Summary of Generalized Few-shot Meets Remote Sensing: Discovering Novel Classes in Land Cover Mapping Via Hybrid Semantic Segmentation Framework, by Zhuohong Li et al.
Generalized Few-Shot Meets Remote Sensing: Discovering Novel Classes in Land Cover Mapping via Hybrid Semantic Segmentation Framework
by Zhuohong Li, Fangxiao Lu, Jiaqi Zou, Lei Hu, Hongyan Zhang
First submitted to arxiv on: 19 Apr 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); 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 proposes a generalized few-shot segmentation-based framework, called SegLand, to rapidly update land-cover maps in response to changes in natural and human activities. The approach is designed to address the challenge of discovering newly appeared land-cover types in existing classification systems, which is hindered by complex land objects at various scales and insufficient labeled data over a wide geographic area. The framework consists of three parts: data pre-processing, hybrid segmentation structure, and ultimate fusion. The latter combines multiple base learners with a modified Projection onto Orthogonal Prototypes (POP) network to enhance base-class recognition and extract novel classes from limited label data. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The SegLand framework is designed for high-resolution land-cover mapping and has won first place in the OpenEarthMap Land Cover Mapping Few-Shot Challenge. The approach can automatically update novel land-cover classes with limited labeled data, making it a vital tool for rapidly updating land-cover maps in response to changes on the ground. |
Keywords
* Artificial intelligence * Classification * Few shot
