Hierarchical Cellular Automata for Visual Saliency

• Published in: International journal of computer vision Vol. 126; no. 7; pp. 751 - 770
• Main Authors: Qin, Yao, Feng, Mengyang, Lu, Huchuan, Cottrell, Garrison W.
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.07.2018; Springer; Springer Nature B.V
• Subjects: Algorithms; Analysis; Artificial Intelligence; Artificial neural networks; Bayesian analysis; Cellular automata; Computer Imaging; Computer Science; Computer vision; Correlation analysis; Feature extraction; Image detection; Image Processing and Computer Vision; Machine learning; Object recognition; Pattern Recognition; Pattern Recognition and Graphics; Propagation; Robots; Salience; State of the art; Vision; Deep contrast features; Hierarchical Cellular Automata; Bayesian framework; Saliency detection
• ISSN: 0920-5691; 1573-1405
• DOI: 10.1007/s11263-017-1062-2

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.