用简单模块实现可微、高效的对象中心表示学习，适合持续学习场景。
Simplified priors for Object-Centric Learning
- 仅用卷积、最大池化和注意力层构建可微分的槽注意力机制。
- 在标准数据集上性能媲美或超越已有复杂方法，且无需迭代优化。
- 适合追求轻量、可扩展对象表示的学习系统开发者。
人类擅长从数据中抽象出可复用的概念，而当前持续学习系统缺乏此能力。对象中心学习通过无监督方式从数据中构建抽象表示（称为“槽”）来应对这一挑战。现有图像方法多过于复杂、不可微或难以扩展。本文提出一种概念简洁、完全可微、非迭代且可扩展的方法SAMP（Simplified Slot Attention with Max Pool Priors）。该方法仅使用卷积、最大池化层与注意力层即可实现：先用卷积神经网络编码输入图像，再通过交替的卷积与最大池化层生成专用子网络并提取原始槽；随后以这些原始槽作为查询，在编码图像上执行简化槽注意力。尽管结构简单，其在标准基准测试中表现竞争力甚至更优。
原文摘要 · Abstract (English)
Humans excel at abstracting data and constructing \emph{reusable} concepts, a capability lacking in current continual learning systems. The field of object-centric learning addresses this by developing abstract representations, or slots, from data without human supervision. Different methods have been proposed to tackle this task for images, whereas most are overly complex, non-differentiable, or poorly scalable. In this paper, we introduce a conceptually simple, fully-differentiable, non-iterative, and scalable method called SAMP Simplified Slot Attention with Max Pool Priors). It is implementable using only Convolution and MaxPool layers and an Attention layer. Our method encodes the input image with a Convolutional Neural Network and then uses a branch of alternating Convolution and MaxPool layers to create specialized sub-networks and extract primitive slots. These primitive slots are then used as queries for a Simplified Slot Attention over the encoded image. Despite its simplicity, our method is competitive or outperforms previous methods on standard benchmarks.
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。