyond Image for Semantic Segmentation](https://mlsanity.com/paper/2108.11819/) (2021)
- [Label-Efficient Learning in Agriculture: A Comprehensive Review](https://mlsanity.com/paper/2305.14691/) (2023)
- [MCIBI++: Soft Mining Contextual Information Beyond Image for Semantic Segmentation](https://mlsanity.com/paper/2209.04471/) (2022)
- [PatchDCT: Patch Refinement for High Quality Instance Segmentation](https://mlsanity.com/paper/2302.02693/) (2023)
- [Think Before You Segment: High-Quality Reasoning Segmentation with GPT Chain of Thoughts](https://mlsanity.com/paper/2503.07503/) (2025)
- [PatchRefineNet: Improving Binary Segmentation by Incorporating Signals from Optimal Patch-wise Binarization](https://mlsanity.com/paper/2211.06560/) (2022)
- [Stable Segment Anything Model](https://mlsanity.com/paper/2311.15776/) (2023)
- [Self-supervised Learning for Panoptic Segmentation of Multiple Fruit Flower Species](https://mlsanity.com/paper/2209.04618/) (2022)
- [GeloVec: Higher Dimensional Geometric Smoothing for Coherent Visual Feature Extraction in Image Segmentation](https://mlsanity.com/paper/2505.01057/) (2025)
- [Uncertainty-Based Dynamic Graph Neighborhoods For Medical Segmentation](https://mlsanity.com/paper/2108.03117/) (2021)
- [Leveraging Adaptive Implicit Representation Mapping for Ultra High-Resolution Image Segmentation](https://mlsanity.com/paper/2407.21256/) (2024)
- [AgRegNet: A Deep Regression Network for Flower and Fruit Density Estimation, Localization, and Counting in Orchards](https://mlsanity.com/paper/2409.17400/) (2024)

## Abstract (arXiv)

Despite recent improvements using fully convolutional networks, in general, the segmentation produced by most state-of-the-art semantic segmentation methods does not show satisfactory adherence to the object boundaries. We propose a method to refine the segmentation results generated by such deep learning models. Our method takes as input the confidence scores generated by a pixel-dense segmentation network and re-labels pixels with low confidence levels. The re-labeling approach employs a region growing mechanism that aggregates these pixels to neighboring areas with high confidence scores and similar appearance. In order to correct the labels of pixels that were incorrectly classified with high confidence level by the semantic segmentation algorithm, we generate multiple region growing steps through a Monte Carlo sampling of the seeds of the regions. Our method improves the accuracy of a state-of-the-art fully convolutional semantic segmentation approach on the publicly available COCO and PASCAL datasets, and it shows significantly better results on selected sequences of the finely-annotated DAVIS dataset.