基于部分与整体之间循环游走的对象中心学习
Object-centric Learning with Cyclic Walks between Parts and Whole
AI总结：
本文提出在视觉Transformer感知特征与槽绑定对象表示之间建立循环游走，利用部分-整体循环一致性作为监督信号训练槽注意力模块，在多个无监督任务中实现复杂场景的对象发现与分割，同时避免解码器重建带来的计算开销。
摘要：
从复杂自然环境中学习以对象为中心的表示，使人类和机器都具备从低级感知特征进行推理的能力。为了捕捉场景中的组合实体，我们提出了在从视觉Transformer提取的感知特征与对象实体之间进行循环游走的方法。首先，槽注意力模块与这些感知特征交互，并产生一组有限的槽表示。这些槽可以通过槽间注意力竞争绑定到场景中的任意对象实体。接下来，我们基于感知特征（即“部分”）与槽绑定的对象表示（即“整体”）之间的成对相似性，沿着高转移概率建立实体-特征对应关系，实现循环游走。整体大于部分之和，部分构成整体。部分-整体交互形成循环一致性，作为监督信号来训练槽注意力模块。我们在三个无监督任务中的七个图像数据集上进行了严格的实验，结果表明，使用我们的循环游走方法训练的网络能够在复杂场景中分离前景和背景、发现对象并分割语义对象。与附带解码器进行像素级或特征级重建的以对象为中心的模型相比，我们的循环游走提供了强学习信号，避免了计算开销并提高了内存效率。我们的源代码和数据可在以下链接获取：\href{https://github.com/ZhangLab-DeepNeuroCogLab/Parts-Whole-Object-Centric-Learning/}{link}。
英文摘要：
Learning object-centric representations from complex natural environments enables both humans and machines with reasoning abilities from low-level perceptual features. To capture compositional entities of the scene, we proposed cyclic walks between perceptual features extracted from vision transformers and object entities. First, a slot-attention module interfaces with these perceptual features and produces a finite set of slot representations. These slots can bind to any object entities in the scene via inter-slot competitions for attention. Next, we establish entity-feature correspondence with cyclic walks along high transition probability based on the pairwise similarity between perceptual features (aka "parts") and slot-binded object representations (aka "whole"). The whole is greater than its parts and the parts constitute the whole. The part-whole interactions form cycle consistencies, as supervisory signals, to train the slot-attention module. Our rigorous experiments on \textit{seven} image datasets in \textit{three} \textit{unsupervised} tasks demonstrate that the networks trained with our cyclic walks can disentangle foregrounds and backgrounds, discover objects, and segment semantic objects in complex scenes. In contrast to object-centric models attached with a decoder for the pixel-level or feature-level reconstructions, our cyclic walks provide strong learning signals, avoiding computation overheads and enhancing memory efficiency. Our source code and data are available at: \href{https://github.com/ZhangLab-DeepNeuroCogLab/Parts-Whole-Object-Centric-Learning/}{link}.
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。
