Summary of Data-centric Machine Learning For Earth Observation: Necessary and Sufficient Features, by Hiba Najjar et al.
Data-Centric Machine Learning for Earth Observation: Necessary and Sufficient Features
by Hiba Najjar, Marlon Nuske, Andreas Dengel
First submitted to arxiv on: 21 Aug 2024
Categories
- Main: Machine Learning (cs.LG)
- 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 The paper contributes to the advancement of machine learning models by focusing on a data-centric perspective. It leverages model explanation methods to identify crucial features for optimal performance and the smallest set required to achieve it. The approach is evaluated on three temporal multimodal geospatial datasets, comparing multiple model explanation techniques. Results show that some datasets can reach optimal accuracy with less than 20% of instances, while others require a single band from a single modality. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper helps improve machine learning models by looking at the data instead of just the architecture. It uses special methods to figure out which parts of the data are most important for the model to work well. The approach is tested on three different datasets that combine time and location information in multiple forms. The results show that some datasets can achieve their best performance with less than 20% of the available data, while others need only a single piece of information. |
Keywords
» Artificial intelligence » Machine learning
