Abstract
Few-shot classification consists of a training phase where a model is learned on a relatively large dataset and an adaptation phase where the learned model is adapted to previously-unseen tasks with limited labeled samples. In this paper, we empirically prove that the training algorithm and the adaptation algorithm can be completely disentangled, which allows algorithm analysis and design to be done individually for each phase. Our meta-analysis for each phase reveals several interesting insights that may help better understand key aspects of few-shot classification and connections with other fields such as visual representation learning and transfer learning. We hope the insights and research challenges revealed in this paper can inspire future work in related directions.
Abstract (translated)
单样本分类( Few-shot classification)包括一个训练阶段,在该阶段中,模型在一个相对较大的数据集上学习,并在一个适应阶段,该阶段中,适应学习模型以适应从未见过的任务,且标记样本有限。在本文中,我们Empirically证明,训练算法和适应算法可以完全分离,这使得每个阶段都可以单独进行算法分析和设计。我们对每个阶段的meta分析揭示了几个有趣的见解,这些见解可能有助于更好地理解单样本分类的关键方面,以及与视觉表示学习和转移学习等其他领域的联系。我们希望本文揭示的见解和研究挑战可以激励未来相关方向的工作。
URL
https://arxiv.org/abs/2301.12246
