Summary of Vertical Federated Image Segmentation, by Paul K. Mandal et al.
Vertical Federated Image Segmentation
by Paul K. Mandal, Cole Leo
First submitted to arxiv on: 15 Jan 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); Distributed, Parallel, and Cluster Computing (cs.DC); Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary A novel vertical federated learning (VFL) model is proposed for image segmentation tasks, addressing concerns around data privacy and acquisition. In this setting, multiple decentralized data sources lack labelled ground truth, making it challenging to develop accurate models. To overcome these limitations, the authors introduce a VFL architecture that enables private sharing of weights between federates and a central server. This system utilizes an FCN model capable of operating on unlabelled data and maintaining nominal accuracy. The proposed approach is evaluated on the CamVid dataset, examining the impact of feature compression and overall performance metrics under these constraints. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Imagine you’re trying to develop artificial intelligence solutions for image-based problems, but you can’t access all the necessary data because it’s stored in different places. This makes it hard to create accurate models. Some of these data sources don’t even have labels, making it difficult to assign classifications. Researchers propose a new way to tackle this issue using vertical federated learning (VFL). This approach allows private sharing of information between different data sources and a central server, enabling image segmentation tasks while maintaining accuracy. |
Keywords
* Artificial intelligence * Federated learning * Image segmentation
