Summary of Horizontal Federated Computer Vision, by Paul K. Mandal et al.
Horizontal Federated Computer Vision
by Paul K. Mandal, Cole Leo, Connor Hurley
First submitted to arxiv on: 31 Dec 2023
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 This research paper presents innovative solutions for object detection and recognition, as well as image segmentation, in the context of rapidly growing visual data. To tackle the challenge of decentralized data storage and privacy regulations, the authors propose federated implementations using Faster R-CNN (FRCNN) and Fully Convolutional Network (FCN). The FRCNN was trained on 5000 COCO2017 examples, while the FCN utilized the entire CamVid train set. This work addresses the increasing volume and decentralized nature of visual data, offering efficient solutions that comply with privacy regulations. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This research helps us deal with a huge amount of visual data being recorded everywhere! Imagine having all sorts of pictures and videos stored in different places, and needing to find specific things like objects or animals within those images. That’s what this paper is about: making it easier and faster to do that without breaking any rules or invading people’s privacy. The researchers came up with new ways to use special computer networks (Faster R-CNN and FCN) to help us find what we’re looking for in all these visual data. They tested their ideas on big datasets like COCO2017 and CamVid, and showed that it works! |
Keywords
* Artificial intelligence * Cnn * Convolutional network * Image segmentation * Object detection
