Summary of Towards Robust Ferrous Scrap Material Classification with Deep Learning and Conformal Prediction, by Paulo Henrique Dos Santos et al.
Towards Robust Ferrous Scrap Material Classification with Deep Learning and Conformal Prediction
by Paulo Henrique dos Santos, Valéria de Carvalho Santos, Eduardo José da Silva Luz
First submitted to arxiv on: 19 Apr 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: 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 The paper presents a novel approach to classifying ferrous scrap materials using conformal prediction, which quantifies uncertainty and enhances robustness. By integrating Split Conformal Prediction with state-of-the-art computer vision models like Vision Transformer (ViT), Swin Transformer, and ResNet-50, the authors demonstrate improved reliability and explainability of classification decisions. The method is evaluated on a comprehensive dataset of 8147 images spanning nine ferrous scrap classes, showing that the Swin Transformer model achieves an average classification accuracy exceeding 95%. Additionally, the Score-CAM method is effective in clarifying visual features, enhancing explainability. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper finds a way to better sort and recycle metal scraps. It uses special computer vision models like Vision Transformer (ViT), Swin Transformer, and ResNet-50 to recognize different types of scrap materials. The approach also includes techniques called conformal prediction and Explainable Artificial Intelligence (XAI) to make the results more trustworthy. The method is tested on a big dataset of over 8,000 images and shows that it can accurately identify different types of scrap materials with high accuracy. |
Keywords
» Artificial intelligence » Classification » Resnet » Transformer » Vision transformer » Vit
