提出基于视角的少样本学习，让模型自适应选择比较角度。
Aspect-Based Few-Shot Learning
- 用查询和支撑集动态生成上下文视角，替代固定类别标签
- 在几何形状与精灵数据集上实现新视角下的少样本分类
- 适合需要灵活理解任务语境的少样本场景
我们通过引入‘视角’概念，拓展了少样本学习的传统范式。传统方法假设每个数据点由单一‘真实’标签定义，用于查询与支撑集对象的对比。但人类专家在无预设标签时，会以支撑集其他数据为上下文，决定比较的抽象层次与视角。本文提出一种新架构与训练流程，能根据查询和支撑集生成上下文，并实现不依赖预设类别的视角感知少样本学习。我们在几何形状（Geometric Shapes）和精灵（Sprites）数据集上验证了该方法的有效性，结果表明其相比传统少样本学习更具可行性。
原文摘要 · Abstract (English)
We generalize the formulation of few-shot learning by introducing the concept of an aspect. In the traditional formulation of few-shot learning, there is an underlying assumption that a single "true" label defines the content of each data point. This label serves as a basis for the comparison between the query object and the objects in the support set. However, when a human expert is asked to execute the same task without a predefined set of labels, they typically consider the rest of the data points in the support set as context. This context specifies the level of abstraction and the aspect from which the comparison can be made. In this work, we introduce a novel architecture and training procedure that develops a context given the query and support set and implements aspect-based few-shot learning that is not limited to a predetermined set of classes. We demonstrate that our method is capable of forming and using an aspect for few-shot learning on the Geometric Shapes and Sprites dataset. The results validate the feasibility of our approach compared to traditional few-shot learning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。