Salient object detection is a key step in many image analysis tasks as it not only identifies relevant parts of a visual scene but may also reduce computational complexity by filtering out irrelevant segments of the scene. This motivates the question of how to efficiently find salient regions and objects in images. In this dissertation, we propose two novel methods to automatically discover the salient regions and objects in the images.

First, we propose a method to find characteristic landmarks and recognize ancient Roman imperial coins using deep convolutional neural networks (CNNs). For this purpose, we train the CNNs on the coin recognition task and we formulate an optimization problem to discover class-specific salient coin regions using the trained CNNs. Analysis of discovered salient regions confirms that they are largely consistent with human expert annotations.

Next, we propose a salient object detection method that combines a shape prediction driven by a convolutional neural network with the mid and low-region preserving image information. Our model learns a shape of a salient object using a CNN model for a target region and estimates the full but coarse saliency map of the target image. The map is then refined using image specific low-to-mid level information. Experimental results show that the proposed method outperforms previous state-of-the-arts methods in salient object detection.