arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2302.10624cs.CV
收藏

通过不一致协调的自改进目标检测

Self-improving object detection via disagreement reconciliation

Istituto Italiano di Tecnologia(意大利技术研究院);University of Genova(热那亚大学)

Gianluca Scarpellini, Stefano Rosa, Pietro Morerio, Lorenzo Natale, Alessio Del Bue

摘要:

当新的环境条件在训练数据中不能充分表示时,对象检测器经常经历性能下降。本文研究了如何在新环境中探索和获取图像时自动微调预先存在的对象检测器,而不依赖于人为干预,即,以自我监督的方式。在我们的设置中,代理最初使用预先训练的现成检测器来定位对象并关联伪标签来探索环境。通过假设同一对象的伪标签在不同的视图中必须是一致的,我们设计了一种新的机制,用于从观察结果之间的共识中产生精确的预测。我们的方法在mAP方面将现成的对象检测器提高了2.66%,并且在不依赖地面实况注释的情况下优于当前的最新技术水平。

英文摘要:

Object detectors often experience a drop in performance when new environmental conditions are insufficiently represented in the training data. This paper studies how to automatically fine-tune a pre-existing object detector while exploring and acquiring images in a new environment without relying on human intervention, i.e., in a self-supervised fashion. In our setting, an agent initially explores the environment using a pre-trained off-the-shelf detector to locate objects and associate pseudo-labels. By assuming that pseudo-labels for the same object must be consistent across different views, we devise a novel mechanism for producing refined predictions from the consensus among observations. Our approach improves the off-the-shelf object detector by 2.66% in terms of mAP and outperforms the current state of the art without relying on ground-truth annotations.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑