Summary of A Review and Implementation Of Object Detection Models and Optimizations For Real-time Medical Mask Detection During the Covid-19 Pandemic, by Ioanna Gogou et al.
A Review and Implementation of Object Detection Models and Optimizations for Real-time Medical Mask Detection during the COVID-19 Pandemic
by Ioanna Gogou, Dimitrios Koutsomitropoulos
First submitted to arxiv on: 28 May 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI)
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 paper evaluates the performance of Convolutional Neural Network (CNN)-based object detection models, focusing on the speed-accuracy trade-off. The authors assess various fundamental models on the Common Objects in Context (COCO) dataset and analyze their memory consumption, computational cost, and storage requirements. They then select a highly efficient model, YOLOv5, to train on the Properly-Wearing Masked Faces Dataset (PWMFD), exploring the benefits of transfer learning, data augmentations, and Squeeze-and-Excitation attention mechanisms for real-time medical mask detection. The authors propose an optimized model based on YOLOv5s with transfer learning, achieving a speed increase of over two times compared to SE-YOLOv3 while maintaining mean Average Precision at 67%. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper looks at how well computers can recognize objects in pictures. It compares different ways that computer models work and tries to find the best balance between how fast they are and how accurate they are. The authors then use one of these models, YOLOv5, to try to better detect people wearing medical masks correctly or incorrectly. They add some special tricks to make it faster and more accurate. They think this could be useful during the COVID-19 pandemic. |
Keywords
» Artificial intelligence » Attention » Cnn » Mask » Mean average precision » Neural network » Object detection » Transfer learning
