论文标题
使用分类器进行半监督对象检测来惩罚提案
Penalizing Proposals using Classifiers for Semi-Supervised Object Detection
论文作者
论文摘要
获取用于对象检测的黄金标准注释数据通常是昂贵的，涉及人类水平的努力。半监督对象检测算法通过少量的金标准标签和用于生成银标准标签的大型无标记数据集解决了问题。但是，在银标签上进行培训并不能产生良好的结果，因为它们是机器生成的注释。在这项工作中，我们设计了一个修改后的损耗功能，以训练由弱注释器产生的大型银标准注释集。我们包括与注释相关的置信度度量，作为损失函数中的附加术语，表示注释的质量。我们测试方法对各种测试集的有效性，并使用许多变体将结果与当前的某些对象检测方法进行比较。与未使用置信度度量的基线相比，我们通过使用拟议的置信度度量，使用25％标记的数据获得了4％的MAP增益，并使用50％标记的数据获得了MAP增益。
Obtaining gold standard annotated data for object detection is often costly, involving human-level effort. Semi-supervised object detection algorithms solve the problem with a small amount of gold-standard labels and a large unlabelled dataset used to generate silver-standard labels. But training on the silver standard labels does not produce good results, because they are machine-generated annotations. In this work, we design a modified loss function to train on large silver standard annotated sets generated by a weak annotator. We include a confidence metric associated with the annotation as an additional term in the loss function, signifying the quality of the annotation. We test the effectiveness of our approach on various test sets and use numerous variations to compare the results with some of the current approaches to object detection. In comparison with the baseline where no confidence metric is used, we achieved a 4% gain in mAP with 25% labeled data and 10% gain in mAP with 50% labeled data by using the proposed confidence metric.
