Visual salience is an intriguing phenomenon observed in biological neural systems. Numerous attempts have been made to model visual salience mathematically using various feature contrasts, either locally or globally. However, these algorithmic models tend to ignore the problem’s biological solutions, in which visual salience appears to arise during the propagation of visual stimuli along the visual cortex. In this paper, inspired by the conjecture that salience arises from deep propagation along the visual cortex, we present a Deep Salience model where a multi-layer model based on successive Markov random fields (sMRF) is proposed to analyze the input image successively through its deep belief propagation. As a result, the foreground object can be automatically separated from the background in a fully unsupervised way. Experimental evaluation on the benchmark dataset validated that our Deep Salience model can consistently outperform eleven state-of-the-art salience models, yielding the higher rates in the precision-recall tests and attaining the best F-measure and mean-square error in the experiments.
|Title of host publication||Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence|
|Publisher||The AAAI Press|
|Number of pages||7|
|Publication status||Published - Jul 2014|
|Event||The Twenty-Eighth AAAI Conference on Artificial Intelligence - Quebec City, Canada|
Duration: 27 Jul 2014 → 31 Jul 2014
|Conference||The Twenty-Eighth AAAI Conference on Artificial Intelligence|
|Period||27/07/2014 → 31/07/2014|
FingerprintDive into the research topics of 'Deep Salience: Visual Salience Modeling via Deep Belief Propagation'. Together they form a unique fingerprint.
- School of Electronics, Electrical Engineering and Computer Science - Visiting Scholar
- Speech, Image and Vision Systems