Context Proposals for Saliency Detection

06/27/2018
by   Aymen Azaza, et al.
0

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).

READ FULL TEXT

page 7

page 8

page 10

page 13

page 21

page 25

research
05/08/2023

SegGPT Meets Co-Saliency Scene

Co-salient object detection targets at detecting co-existed salient obje...
research
03/14/2016

Saliency Detection for Improving Object Proposals

Object proposals greatly benefit object detection task in recent state-o...
research
06/14/2017

SalProp: Salient object proposals via aggregated edge cues

In this paper, we propose a novel object proposal generation scheme by f...
research
03/03/2015

Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation

We propose a unified approach for bottom-up hierarchical image segmentat...
research
12/04/2016

Learning to Segment Object Proposals via Recursive Neural Networks

To avoid the exhaustive search over locations and scales, current state-...
research
10/20/2018

Sequential Context Encoding for Duplicate Removal

Duplicate removal is a critical step to accomplish a reasonable amount o...
research
04/11/2018

Fusing Saliency Maps with Region Proposals for Unsupervised Object Localization

In this paper we address the problem of unsupervised localization of obj...

Please sign up or login with your details

Forgot password? Click here to reset