Generalized Few-Shot Semantic Segmentation in Remote Sensing: Challenge and Benchmark

TL;DR

This paper introduces a new generalized few-shot semantic segmentation benchmark for remote sensing, addressing the challenge of learning from limited data while maintaining performance on base classes, and provides a dataset and benchmark results.

Contribution

It is the first to propose a generalized few-shot segmentation benchmark in remote sensing, augmenting existing datasets and establishing a challenge with benchmark results.

Findings

Benchmark dataset released during CVPR 2024

Models evaluated on validation and test sets

Addresses the challenge of balancing novel and base class performance

Abstract

Learning with limited labelled data is a challenging problem in various applications, including remote sensing. Few-shot semantic segmentation is one approach that can encourage deep learning models to learn from few labelled examples for novel classes not seen during the training. The generalized few-shot segmentation setting has an additional challenge which encourages models not only to adapt to the novel classes but also to maintain strong performance on the training base classes. While previous datasets and benchmarks discussed the few-shot segmentation setting in remote sensing, we are the first to propose a generalized few-shot segmentation benchmark for remote sensing. The generalized setting is more realistic and challenging, which necessitates exploring it within the remote sensing context. We release the dataset augmenting OpenEarthMap with additional classes labelled for the generalized few-shot evaluation setting. The dataset is released during the OpenEarthMap land cover mapping generalized few-shot challenge in the L3D-IVU workshop in conjunction with CVPR 2024. In this work, we summarize the dataset and challenge details in addition to providing the benchmark results on the two phases of the challenge for the validation and test sets.