将持续小样本学习基准扩展至包含特定实例识别
Expanding continual few-shot learning benchmarks to include recognition of specific instances
AI总结：
本研究扩展持续小样本学习（CFSL）基准，将类别数量提升一个数量级并新增特定实例识别测试，实验发现带回放机制的模型变体可显著提升两类任务性能，尤其对实例测试效果突出。
摘要：
持续学习与小样本学习是机器学习（ML）向更广泛能力发展进程中的重要前沿方向。近年来，学界对二者的结合产生了浓厚兴趣，Antoniou等人提出的Continual few-shot Learning（CFSL，持续小样本学习）框架（arXiv:2004.11967）是最早的相关研究案例之一。\n本研究从两个方面扩展CFSL，以覆盖更广泛的挑战——这些挑战对真实场景下智能体的行为至关重要。第一，我们将类别数量提升了一个数量级，使实验结果更易与标准持续学习实验对标；第二，我们引入了“实例测试”，要求识别类别的特定实例，这是动物认知中的一项能力，但在机器学习研究中通常被忽略。\n为初步探索机器学习模型在上述条件下的性能，我们选取了原始CFSL研究中的代表性基线模型，并新增了一种带回放机制的模型变体。正如预期，学习更多类别比原始CFSL实验难度更高；有趣的是，图像实例与类别的呈现方式会影响分类性能。令人意外的是，基线模型在实例测试中的准确率与其他分类任务相当，但在存在严重遮挡和噪声的情况下表现不佳。采用回放机制进行巩固可大幅提升两类任务的性能，对实例测试的提升效果尤为显著。
英文摘要：
Continual learning and few-shot learning are important frontiers in progress toward broader Machine Learning (ML) capabilities. Recently, there has been intense interest in combining both. One of the first examples to do so was the Continual few-shot Learning (CFSL) framework of Antoniou et al. arXiv:2004.11967. In this study, we extend CFSL in two ways that capture a broader range of challenges, important for intelligent agent behaviour in real-world conditions. First, we increased the number of classes by an order of magnitude, making the results more comparable to standard continual learning experiments. Second, we introduced an 'instance test' which requires recognition of specific instances of classes -- a capability of animal cognition that is usually neglected in ML. For an initial exploration of ML model performance under these conditions, we selected representative baseline models from the original CFSL work and added a model variant with replay. As expected, learning more classes is more difficult than the original CFSL experiments, and interestingly, the way in which image instances and classes are presented affects classification performance. Surprisingly, accuracy in the baseline instance test is comparable to other classification tasks, but poor given significant occlusion and noise. The use of replay for consolidation substantially improves performance for both types of tasks, but particularly for the instance test.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
