Summary of Cross-modal Learning Of Housing Quality in Amsterdam, by Alex Levering et al.
Cross-Modal Learning of Housing Quality in Amsterdam
by Alex Levering, Diego Marcos, Devis Tuia
First submitted to arxiv on: 13 Mar 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 The proposed study evaluates various data sources and models for assessing housing quality in Amsterdam using both ground-level and aerial imagery. For ground-level images, the performance of Google StreetView (GSV) and Flickr images is compared. The results show that GSV achieves the most accurate building quality scores, outperforming aerial images by approximately 30%. However, it is found that combining Flickr image features with aerial image features using careful filtering and a suitable pre-trained model can reduce the performance gap to GSV features by half, from 30% to 15%. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The researchers test different data sources and models for recognizing housing quality in Amsterdam. They compare Google StreetView (GSV) images with Flickr images at ground level. The results show that GSV is better at predicting building quality, but they also find a way to make Flickr images work almost as well. This could be important because it’s harder to get GSV images and they’re not always available. |
