Saliency Detection for Improving Object Proposals

03/14/2016
by   Shuhan Chen, et al.
0

Object proposals greatly benefit object detection task in recent state-of-the-art works. However, the existing object proposals usually have low localization accuracy at high intersection over union threshold. To address it, we apply saliency detection to each bounding box to improve their quality in this paper. We first present a geodesic saliency detection method in contour, which is designed to find closed contours. Then, we apply it to each candidate box with multi-sizes, and refined boxes can be easily produced in the obtained saliency maps which are further used to calculate saliency scores for proposal ranking. Experiments on PASCAL VOC 2007 test dataset demonstrate the proposed refinement approach can greatly improve existing models.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 3

06/27/2018

Context Proposals for Saliency Detection

One of the fundamental properties of a salient object region is its cont...
04/02/2018

Exploring to learn visual saliency: The RL-IAC approach

The problem of object localization and recognition on autonomous mobile ...
04/22/2022

Few-Shot Object Detection with Proposal Balance Refinement

Few-shot object detection has gained significant attention in recent yea...
06/14/2017

SalProp: Salient object proposals via aggregated edge cues

In this paper, we propose a novel object proposal generation scheme by f...
09/24/2017

Can Image Retrieval help Visual Saliency Detection?

We propose a novel image retrieval framework for visual saliency detecti...
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...
09/08/2015

Object Proposals for Text Extraction in the Wild

Object Proposals is a recent computer vision technique receiving increas...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.