Abstract
A key human ability is to decompose a scene into distinct objects and use their relationships to understand the environment. Object-centric learning aims to mimic this process in an unsupervised manner. Recently, the slot attention-based framework has emerged as a leading approach in this area and has been widely used in various downstream tasks. However, existing slot attention methods face two key limitations: (1) a lack of high-level semantic information. In current methods, image areas are assigned to slots based on low-level features such as color and texture. This makes the model overly sensitive to low-level features and limits its understanding of object contours, shapes, or other semantic characteristics. (2) The inability to fine-tune the encoder. Current methods require a stable feature space throughout training to enable reconstruction from slots, which restricts the flexibility needed for effective object-centric learning. To address these limitations, we propose a novel ContextFusion stage and a Bootstrap Branch, both of which can be seamlessly integrated into existing slot attention models. In the ContextFusion stage, we exploit semantic information from the foreground and background, incorporating an auxiliary indicator that provides additional contextual cues about them to enrich the semantic content beyond low-level features. In the Bootstrap Branch, we decouple feature adaptation from the original reconstruction phase and introduce a bootstrap strategy to train a feature-adaptive mechanism, allowing for more flexible adaptation. Experimental results show that our method significantly improves the performance of different SOTA slot attention models on both simulated and real-world datasets.
Abstract (translated)
人类的一个关键能力是能够将场景分解为不同的对象，并利用这些对象之间的关系来理解环境。基于此，对象中心学习（Object-centric Learning）旨在以无监督的方式模仿这一过程，在该领域中，基于槽位注意力的框架已成为一种领先的方法，并且广泛应用于各种下游任务中。然而，现有的槽位注意方法面临着两个主要限制：(1) 缺乏高层次语义信息。在当前的方法中，图像区域是根据颜色和纹理等低级特征分配给槽位的。这使得模型对低级特征过于敏感，并限制了其理解对象轮廓、形状或其他语义特性。(2) 无法微调编码器。目前的方法在整个训练过程中需要一个稳定的特征空间以实现从槽位进行重构，从而限制了有效对象中心学习所需的灵活性。 为了克服这些局限性，我们提出了一种新颖的ContextFusion阶段和Bootstrap分支，这两者都可以无缝集成到现有的槽位注意力模型中。在ContextFusion阶段中，我们利用前景和背景中的语义信息，并引入了一个辅助指示器来提供关于它们的额外上下文线索，从而超越低级特征丰富语义内容。在Bootstrap分支中，我们将特征适应与原始重构阶段解耦，并引入了一种引导策略以训练一种可自适应机制，从而允许更加灵活的适应性调整。 实验结果显示，我们的方法显著提高了不同最先进的（SOTA）槽位注意模型在模拟和现实世界数据集上的性能。
URL
https://arxiv.org/abs/2509.02032
