无需标注，精准分割复杂真实图像中的多个物体
unMORE: Unsupervised Multi-Object Segmentation via Center-Boundary Reasoning
- 分两阶段学习物体中心与边界特征，构建多层次物体先验
- 在6个真实数据集上超越现有方法，尤其在密集场景表现卓越
- 完全无网络推理模块，适合无标签数据的多物体分割任务
我们研究单张图像上无监督多物体分割这一挑战性问题。现有方法依赖图像重建目标学习物体性或使用预训练图像特征进行像素聚类，通常仅能分割简单合成物体或发现有限数量的真实物体。本文提出unMORE，一种新型两阶段流程，旨在识别真实图像中大量复杂物体。其关键在于第一阶段显式学习三种精心定义的物体中心表示；第二阶段通过无网络的多物体推理模块，利用这些学习到的物体先验发现多个物体。该推理模块完全无需人工标注。大量实验表明，unMORE在6个真实世界基准数据集（包括具有挑战性的COCO数据集）上显著优于所有现有无监督方法，达到当前最优的物体分割性能。特别地，本方法在拥挤图像中表现优异，而所有基线方法均失效。
原文摘要 · Abstract (English)
We study the challenging problem of unsupervised multi-object segmentation on single images. Existing methods, which rely on image reconstruction objectives to learn objectness or leverage pretrained image features to group similar pixels, often succeed only in segmenting simple synthetic objects or discovering a limited number of real-world objects. In this paper, we introduce unMORE, a novel two-stage pipeline designed to identify many complex objects in real-world images. The key to our approach involves explicitly learning three levels of carefully defined object-centric representations in the first stage. Subsequently, our multi-object reasoning module utilizes these learned object priors to discover multiple objects in the second stage. Notably, this reasoning module is entirely network-free and does not require human labels. Extensive experiments demonstrate that unMORE significantly outperforms all existing unsupervised methods across 6 real-world benchmark datasets, including the challenging COCO dataset, achieving state-of-the-art object segmentation results. Remarkably, our method excels in crowded images where all baselines collapse.
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。