Summary of Imbalance-aware Culvert-sewer Defect Segmentation Using An Enhanced Feature Pyramid Network, by Rasha Alshawi et al.
Imbalance-Aware Culvert-Sewer Defect Segmentation Using an Enhanced Feature Pyramid Network
by Rasha Alshawi, Md Meftahul Ferdaus, Mahdi Abdelguerfi, Kendall Niles, Ken Pathak, Steve Sloan
First submitted to arxiv on: 19 Aug 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 proposes an Enhanced Feature Pyramid Network (E-FPN) for semantic segmentation of culverts and sewer pipes within imbalanced datasets. The model incorporates architectural innovations to improve feature extraction and handle object variations. To address dataset imbalance, it employs strategies like class decomposition and data augmentation. Experimental results on the culvert-sewer defects dataset and a benchmark aerial semantic segmentation drone dataset show that the E-FPN outperforms state-of-the-art methods, achieving an average Intersection over Union (IoU) improvement of 13.8% and 27.2%, respectively. The proposed E-FPN presents a promising solution for enhancing object segmentation in challenging, multi-class real-world datasets. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about making computer models better at recognizing images when the pictures are unbalanced, meaning some classes have much more data than others. This is important because it helps machines learn to identify things like culverts and sewer pipes more accurately. The new model called E-FPN has special features that help it understand objects in different ways. It also uses tricks like adding fake data and breaking down classes into smaller groups to make the task easier. Tests show that E-FPN is better than other models at recognizing objects, with a big improvement of 13.8% on one test and 27.2% on another. This new model could be used for many real-world applications beyond just detecting culvert-sewer defects. |
Keywords
» Artificial intelligence » Data augmentation » Feature extraction » Feature pyramid » Semantic segmentation
