An End-to-End Network for Co-Saliency Detection in One Single Image

TL;DR

This paper introduces an end-to-end trainable neural network for co-saliency detection within single images, combining bottom-up and top-down strategies to improve accuracy and speed.

Contribution

It presents a novel network architecture with a backbone and two branch nets, integrating ground-truth guidance and triplet-based regional clustering for co-saliency detection.

Findings

Achieves state-of-the-art accuracy in co-saliency detection

Operates at 28 frames per second, demonstrating real-time capability

Introduces a new dataset of 2,019 images for evaluation

Abstract

Co-saliency detection within a single image is a common vision problem that has received little attention and has not yet been well addressed. Existing methods often used a bottom-up strategy to infer co-saliency in an image in which salient regions are firstly detected using visual primitives such as color and shape and then grouped and merged into a co-saliency map. However, co-saliency is intrinsically perceived complexly with bottom-up and top-down strategies combined in human vision. To address this problem, this study proposes a novel end-to-end trainable network comprising a backbone net and two branch nets. The backbone net uses ground-truth masks as top-down guidance for saliency prediction, whereas the two branch nets construct triplet proposals for regional feature mapping and clustering, which drives the network to be bottom-up sensitive to co-salient regions. We construct a new dataset of 2,019 natural images with co-saliency in each image to evaluate the proposed method. Experimental results show that the proposed method achieves state-of-the-art accuracy with a running speed of 28 fps.