论文标题
用余弦诊断和补救射击灵敏度几乎没有学习者
Diagnosing and Remedying Shot Sensitivity with Cosine Few-Shot Learners
论文作者
论文摘要
很少的识别涉及训练图像分类器，以使用几个示例（Shot）在测试时间区分新颖概念。现有方法通常假定测试时间的射击号已提前知道。这是不现实的，当火车和测试射击不匹配时，流行和基础方法的性能已被证明会受到影响。我们对该现象进行了系统的经验研究。与先前的工作一致，我们发现射击灵敏度在基于公制的几个学习者中广泛存在，但是与先前的工作相反，较大的神经体系结构为变化的测试拍摄提供了一定程度的内置鲁棒性。更重要的是，通过消除对样品噪声的敏感性，一种基于余弦距离的简单，以前已知但非常忽略了一类方法，可以极大地提高对射击变化的鲁棒性。我们为流行和最近的几个弹药分类器提供了余弦替代品，从而扩大了它们对现实环境的适用性。这些余弦模型一致地提高了射击力，超越先前的射击状态，并在一系列基准和架构上提供了竞争精度，包括在非常低的射击方案中取得的显着增长。
Few-shot recognition involves training an image classifier to distinguish novel concepts at test time using few examples (shot). Existing approaches generally assume that the shot number at test time is known in advance. This is not realistic, and the performance of a popular and foundational method has been shown to suffer when train and test shots do not match. We conduct a systematic empirical study of this phenomenon. In line with prior work, we find that shot sensitivity is broadly present across metric-based few-shot learners, but in contrast to prior work, larger neural architectures provide a degree of built-in robustness to varying test shot. More importantly, a simple, previously known but greatly overlooked class of approaches based on cosine distance consistently and greatly improves robustness to shot variation, by removing sensitivity to sample noise. We derive cosine alternatives to popular and recent few-shot classifiers, broadening their applicability to realistic settings. These cosine models consistently improve shot-robustness, outperform prior shot-robust state of the art, and provide competitive accuracy on a range of benchmarks and architectures, including notable gains in the very-low-shot regime.
