ITSELF: Iterative Saliency Estimation fLexible Framework

06/30/2020
by   Leonardo de Melo Joao, et al.
0

Saliency object detection estimates the objects that most stand out in an image. The available unsupervised saliency estimators rely on a pre-determined set of assumptions of how humans perceive saliency to create discriminating features. By fixing the pre-selected assumptions as integral part of their models, these methods cannot be easily extended for specific settings and different image domains. We then propose an superpixel-based ITerative Saliency Estimation fLexible Framework (ITSELF) that allows any number of user-defined assumptions to be added to the model when required. Thanks to recent advancement on superpixel segmentation algorithms, saliency-maps can be used to improve superpixel delineation. By combining a saliency-based superpixel algorithm to a superpixel-based saliency estimator, we propose a novel saliency/superpixel self-improving loop to iteratively enhance saliency maps. We compared ITSELF to two state-of-the-art saliency estimators on five metrics and six datasets, four of which are composed of natural-images, and two of biomedical-images. Experiments show that our approach is more robust than the compared methods, presenting competitive results on natural-image datasets and outperforming them on biomedical-image datasets.

READ FULL TEXT

page 2

page 6

page 8

page 9

page 10

page 12

page 13

page 15

07/24/2020

Hallucinating Saliency Maps for Fine-Grained Image Classification for Limited Data Domains

Most of the saliency methods are evaluated on their ability to generate ...
01/30/2022

Comprehensive Saliency Fusion for Object Co-segmentation

Object co-segmentation has drawn significant attention in recent years, ...
08/08/2017

An Unsupervised Game-Theoretic Approach to Saliency Detection

We propose a novel unsupervised game-theoretic salient object detection ...
06/19/2017

User-driven mobile robot storyboarding: Learning image interest and saliency from pairwise image comparisons

This paper describes a novel storyboarding scheme that uses a model trai...
06/01/2018

Oversegmenting Graphs

We propose a novel method to adapt a graph to image data. The method dri...
09/25/2022

Towards Stable Co-saliency Detection and Object Co-segmentation

In this paper, we present a novel model for simultaneous stable co-salie...
05/27/2015

New characterizations of minimum spanning trees and of saliency maps based on quasi-flat zones

We study three representations of hierarchies of partitions: dendrograms...