发现扩散模型暗藏实例边界信息，可无监督提取清晰轮廓。
TRACE: Your Diffusion Model is Secretly an Instance Edge Detector
- 从自注意力图中定位物体边界首次出现点，用注意力差异提取边缘
- 推理速度提升81倍，实例分割准确率提高5.1个点（COCO）
- 无需人工标注即可实现高质量分割，适合无监督学习场景
高质量实例与全景分割传统依赖密集的实例级标注（如掩码、框或点），成本高且难扩展。无监督和弱监督方法虽减轻负担，但仍受限于语义主干网络和人为偏见，常导致输出合并或断裂。我们提出TRACE（TRAnsforming diffusion Cues to instance Edges），揭示文本到图像扩散模型实际上隐含实例边缘标注能力。通过识别自注意力图中物体边界首次出现的实例涌现点（IEP），利用注意力边界发散（ABDiv）提取边界，并蒸馏为轻量级单步边缘解码器。该设计无需每图进行扩散反演，实现81倍加速，同时生成更锐利、连续的边界。在COCO基准上，无监督实例分割性能提升+5.1 AP；在标签监督全景分割中，优于点监督基线+1.7 PQ，且未使用任何实例级标签。结果表明，扩散模型编码了隐藏的实例边界先验，解码这些信号为低成本标注提供了实用且可扩展的新路径。
原文摘要 · Abstract (English)
High-quality instance and panoptic segmentation has traditionally relied on dense instance-level annotations such as masks, boxes, or points, which are costly, inconsistent, and difficult to scale. Unsupervised and weakly-supervised approaches reduce this burden but remain constrained by semantic backbone constraints and human bias, often producing merged or fragmented outputs. We present TRACE (TRAnsforming diffusion Cues to instance Edges), showing that text-to-image diffusion models secretly function as instance edge annotators. TRACE identifies the Instance Emergence Point (IEP) where object boundaries first appear in self-attention maps, extracts boundaries through Attention Boundary Divergence (ABDiv), and distills them into a lightweight one-step edge decoder. This design removes the need for per-image diffusion inversion, achieving 81x faster inference while producing sharper and more connected boundaries. On the COCO benchmark, TRACE improves unsupervised instance segmentation by +5.1 AP, and in tag-supervised panoptic segmentation it outperforms point-supervised baselines by +1.7 PQ without using any instance-level labels. These results reveal that diffusion models encode hidden instance boundary priors, and that decoding these signals offers a practical and scalable alternative to costly manual annotation. Project Page: https://shjo-april.github.io/TRACE/
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。