共享集合解码器中的局部增益与固定分配集合损失
Local Gains and Fixed-Assignment Set Losses in Shared Set Decoders
浏览论文内容
中文总结 AI 辅助
该研究针对两个ResNet-50 DETR系列检查点，分析查询-关系删除的局部增益与固定分配集合损失的权衡，发现不同模型的区间持续性存在差异，未识别出干预不变的边缘机制等。
中文摘要 AI 辅助
查询-关系删除可改进被编辑的槽位，同时降低包含该槽位的预测集合的效用。我们在两个相关的ResNet-50 DETR系列检查点中研究这种权衡，使用每个检查点来自710对图像-关系单元的记录、选择条件证据。主要比较是从选定的目标删除中减去匹配的主动对照，该对照在不同的记录接收方处删除相同的主导源，因此是复合对比而非相同接收方的安慰剂。在两个检查点中，目标减对照对比在局部为正，而固定分配为负。相反符号模式发生在302/710个DETR单元和460/710个DINO单元内。重新匹配后，相应的数量为285/710和433/710。重新匹配和原生选择吸收了足够的平均损失，使得DETR的区间穿过零，而DINO的区间仍为负，因此跨读数的持续性因检查点而异。硬删除与质量保留编辑之间的固定映射比较在重新匹配前也不同。该比较依赖于结果盲映射，未建立相同剂量的迁移。因此，局部干预的成功并不决定联合解码集合的后果。支持的结论是选择条件删除敏感性，其持续性取决于读数和干预算子。我们未识别出干预不变的边缘机制、检测器级别的退化、总体患病率或训练时正则化器的值。
英文摘要
A query-relation deletion can improve the edited slot while reducing the utility of the prediction set that contains it. We study this tension in two related ResNet-50 DETR-family checkpoints using recorded, selection-conditional evidence from 710 paired image-relation units per checkpoint. The primary comparison subtracts a matched active control, which deletes the same leader source at a different recorded recipient, from the selected target deletion. It is therefore a composite contrast rather than a same-recipient placebo. The target-minus-control contrast is locally positive and fixed-assignment negative in both checkpoints. The opposite-sign pattern occurs within 302/710 DETR units and 460/710 DINO units. After rematching, the corresponding counts are 285/710 and 433/710. Rematching and native selection absorb enough of the mean loss for DETR intervals to cross zero, whereas DINO intervals remain negative, so persistence across readouts differs by checkpoint. A fixed-map comparison between hard deletion and a mass-preserving edit also differs before rematching. That comparison is conditional on the outcome-blind map and does not establish same-dose transport. Local intervention success therefore does not determine the consequence for a jointly decoded set. The supported conclusion is selection-conditional deletion sensitivity whose persistence depends on the readout and intervention operator. We do not identify an intervention-invariant edge mechanism, detector-level degradation, population prevalence, or the value of a training-time regularizer.
发表机构
- School of Biomedical Engineering, ShanghaiTech University（上海科技大学生物医学工程学院）
- Wuhan United Imaging Surgical Co., Ltd.（武汉联影外科医疗有限公司）
机构由 AI 辅助整理，请以论文原文为准。
