Multitask image clustering approaches intend to improve the model accuracy on each task by exploring the relationships of multiple related image clustering tasks. However, most existing multitask clustering (MTC) approaches isolate the representation abstraction from the downstream clustering procedure, which makes the MTC models unable to perform unified optimization. In addition, the existing MTC relies on exploring the relevant information of multiple related tasks to discover their latent correlations while ignoring the irrelevant information between partially related tasks, which may also degrade the clustering performance. To tackle these issues, a multitask image clustering method named deep multitask information bottleneck (DMTIB) is devised, which aims at conducting multiple related image clustering by maximizing the relevant information of multiple tasks while minimizing the irrelevant information among them. Specifically, DMTIB consists of a main-net and multiple subnets to characterize the relationships across tasks and the correlations hidden in a single clustering task. Then, an information maximin discriminator is devised to maximize the mutual information (MI) measurement of positive samples and minimize the MI of negative ones, in which the positive and negative sample pairs are constructed by a high-confidence pseudo-graph. Finally, a unified loss function is devised for the optimization of task relatedness discovery and MTC simultaneously. Empirical comparisons on several benchmark datasets, NUS-WIDE, Pascal VOC, Caltech-256, CIFAR-100, and COCO, show that our DMTIB approach outperforms more than 20 single-task clustering and MTC approaches.

中文翻译：

---

通过深度信息瓶颈的多任务图像聚类


多任务图像聚类方法旨在通过探索多个相关图像聚类任务的关系来提高每个任务的模型准确性。然而，大多数现有的多任务聚类（MTC）方法将表示抽象与下游聚类过程隔离，这使得MTC模型无法进行统一优化。此外，现有的MTC依赖于探索多个相关任务的相关信息来发现它们的潜在相关性，而忽略了部分相关任务之间的不相关信息，这也可能降低聚类性能。为了解决这些问题，提出了一种名为深度多任务信息瓶颈（DMTIB）的多任务图像聚类方法，其目的是通过最大化多个任务的相关信息同时最小化它们之间的不相关信息来进行多个相关图像聚类。具体来说，DMTIB 由一个主网和多个子网组成，用于表征任务之间的关系以及隐藏在单个聚类任务中的相关性。然后，设计了信息最大最小判别器，以最大化正样本的互信息（MI）测量并最小化负样本的互信息，其中正负样本对由高置信度伪图构造。最后，设计了一个统一的损失函数来同时优化任务相关性发现和 MTC。对几个基准数据集（NUS-WIDE、Pascal VOC、Caltech-256、CIFAR-100 和 COCO）的实证比较表明，我们的 DMTIB 方法优于 20 多种单任务聚类和 MTC 方法。