无需标注，一次切割生成多物体掩码，实现强性能无监督实例分割。
Enhancing Object Discovery for Unsupervised Instance Segmentation and Object Detection
- 用单次归一化割裂生成粗略伪标签，不依赖聚类或后处理
- 在多个基准上超越现有最佳方法，零样本下达到领先性能
- 适合追求无监督目标检测与分割的科研与工程应用
我们提出 Cut-Once-and-LEaRn (COLER)，一种简单的无监督实例分割与目标检测方法。COLER 首先使用自研的 CutOnce 生成粗略伪标签，再让检测器从中学习。CutOnce 仅进行一次归一化割裂（NCut），不依赖任何聚类方法（如 K-Means），但可生成图像中多个物体的掩码。该工作为 NCut 算法在多物体分割中的应用开辟新方向。我们设计了若干新颖且简洁的模块，使 CutOnce 充分利用自监督模型的对象发现能力，同时摆脱对掩码后处理的依赖。训练过程中，COLER 不需为伪标签设计特殊损失函数，性能通过自训练进一步提升。COLER 是一种零样本无监督模型，在多个基准上优于此前最优方法。我们认为该方法有助于推动无监督目标定位领域的发展。代码已开源：https://github.com/Quantumcraft616/COLER。
原文摘要 · Abstract (English)
We propose Cut-Once-and-LEaRn (COLER), a simple approach for unsupervised instance segmentation and object detection. COLER first uses our developed CutOnce to generate coarse pseudo labels, then enables the detector to learn from these masks. CutOnce applies Normalized Cut (NCut) only once and does not rely on any clustering methods (e.g., K-Means), but it can generate multiple object masks in an image. Our work opens a new direction for NCut algorithm in multi-object segmentation. We have designed several novel yet simple modules that not only allow CutOnce to fully leverage the object discovery capabilities of self-supervised model, but also free it from reliance on mask post-processing. During training, COLER achieves strong performance without requiring specially designed loss functions for pseudo labels, and its performance is further improved through self-training. COLER is a zero-shot unsupervised model that outperforms previous state-of-the-art methods on multiple benchmarks. We believe our method can help advance the field of unsupervised object localization. Code is available at: https://github.com/Quantumcraft616/COLER.
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。