Robust Salient Object Detection via Fusing Foreground and Background Priors

  title={Robust Salient Object Detection via Fusing Foreground and Background Priors},
  author={Kan Huang and Chunbiao Zhu and Ge Li},
  journal={2018 25th IEEE International Conference on Image Processing (ICIP)},
  • Kan HuangChunbiao ZhuGe Li
  • Published 1 November 2017
  • Computer Science
  • 2018 25th IEEE International Conference on Image Processing (ICIP)
Automatic salient object detection without any supervised labor tends to greatly enhance many computer vision tasks. This paper proposes a novel bottom-up salient object detection framework which considers both foreground and background priors in detecting process. First, a series of foreground seeds are extracted from an image based on surroundedness cue. Then, a foreground-corresponding saliency map is generated via ranking algorithm according to these seeds. In a similar way a series of… 

Figures and Tables from this paper

Saliency Detection via Fusing Color Contrast and Hash Fingerprint

This study proposes a simple and effective saliency detection method combining color contrast and hash fingerprint, which works better even in the presence of complex background or very large salient regions.

Salient Contour-Aware Based Twice Learning Strategy for Saliency Detection

A novel contour-aware algorithm using FCNs with a twice learning strategy for saliency detection, which imitates and dissects the process of human cognition, to address the problems of existing deep learning-based methods.

A Novel Probabilistic Contrast-Based Complex Salient Object Detection

The proposed Poisson-based probabilistic contrast method produces saliency with the concave topographical surface and is evaluated on the publicly available datasets, compared with 12 state-of-the-art methods.

An efficient modification of generalized gradient vector flow using directional contrast for salient object detection and intelligent scene analysis

The Generalized Gradient Vector Flow model is modified by adding contrast information to enhance salient object information with background information so that for producing contours, not only edge information is utilized, but saliency information is also used.

Annotation of images using local binary pattern and local derivative pattern after salient object detection using minimum directional contrast and gradient vector flow

Automatic image annotation is the process of providing tags to salient objects in the image by modifying cluster-based multi-label learning with feature-induced labeling information enrichment (C-MLFE), and the result is compared with six state-of-the-art algorithms.

Certifiably Robust Interpretation in Deep Learning

It is shown that a sparsified version of the popular SmoothGrad method, which computes the average saliency maps over random perturbation of the input, is certifiably robust against adversarial perturbations.

Foreground-Background Separation via Generalized Nuclear Norm and Structured Sparse Norm Based Low-Rank and Sparse Decomposition

This paper introduces the generalized nuclear norm and structured sparse norm (GNNSSN) method based LRSD for video foreground-background separation, and extends the proposed model to a robust model against noise for practical applications.



Salient object detection via objectness measure

A novel saliency measure called `foreground connectivity' is proposed which determines how tightly a pixel or a region is connected to the estimated foreground in an image and is used as foreground weights and integrated in an optimization framework to obtain the final saliency maps.

Saliency Optimization from Robust Background Detection

This work proposes a robust background measure, called boundary connectivity, which characterizes the spatial layout of image regions with respect to image boundaries and is much more robust and presents unique benefits that are absent in previous saliency measures.

Global contrast based salient region detection

This work proposes a regional contrast based saliency extraction algorithm, which simultaneously evaluates global contrast differences and spatial coherence, and consistently outperformed existing saliency detection methods.

Automatic salient object segmentation based on context and shape prior

A novel automatic salient object segmentation algorithm which integrates both bottom-up salient stimuli and object-level shape prior, leading to binary segmentation of the salient object.

Geodesic saliency propagation for image salient region detection

A novel geodesic saliency propagation method where detected salient objects may be isolated from both the background and other clutter by adding global considerations in the detection process by capable of rendering a uniform saliency map while suppressing the background, leading to salient objects being popped out.

Hierarchical Saliency Detection

This work tackles saliency detection from a scale point of view and proposes a multi-layer approach to analyze saliency cues, by finding saliency values optimally in a tree model.

Saliency Detection with Multi-Scale Superpixels

This work proposes a salient object detection algorithm via multi-scale analysis on superpixels that achieves the highest precision value when evaluated on one of the most popular datasets, the ASD dataset.

Frequency-tuned salient region detection

This paper introduces a method for salient region detection that outputs full resolution saliency maps with well-defined boundaries of salient objects that outperforms the five algorithms both on the ground-truth evaluation and on the segmentation task by achieving both higher precision and better recall.

Region-Based Saliency Detection and Its Application in Object Recognition

The objective of this paper is to introduce an effective region-based solution for saliency detection, and to better encode the image features for solving object recognition task by incorporating a saliency map into sparse coding-based spatial pyramid matching (ScSPM) image representation.

Saliency Detection via Dense and Sparse Reconstruction

A visual saliency detection algorithm from the perspective of reconstruction errors that applies the Bayes formula to integrate saliency measures based on dense and sparse reconstruction errors and refined by an object-biased Gaussian model is proposed.