用元学习让CNN学会跨任务判断图像是否相同
Convolutional Neural Networks Can (Meta-)Learn the Same-Different Relation
- 通过元学习训练CNN，提升其对相同/不同关系的抽象能力
- 在未见过的图像对上实现显著优于传统训练的泛化性能
- 适合研究视觉关系推理与模型泛化性的研究人员
尽管卷积神经网络（CNN）在许多任务中已达到甚至超越人类水平，但其优化目标通常局限于单个对象，如分类和描述。相比之下，人类在涉及视觉关系的任务中仍远超CNN，例如识别两个物体是否相同。已有研究发现，尽管可通过特定方法引导CNN学习相同-不同关系，但其泛化能力往往较差。本文表明，那些在常规训练下无法有效泛化相同-不同关系的CNN架构，在采用元学习训练时却能成功掌握该关系。元学习通过显式鼓励跨任务的抽象与泛化，使模型具备更强的适应性。
原文摘要 · Abstract (English)
While convolutional neural networks (CNNs) have come to match and exceed human performance in many settings, the tasks these models optimize for are largely constrained to the level of individual objects, such as classification and captioning. Humans remain vastly superior to CNNs in visual tasks involving relations, including the ability to identify two objects as `same' or `different'. A number of studies have shown that while CNNs can be coaxed into learning the same-different relation in some settings, they tend to generalize poorly to other instances of this relation. In this work we show that the same CNN architectures that fail to generalize the same-different relation with conventional training are able to succeed when trained via meta-learning, which explicitly encourages abstraction and generalization across tasks.
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。