Learning robust representations that allow to reliably establish relations between images is of paramount importance for virtually all of computer vision. Annotating the quadratic number of pairwise relations between training images is simply not feasible, while unsupervised inference is prone to noise, thus leaving the vast majority of these relations to be unreliable. To nevertheless find those relations which can be reliably utilized for learning, we follow a divide-and-conquer strategy: We find reliable similarities by extracting compact groups of images and reliable dissimilarities by partitioning these groups into subsets, converting the complicated overall problem into few reliable local subproblems. For each of the subsets we obtain a representation by learning a mapping to a target feature space so that their reliable relations are kept. Transitivity relations between the subsets are then exploited to consolidate the local solutions into a concerted global representation. While iterating between grouping, partitioning, and learning, we can successively use more and more reliable relations which, in turn, improves our image representation. In experiments, our approach shows state-of-the-art performance on unsupervised classification on ImageNet with 46.0% and competes favorably on different transfer learning tasks on PASCAL VOC.

中文翻译：

---

通过发现可靠的图像关系进行无监督表示学习

学习允许可靠地建立图像之间关系的鲁棒表示对于几乎所有计算机视觉都至关重要。注释训练图像之间成对关系的二次数根本不可行，而无监督推理容易产生噪声，从而使这些关系中的绝大多数不可靠。尽管如此，为了找到那些可以可靠地用于学习的关系，我们遵循分而治之的策略：我们通过提取紧凑的图像组来找到可靠的相似性，通过将这些组划分为子集来找到可靠的不同点，将复杂的整体问题转化为少数可靠的局部子问题。对于每个子集，我们通过学习到目标特征空间的映射来获得一个表示，以便保持它们的可靠关系。然后利用子集之间的传递关系将局部解决方案合并为协调一致的全局表示。在分组、分区和学习之间进行迭代时，我们可以连续使用越来越可靠的关系，从而改进我们的图像表示。在实验中，我们的方法在 ImageNet 上以 46.0% 的无监督分类显示了最先进的性能，并且在 PASCAL VOC 上的不同迁移学习任务上表现出色。