In recent years, few-shot remote sensing scene classification (FSRSSC) has attracted more and more attention. For FSRSSC, most methods currently focus on designing a meta-learning algorithm, which obtains meta-knowledge from limited samples and then applies it to novel tasks. In this work, on one hand, we optimize the training pipeline of the feature extractor; on the other hand, we apply a novel model fusion method further to optimize the feature extractor capability of the feature extractor. We show a novel FSRSSC baseline: learning two feature representations through using two self-supervised methods on the meta-training set and then fusing the two representations into one. Then, training a linear classifier on this representation achieves state-of-the-art performance. It shows that training a good feature extractor can be more efficient than complex meta-learning algorithms for FSRSSC. We believe that our results can inspire a rethinking of FSRSSC benchmarks.

中文翻译：

---

重新思考少镜头遥感场景分类：您只需要一个好的嵌入吗？

近年来，小样本遥感场景分类（FSRSSC）越来越受到关注。对于 FSRSSC，目前大多数方法都集中在设计一种元学习算法，该算法从有限的样本中获取元知识，然后将其应用于新任务。在这项工作中，一方面，我们优化了特征提取器的训练管道；另一方面，我们应用一种新的模型融合方法进一步优化特征提取器的特征提取器能力。我们展示了一种新颖的 FSRSSC 基线：通过在元训练集上使用两种自监督方法学习两种特征表示，然后将两种表示融合为一个。然后，在这个表示上训练一个线性分类器可以达到最先进的性能。它表明，训练一个好的特征提取器可以比 FSRSSC 的复杂元学习算法更有效。我们相信我们的结果可以激发对 FSRSSC 基准的重新思考。