论文标题
通过虚拟类别学习的半监督对象检测
Semi-supervised Object Detection via Virtual Category Learning
论文作者
论文摘要
由于在现实世界应用程序中标记的数据的昂贵性，以伪标签为基础的半监督对象探测器具有吸引力。但是，处理令人困惑的样本并非繁琐：放弃有价值的混乱样本会损害模型的概括，同时将其用于训练会加剧由于不可避免的错误标志性而引起的确认偏见问题。为了解决这个问题，本文提议在没有标签校正的情况下主动使用令人困惑的样品。具体而言，将虚拟类别（VC）分配给每个混乱的样本，以便即使没有具体标签，它们也可以安全地为模型优化做出贡献。它归因于将训练样本与虚拟类别之间的嵌入距离指定为类间距离的下限。此外，我们还修改了本地化损失，以允许位置回归的高质量边界。广泛的实验表明，所提出的VC学习显着超过了最新的实验，尤其是在少量可用标签的情况下。
Due to the costliness of labelled data in real-world applications, semi-supervised object detectors, underpinned by pseudo labelling, are appealing. However, handling confusing samples is nontrivial: discarding valuable confusing samples would compromise the model generalisation while using them for training would exacerbate the confirmation bias issue caused by inevitable mislabelling. To solve this problem, this paper proposes to use confusing samples proactively without label correction. Specifically, a virtual category (VC) is assigned to each confusing sample such that they can safely contribute to the model optimisation even without a concrete label. It is attributed to specifying the embedding distance between the training sample and the virtual category as the lower bound of the inter-class distance. Moreover, we also modify the localisation loss to allow high-quality boundaries for location regression. Extensive experiments demonstrate that the proposed VC learning significantly surpasses the state-of-the-art, especially with small amounts of available labels.
