MARCO：探索语义对应的未知空间
MARCO: Navigating the Unseen Space of Semantic Correspondence
用自蒸馏把稀疏关键点监督扩展成密集语义一致的对应，配合粗到细目标提升细粒度定位，为做稠密匹配/关键点迁移的视觉工作提供了一个可替换扩散骨干的轻量 DINOv2 训练框架。
原文依据 a self-distillation framework, which expands sparse supervision beyond annotated regions
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近期语义对应领域的进展依赖于双编码器架构，将 DINOv2 与扩散骨干网络相结合。这类方法虽然准确，但这些十亿参数级模型在训练关键点之外的泛化能力较差，暴露出基准性能与真实可用性之间的差距——在真实场景中，查询点很少与训练时见过的点相同。我们在 DINOv2 的基础上提出 MARCO，一个由新颖训练框架驱动的统一通用对应模型，同时增强细粒度定位与语义泛化能力。通过将提升空间精度的由粗到细目标与自蒸馏框架相结合——后者将稀疏监督扩展到标注区域之外——我们的方法把少量关键点转化为稠密且语义一致的对应。MARCO 在 SPair-71k、AP-10K 和 PF-PASCAL 上取得新的最优结果，且增益在细粒度定位阈值上进一步放大（+8.9 PCK@0.01），对未见关键点（+5.1，SPair-U）与未见类别（+4.7，MP-100）的泛化最强，同时比基于扩散的方法小 3 倍、快 10 倍。
英文原文摘要 1131 字符
Recent advances in semantic correspondence rely on dual-encoder architectures, combining DINOv2 with diffusion backbones. While accurate, these billion-parameter models generalize poorly beyond training keypoints, revealing a gap between benchmark performance and real-world usability, where queried points rarely match those seen during training. Building upon DINOv2, we introduce MARCO, a unified model for generalizable correspondence driven by a novel training framework that enhances both fine-grained localization and semantic generalization. By coupling a coarse-to-fine objective that refines spatial precision with a self-distillation framework, which expands sparse supervision beyond annotated regions, our approach transforms a handful of keypoints into dense, semantically coherent correspondences. MARCO sets a new state of the art on SPair-71k, AP-10K, and PF-PASCAL, with gains that amplify at fine-grained localization thresholds (+8.9 PCK@0.01), strongest generalization to unseen keypoints (+5.1, SPair-U) and categories (+4.7, MP-100), while remaining 3x smaller and 10x faster than diffusion-based approaches.