Integrated Deep and Shallow Networks for Salient Object Detection

TL;DR

This paper introduces a unified framework combining deep CNNs and unsupervised methods for salient object detection, achieving superior results on multiple benchmarks.

Contribution

It presents an integrated approach that combines deep learning and unsupervised saliency to improve detection accuracy and boundary sharpness.

Findings

Outperforms state-of-the-art methods on 8 benchmark datasets.

Effectively combines deep features with unsupervised saliency.

Produces spatially consistent saliency maps with sharp boundaries.

Abstract

Deep convolutional neural network (CNN) based salient object detection methods have achieved state-of-the-art performance and outperform those unsupervised methods with a wide margin. In this paper, we propose to integrate deep and unsupervised saliency for salient object detection under a unified framework. Specifically, our method takes results of unsupervised saliency (Robust Background Detection, RBD) and normalized color images as inputs, and directly learns an end-to-end mapping between inputs and the corresponding saliency maps. The color images are fed into a Fully Convolutional Neural Networks (FCNN) adapted from semantic segmentation to exploit high-level semantic cues for salient object detection. Then the results from deep FCNN and RBD are concatenated to feed into a shallow network to map the concatenated feature maps to saliency maps. Finally, to obtain a spatially consistent saliency map with sharp object boundaries, we fuse superpixel level saliency map at multi-scale. Extensive experimental results on 8 benchmark datasets demonstrate that the proposed method outperforms the state-of-the-art approaches with a margin.