发表机构
CamCom Technologies Private Limited（卡姆康技术私人有限公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究无训练上下文分割问题，提出REBASE框架，通过识别参考图像低秩背景特征子空间并投影特征，结合相似性加权最远点采样等生成正点提示，在多个数据集上取得无训练方法新成果，有效提升一次性定位效果。
AI 中文摘要
无训练上下文分割能在推理时从单个带注释的参考图像引入新对象类别，消除类增量学习的再训练和内存开销。近期方法通过结合语义对应视觉基础模型与可提示分割网络实现，但受跨图像相似性映射质量限制。我们提出REBASE框架，明确抑制虚假上下文对应。该方法从参考图像识别低秩背景特征子空间，将参考和查询特征投影到其正交补，生成正点提示，在多个数据集上达无训练方法新水平，证明显式背景子空间去除对一次性定位有效。
英文摘要
Training-free in-context segmentation enables new object categories to be introduced at inference time from a single annotated reference image, eliminating the retraining and memory overhead of class-incremental learning. Recent approaches achieve this by combining vision foundation models for semantic correspondence with promptable segmentation networks like SAM. However, their performance is fundamentally limited by the quality of the cross-image similarity map; shared contextual backgrounds between the reference and query systematically elevate similarity in non-target regions, degrading prompt localization. We present REBASE, a training-free framework that explicitly suppresses these spurious contextual correspondences. Our method identifies the low-rank background feature subspace from the reference image and project the reference and query features onto its orthogonal complement in closed form, yielding cleaner semantic matching. We then generate positive point prompts using similarity-weighted farthest-point sampling, paired with a refined dense similarity prior. Without any training or parameter updates, our approach establishes a new state of the art among training-free methods on PACO-Part, FSS-1000, and cross-domain datasets such as ISIC2018, demonstrating that explicit background subspace removal is a highly effective principle for one-shot localization.
CommentsAccepted to ACCV 2026 (Oral presentation)
