Summary of Interactive Explainable Anomaly Detection For Industrial Settings, by Daniel Gramelt et al.
Interactive Explainable Anomaly Detection for Industrial Settings
by Daniel Gramelt, Timon Höfer, Ute Schmid
First submitted to arxiv on: 1 Oct 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 In this paper, researchers focus on improving visual anomaly detection in industrial settings by developing a framework that enriches Convolutional Neural Networks (CNNs) with explanations and allows for user interaction to increase confidence in the model’s decisions. They present a CNN-based classification model and a model-agnostic explanation algorithm for black-box classifiers, demonstrating how these can be integrated into an interactive interface that facilitates human feedback. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The researchers aim to make industrial quality control more efficient by developing a system that not only detects defects but also explains its reasoning. This paper shows how NearCAIPI, a new interaction framework, can improve AI trustworthiness through user interaction and integration of human feedback into an interactive process chain. |
Keywords
» Artificial intelligence » Anomaly detection » Classification » Cnn
