Summary of Semi-supervised Segmentation Of Land Cover Images Using Nonlinear Canonical Correlation Analysis with Multiple Features and T-sne, by Hong Wei et al.
Semi-supervised segmentation of land cover images using nonlinear canonical correlation analysis with multiple features and t-SNE
by Hong Wei, James Xiao, Yichao Zhang, Xia Hong
First submitted to arxiv on: 22 Jan 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 research proposes a novel semi-supervised approach to image segmentation, leveraging remote sensing data with multiple bands and textures to segment land cover subregions. By creating a high-dimensional feature space, the authors use t-SNE to project this data onto a 3D embedding. They then introduce RBF-CCA, a modified canonical correlation analysis algorithm that learns an associated projection matrix using only a small labelled dataset. The resulting canonical variables are applied using k-means clustering to achieve excellent segmentation results on remotely sensed multispectral images. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Imagine trying to sort different types of land cover into categories, like forests, fields, and buildings. This can be a big challenge because each pixel in an image might have slightly different features that help distinguish between these categories. To make this process easier, researchers developed a new way to segment images using remote sensing data. They started by creating a special feature space where they could analyze all the pixels together. Then, they used a technique called t-SNE to shrink this space down to just three dimensions. Next, they created a special algorithm that used some labeled examples to figure out how to group similar pixels together. Finally, they applied this algorithm to several different images and got great results! |
Keywords
» Artificial intelligence » Clustering » Embedding » Image segmentation » K means » Semi supervised
