Saliency detection, finding the most important parts of an image, has become increasingly popular in computer vision. In this paper, we introduce Hierarchical Cellular Automata (HCA)—a temporally evolving model to intelligently detect salient objects. HCA consists of two main components: Single-layer Cellular Automata (SCA) and Cuboid Cellular Automata (CCA). As an unsupervised propagation mechanism, Single-layer Cellular Automata can exploit the intrinsic relevance of similar regions through interactions with neighbors. Low-level image features as well as high-level semantic information extracted from deep neural networks are incorporated into the SCA to measure the correlation between different image patches. With these hierarchical deep features, an impact factor matrix and a coherence matrix are constructed to balance the influences on each cell’s next state. The saliency values of all cells are iteratively updated according to a well-defined update rule. Furthermore, we propose CCA to integrate multiple saliency maps generated by SCA at different scales in a Bayesian framework. Therefore, single-layer propagation and multi-scale integration are jointly modeled in our unified HCA. Surprisingly, we find that the SCA can improve all existing methods that we applied it to, resulting in a similar precision level regardless of the original results. The CCA can act as an efficient pixel-wise aggregation algorithm that can integrate state-of-the-art methods, resulting in even better results. Extensive experiments on four challenging datasets demonstrate that the proposed algorithm outperforms state-of-the-art conventional methods and is competitive with deep learning based approaches.

中文翻译：

---

用于视觉显着性的分层元胞自动机

显着性检测，即找出图像中最重要的部分，在计算机视觉中变得越来越流行。在本文中，我们介绍了分层元胞自动机 (HCA)——一种用于智能检测显着对象的时间演化模型。HCA 由两个主要部分组成：单层元胞自动机 (SCA) 和长方体元胞自动机 (CCA)。作为一种无监督的传播机制，单层元胞自动机可以通过与邻居的交互来利用相似区域的内在相关性。从深度神经网络中提取的低级图像特征以及高级语义信息被合并到 SCA 中，以测量不同图像块之间的相关性。有了这些层次深度的特征，构建影响因子矩阵和相干矩阵来平衡对每个单元格下一状态的影响。根据明确定义的更新规则迭代更新所有单元格的显着值。此外，我们建议 CCA 在贝叶斯框架中集成由 SCA 在不同尺度上生成的多个显着图。因此，单层传播和多尺度集成在我们统一的 HCA 中联合建模。令人惊讶的是，我们发现 SCA 可以改进我们应用它的所有现有方法，无论原始结果如何，都可以达到相似的精度水平。CCA 可以作为一种高效的逐像素聚合算法，可以集成最先进的方法，从而产生更好的结果。