论文标题
多次实例学习具有极端域移动的弱监督对象检测的深度特征
Multiple instance learning on deep features for weakly supervised object detection with extreme domain shifts
论文作者
论文摘要
在过去的几年中，仅使用图像级注释仅使用图像级注释的对象检测（WSOD）引起了人们的关注。尽管通常使用针对自然图像的域特异性解决方案来解决此类任务，但我们表明，在预训练的深度特征上应用的一种简单的多重实例方法可以在非光学数据集中产生出色的性能，可能包括新类。该方法不包括任何微调或跨域学习，因此有效，可能适用于任意数据集和类。我们研究了所提出的方法的几种口味，其中一些包括多层感知器和多面体分类器。尽管它很简单，但我们的方法在一系列可公开的数据集上显示了竞争成果，包括绘画（People-Art，Iconart），水彩画，剪贴画和漫画，并允许快速学习看不见的视觉类别。
Weakly supervised object detection (WSOD) using only image-level annotations has attracted a growing attention over the past few years. Whereas such task is typically addressed with a domain-specific solution focused on natural images, we show that a simple multiple instance approach applied on pre-trained deep features yields excellent performances on non-photographic datasets, possibly including new classes. The approach does not include any fine-tuning or cross-domain learning and is therefore efficient and possibly applicable to arbitrary datasets and classes. We investigate several flavors of the proposed approach, some including multi-layers perceptron and polyhedral classifiers. Despite its simplicity, our method shows competitive results on a range of publicly available datasets, including paintings (People-Art, IconArt), watercolors, cliparts and comics and allows to quickly learn unseen visual categories.
