论文标题
大规模图像集中的无监督，多对象发现
Toward unsupervised, multi-object discovery in large-scale image collections
论文作者
论文摘要
本文解决了在没有任何监督的情况下发现图像集合中存在的对象的问题。我们以Vo等人的优化方法为基础。 （CVPR'19）有了几个关键的新颖性：（1）我们提出了一种基于显着性的区域建议算法，该算法与其他竞争方法相比，与地面真实对象的重叠明显更高。此过程利用现成的CNN具有在没有任何边界框信息的情况下进行分类任务培训的，但否则是无监督的。 （2）我们利用提议的固有层次结构作为对对象发现Vo等的方法的有效正规化器，从而提高了其性能，从而在几个标准的基准上都显着改善了艺术的状态。 （3）我们采用两阶段的策略，在使用整个图像集合之前，使用一组少量的图像选择有希望的建议，以发现其描绘的对象，使我们第一次（据我们所知）首次处理（据我们所知），在每个图像中发现了一个图像中的每个图像中的多个图像中，都有多达20,000张图像，并将其与现有的图像相比，并且第一个图像介绍了一个图像，并提高了一个图像，并提高了一个图像，并提高了一个图像的范围。
This paper addresses the problem of discovering the objects present in a collection of images without any supervision. We build on the optimization approach of Vo et al. (CVPR'19) with several key novelties: (1) We propose a novel saliency-based region proposal algorithm that achieves significantly higher overlap with ground-truth objects than other competitive methods. This procedure leverages off-the-shelf CNN features trained on classification tasks without any bounding box information, but is otherwise unsupervised. (2) We exploit the inherent hierarchical structure of proposals as an effective regularizer for the approach to object discovery of Vo et al., boosting its performance to significantly improve over the state of the art on several standard benchmarks. (3) We adopt a two-stage strategy to select promising proposals using small random sets of images before using the whole image collection to discover the objects it depicts, allowing us to tackle, for the first time (to the best of our knowledge), the discovery of multiple objects in each one of the pictures making up datasets with up to 20,000 images, an over five-fold increase compared to existing methods, and a first step toward true large-scale unsupervised image interpretation.
