# UCloudNet: A Residual U-Net with Deep Supervision for Cloud Image Segmentation

arXiv: https://arxiv.org/abs/2501.06440 · HTML: https://mlsanity.com/paper/2501.06440/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 30 references that are in the map.
- First posted on arXiv 11 Jan 2025.

## Builds on (most cited first, 15 of 15)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [MENTOR: Multi-level Self-supervised Learning for Multimodal Recommendation](https://mlsanity.com/paper/2402.19407/) (2024)
- [CloudSegNet: A Deep Network for Nychthemeron Cloud Image Segmentation](https://mlsanity.com/paper/1904.07979/) (2019)
- [Color-based Segmentation of Sky/Cloud Images From Ground-based Cameras](https://mlsanity.com/paper/1606.03669/) (2016)
- [Human-oriented Representation Learning for Robotic Manipulation](https://mlsanity.com/paper/2310.03023/) (2023)
- [Joint Pedestrian Trajectory Prediction through Posterior Sampling](https://mlsanity.com/paper/2404.00237/) (2024)
- [Systematic study of color spaces and components for the segmentation of sky/cloud images](https://mlsanity.com/paper/1701.04520/) (2017)
- [Nighttime sky/cloud image segmentation](https://mlsanity.com/paper/1705.10583/) (2017)
- [Multi-label Cloud Segmentation Using a Deep Network](https://mlsanity.com/paper/1903.06562/) (2019)
- [DMCNet: Diversified Model Combination Network for Understanding Engagement from Video Screengrabs](https://mlsanity.com/paper/2204.06454/) (2022)
- [AbHE: All Attention-based Homography Estimation](https://mlsanity.com/paper/2212.03029/) (2022)
- [Stereo Matching Based on Visual Sensitive Information](https://mlsanity.com/paper/2105.10831/) (2021)
- [Estimating Solar Irradiance Using Sky Imagers](https://mlsanity.com/paper/1910.04981/) (2019)
- [Design of low-cost, compact and weather-proof whole sky imagers for high-dynamic-range captures](https://mlsanity.com/paper/1704.05678/) (2017)
- [Graph-based Local Climate Classification in Iran](https://mlsanity.com/paper/2110.09209/) (2021)

## Built on by (most cited first, 5 of 5)

- [DDUNet: Dual Dynamic U-Net for Highly-Efficient Cloud Segmentation](https://mlsanity.com/paper/2501.15385/) (2025)
- [Image-to-Image Translation with Diffusion Transformers and CLIP-Based Image Conditioning](https://mlsanity.com/paper/2505.16001/) (2025)
- [CP2M: Clustered-Patch-Mixed Mosaic Augmentation for Aerial Image Segmentation](https://mlsanity.com/paper/2501.15389/) (2025)
- [TrafficKAN-GCN: Graph Convolutional-based Kolmogorov-Arnold Network for Traffic Flow Optimization](https://mlsanity.com/paper/2503.03276/) (2025)
- [Segregation and Context Aggregation Network for Real-time Cloud Segmentation](https://mlsanity.com/paper/2504.14178/) (2025)

## Abstract (arXiv)

Recent advancements in meteorology involve the use of ground-based sky cameras for cloud observation. Analyzing images from these cameras helps in calculating cloud coverage and understanding atmospheric phenomena. Traditionally, cloud image segmentation relied on conventional computer vision techniques. However, with the advent of deep learning, convolutional neural networks (CNNs) are increasingly applied for this purpose. Despite their effectiveness, CNNs often require many epochs to converge, posing challenges for real-time processing in sky camera systems. In this paper, we introduce a residual U-Net with deep supervision for cloud segmentation which provides better accuracy than previous approaches, and with less training consumption. By utilizing residual connection in encoders of UCloudNet, the feature extraction ability is further improved.