Abstract
We aim at detecting salient objects in unconstrained images. In unconstrained images, the number of salient ob-jects (if any) varies from image to image, and is not given.We present a salient object detection system that directly outputs a compact set of detection windows, if any, for aninput image. Our system leverages a Convolutional-Neural-Network model to generate location proposals of salient ob-jects. Location proposals tend to be highly overlapping andnoisy. Based on the Maximum a Posteriori principle, we propose a novel subset optimization framework to generate a compact set of detection windows out of noisy proposals. In experiments, we show that our subset optimization formulation greatly enhances the performance of our system, and our system attains 16-34% relative improvement in Av-erage Precision compared with the state-of-the-art on three challenging salient object datasets.