Context Proposals for Saliency Detection

TL;DR

This paper enhances saliency detection by integrating context proposals with object proposals, introducing new features that improve segmentation performance across multiple datasets.

Contribution

It introduces a novel approach combining context proposals with object proposals and develops new features to improve salient object detection accuracy.

Findings

Multiscale Combinatorial Grouping outperforms other object proposal methods.

Context features improve saliency detection performance.

Method achieves competitive results on multiple datasets.

Abstract

One of the fundamental properties of a salient object region is its contrast with the immediate context. The problem is that numerous object regions exist which potentially can all be salient. One way to prevent an exhaustive search over all object regions is by using object proposal algorithms. These return a limited set of regions which are most likely to contain an object. Several saliency estimation methods have used object proposals. However, they focus on the saliency of the proposal only, and the importance of its immediate context has not been evaluated. In this paper, we aim to improve salient object detection. Therefore, we extend object proposal methods with context proposals, which allow to incorporate the immediate context in the saliency computation. We propose several saliency features which are computed from the context proposals. In the experiments, we evaluate five object proposal methods for the task of saliency segmentation, and find that Multiscale Combinatorial Grouping outperforms the others. Furthermore, experiments show that the proposed context features improve performance, and that our method matches results on the FT datasets and obtains competitive results on three other datasets (PASCAL-S, MSRA-B and ECSSD).