用紧凑性聚类机制实现无监督对象发现，自动生成高质量分割掩码。
Hierarchical Compact Clustering Attention (COCA) for Unsupervised Object-Centric Learning
- 基于紧凑性原理的注意力聚类模块，构建分层网络提取对象中心表征。
- 在六大数据集上优于或媲美现有模型，九项指标表现优异。
- 无需预设对象数量，能更好分割背景，适合无监督图像分割任务。
我们提出紧凑聚类注意力（COCA）层，一种有效的构建模块，通过分层策略实现对象中心表征学习，并解决单图上的无监督对象发现任务。当级联到自下而上的分层网络架构（即COCA-Net）时，COCA是一种基于注意力的聚类模块，能够从多对象场景中提取对象中心表征。其核心是利用物理紧凑性概念的新型聚类算法，突出场景中的独立对象质心，提供空间归纳偏置。得益于该策略，COCA-Net在解码器侧和编码器侧均生成高质量分割掩码。此外，COCA-Net不依赖预设的对象掩码数量，对背景元素的分割效果优于竞争对手。我们在六个广泛采用的数据集上展示了COCA-Net的分割性能，其在九个不同评估指标上达到优于或可比当前最优模型的结果。
原文摘要 · Abstract (English)
We propose the Compact Clustering Attention (COCA) layer, an effective building block that introduces a hierarchical strategy for object-centric representation learning, while solving the unsupervised object discovery task on single images. COCA is an attention-based clustering module capable of extracting object-centric representations from multi-object scenes, when cascaded into a bottom-up hierarchical network architecture, referred to as COCA-Net. At its core, COCA utilizes a novel clustering algorithm that leverages the physical concept of compactness, to highlight distinct object centroids in a scene, providing a spatial inductive bias. Thanks to this strategy, COCA-Net generates high-quality segmentation masks on both the decoder side and, notably, the encoder side of its pipeline. Additionally, COCA-Net is not bound by a predetermined number of object masks that it generates and handles the segmentation of background elements better than its competitors. We demonstrate COCA-Net's segmentation performance on six widely adopted datasets, achieving superior or competitive results against the state-of-the-art models across nine different evaluation metrics.
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。