计算机科学
利用
查询扩展
图形
匹配(统计)
查询优化
萨尔盖博
集合(抽象数据类型)
邻接表
数据挖掘
查询语言
对象(语法)
特征(语言学)
目标检测
邻接矩阵
Web查询分类
布尔连接查询
在线聚合
理论计算机科学
班级(哲学)
情报检索
人工智能
Web搜索查询
期限(时间)
有向图
缩小
特征匹配
特征向量
知识库
模式识别(心理学)
按示例查询
特征提取
校准
作者
Wenxiao Fan,Jingling Fu,Luohang Liu,Lichen Ma,Yu He,Zhiyang Yu,Weishan Bi,Junshi Huang,Yan Li,Gu Simiu,Kan Li
标识
DOI:10.48550/arxiv.2609.26092
摘要
One-to-one (O2O) matching enables Detection Transformers (DETRs) to perform end-to-end set prediction by assigning each object to a single positive query. However, the strongest classification, center, scale, and overlap evidence for an object is often distributed across multiple queries. This mismatch leaves only the matched owner positively supervised for the object, while other evidence-bearing queries receive no box target for it. We term this query knowledge fragmentation. To exploit such complementary evidence without one-to-many supervision, we propose BS-O2G, a plug-in that builds a sparse prediction-aware graph from decoded features, boxes, and class distributions to organize query collaboration in feature and optimization spaces while preserving the original O2O matcher, positive labels, and objective. One-to-Graph (O2G) calibration propagates relative messages over this graph to consolidate query evidence in the forward pass, whereas Backward Sharing (BS) reuses its transposed detached adjacency to route gradients across persistent query basis vectors without changing the decoder input in the forward pass. Experiments across diverse DETR methods, backbones, COCO, and CrowdHuman show consistent gains and faster convergence with negligible parameter/FLOP growth and modest runtime overhead, supporting graph-based query collaboration as an alternative to expanding positive assignments.
科研通智能强力驱动
Strongly Powered by AbleSci AI