ITSELF: Iterative Saliency Estimation fLexible Framework

by   Leonardo de Melo Joao, et al.

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.


page 2

page 6

page 8

page 9

page 10

page 12

page 13

page 15


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

Most of the saliency methods are evaluated on their ability to generate ...

Comprehensive Saliency Fusion for Object Co-segmentation

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

An Unsupervised Game-Theoretic Approach to Saliency Detection

We propose a novel unsupervised game-theoretic salient object detection ...

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...

Oversegmenting Graphs

We propose a novel method to adapt a graph to image data. The method dri...

Towards Stable Co-saliency Detection and Object Co-segmentation

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

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

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