Salient Object Detection: A Discriminative Regional Feature Integration Approach

Jiang, Huaizu; Wang, Jingdong; Yuan, Zejian; Wu, Yaming; Zheng, Nanning; Li, Shipeng

doi:10.1109/cvpr.2013.271

Cited by 1,037 publications

(806 citation statements)

References 59 publications

Supporting

Mentioning

797

Contrasting

Unclassified

Order By: Relevance

“…To evaluate the performance of our saliency model, we choose 10 state-ofthe-art saliency models: DRFI, IDRFI, BL, CGVS, DW, HDCT, MS, PR-GL, RRWR and SPMP to compare with our model [10,[28][29][30][31][32][33][34][35][36]. In experiments, we utilize 2 metrics for quantitative performance evaluations including Precision and Recall curve(PR) and F-measure.…”

Section: Experiments Resultsmentioning

confidence: 99%

“…In most traditional methods, the salient objects were derived by the features extracted from pixels or regions, images were usually decomposed into several superpixel regions and final saliency maps consisted of these regions with their saliency scores [7][8][9][10]. The performance of these models rely on the segmentation methods and the selection of the feature.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Saliency Detection Via Dense Convolution Network

Fang¹,

Cao²,

Xing³

2017

International Symposium on Computer Science and Artificial Intelligence(ISCSAI)

View full text Add to dashboard Cite

Saliency detection is a fundamental problem in the field of image processing and computer vision. The convolutional model has been also used in saliency detection for its outstanding performance on image classification and localization task. In this paper, we propose a novel way to detect the salient object by modifying the Dense Convolution Network (DenseNet). We replace the fully-connected layer and the final pooling layer in DenseNet into a convolution layer and a deconvolution layer to fit the saliency detection task. And our network ends up with a squared Euclidean loss layer for saliency regression. Our network is end-to-end architecture which outputs saliency maps directly. Experimental results demonstrate that our approach is competitive in comparison with the state-of-the-art approaches.

show abstract

Section: Experiments Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Saliency Detection Via Dense Convolution Network

Fang¹,

Cao²,

Xing³

2017

International Symposium on Computer Science and Artificial Intelligence(ISCSAI)

View full text Add to dashboard Cite

show abstract

“…Therefore, in this work we focus on unsupervised salient object detection. While supervised approaches, such as those in [45] and [36], have the potential of finding more accurate results, their performance depends on the training process followed and the data that has been exploited for training. Recent works have also indicated that unsupervised saliency detection approaches can compete (or even outperform) supervised methods [43].…”

Section: Probabilistic Saliency Estimationmentioning

confidence: 99%

“…DRFI [45] was also ranked as one of the top methods in the study; however, it is a supervised method and, hence, it is not included in our comparisons. The saliency maps for the above algorithms were downloaded from the website [30] related to the study in [43].…”

Section: Comparison With the State-of-the-artmentioning

confidence: 99%

Probabilistic saliency estimation

Aytekin

Iosifidis

Gabbouj

2018

Pattern Recognition

View full text Add to dashboard Cite

Abstract-In this paper, we model the salient object detection problem under a probabilistic framework encoding the boundary connectivity saliency cue and smoothness constraints in an optimization problem. We show that this problem has a closed form global optimum which estimates the salient object. We further show that along with the probabilistic framework, the proposed method also enjoys a wide range of interpretations, i.e. graph cut, diffusion maps and one-class classification. With an analysis according to these interpretations, we also find that our proposed method provides approximations to the global optimum to another criterion that integrates local/global contrast and large area saliency cues. The proposed approach achieves mostly leading performance compared to the state-of-the-art algorithms over a large set of salient object detection datasets including around 17k images for several evaluation metrics. Furthermore, the computational complexity of the proposed method is favorable/comparable to many state-of-the-art techniques.

show abstract

“…Recently, numerous bottom-up saliency detection methods have been proposed,which prefer to generate the saliency map by utilizing the boundary information.In [12],the contrast against image boundary is used as a new regional feature vector to characterize the background.In [14],a more robust boundary-based measure is proposed,which takes the spatial layout of image patches into consideration. [15] uses the four boundaries of an image as background cues to get foreground queries via manifold ranking(MR).…”

Section: Related Workmentioning

confidence: 99%