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.
翻译:由于在现实应用中贴有标签的数据成本很高,以假贴标签为支撑的半监督对象探测器具有吸引力。然而,处理混杂样本是非技术性的:丢弃有价值的混杂样本会损害模型的概括性,而将其用于培训则会加剧不可避免的误贴造成的确认偏差问题。为了解决这个问题,本文件提议主动使用混淆的样本,而不更正标签。具体地说,为每个混杂样本指定了一个虚拟类别(VC),这样它们即使没有混凝土标签,也能安全地为模型优化做出贡献。这归因于将培训样本和虚拟类别之间的嵌入距离指定为较低等级间距离。此外,我们还修改了本地化损失,以便允许高质量的边界进行位置回归。广泛的实验表明,拟议的VC学习大大超过最新水平,特别是使用少量现有标签。