发表机构
The University of Melbourne; Jimei University（墨尔本大学; 集美大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出生成式验证方法，用独立扩散模型重推导检测标签作为采集信号，统一处理分类与定位错误，在PASCAL VOC和MS-COCO上优于现有主动学习准则。
AI 中文摘要
几乎每一个用于主动目标检测的采集函数都共享一个安排，即被改进的模型同时也是被询问的模型。我们背离了这一安排。在生成式验证中，一个独立的生成模型从检测框内的像素重新推导出检测的标签，两者之间的不一致成为采集信号。两个性质源于该安排本身而非任何调参。一个偏移的框、一个位于背景上的框以及一个携带错误标签的正确框都会产生一个无法通过验证的裁剪区域，因此失败模式已经以单一标量形式组合在一起，现有准则中手工加权的分类和定位项不再需要。并且由于验证器从不观察检测器的置信度，高置信度的错误检测得分最高，尽管一个自推导信号将它们视为无趣，而它们正是未标注时代价最高的。我们将验证器构建为条件扩散模型，其扩散目标是标签表示而非图像。其逆过程是随机的，因此重复生成返回一个分布，其集中度报告证据在多大程度上确定了标签，而分类器则返回单一的点估计。在PASCAL VOC和MS-COCO上，该信号优于输出不确定性、特征几何、扰动和集成准则，在MS-COCO上每轮大约提升一个mAP50点，其最大优势出现在早期轮次，此时高置信度检测器错误最为常见。
英文摘要
Nearly every acquisition function for active object detection shares one arrangement, in that the model being improved is also the model being interrogated. We depart from it. In generative verification an independent generative model re-derives the label of a detection from the pixels inside its predicted box, and the disagreement between the two becomes the acquisition signal. Two properties follow from the arrangement itself rather than from any tuning. A displaced box, a box on background and a correct box carrying the wrong label all yield a crop that fails verification, so the failure modes arrive already combined in one scalar and the hand-weighted classification and localization terms of existing criteria are no longer needed. And because the verifier never observes the detector confidence, confidently wrong detections score highest, although a self-derived signal reads them as uninteresting and they are the costliest to leave unlabeled. We build the verifier as a conditional diffusion model whose diffusion target is a label representation rather than an image. Its reverse process is stochastic, so repeated generations return a distribution whose concentration reports how firmly the evidence determines the label, where a classifier returns a single point estimate. On PASCAL VOC and MS-COCO the signal outperforms output-uncertainty, feature-geometry, perturbation and ensemble criteria, gaining about one mAP50 point per round on MS-COCO, with its largest margins in the early rounds where confident detector errors are most common.
