Fusing generic objectness and visual saliency for salient object detection

Chang, Kai-Yueh; Liu, Tyng-Luh; Chen, Hwann-Tzong; Lai, Shang-Hong

doi:10.1109/iccv.2011.6126333

Cited by 124 publications

(26 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Next, we describe the datasets shortly and report both quantitative and qualitative comparisons of our approach with state-of-the-art approaches in detail. To save space, we compare our method with several prior ones, including SVO [39], PCAS [40], RC [12] and DRFI [11], which are the top four models or their improvements in survey [2]. In addition, we also consider well-known methods, such as CA [32], FT [30], HS [10], LRMR [33] and MR [15], that are not covered in [2].…”

Section: Experimental Results and Analysismentioning

confidence: 99%

“…5, our method produces consistently the lowest error on MSRA-B, SED and iCoSeg datasets, indicating more robustness against different datasets. Despite good performance in precision-recall curves and F-measure, LRMR [33], CA [32], FT [30] and SVO [39] have the higher MAE due to the weak background suppression.…”

Section: Quantitative Comparisonmentioning

confidence: 95%

“…In contrast, such risk is avoided in our method as no threshold is used to binarize the saliency map for performance boosting. For other state-of-the-art approaches, it can be seen that while SVO [39] detects the salient regions, parts of the background are erroneously detected as salient. FT [30], which exploited the central-surround principle by defining the saliency of a pixel as its distance to the average image, generally detect the foreground from input images.…”

Section: Visual Comparisonmentioning

confidence: 99%

See 2 more Smart Citations

Salient Object Detection via Adaptive Region Merging

2016

KSII TIIS

View full text Add to dashboard Cite

Most existing salient object detection algorithms commonly employed segmentation techniques to eliminate background noise and reduce computation by treating each segment as a processing unit. However, individual small segments provide little information about global contents. Such schemes have limited capability on modeling global perceptual phenomena. In this paper, a novel salient object detection algorithm is proposed based on region merging. An adaptive-based merging scheme is developed to reassemble regions based on their color dissimilarities. The merging strategy can be described as that a region R is merged with its adjacent region Q if Q has the lowest dissimilarity with Q among all Q's adjacent regions. To guide the merging process, superpixels that located at the boundary of the image are treated as the seeds. However, it is possible for a boundary in the input image to be occupied by the foreground object. To avoid this case, we optimize the boundary influences by locating and eliminating erroneous boundaries before the region merging. We show that even though three simple region saliency measurements are adopted for each region, encouraging performance can be obtained. Experiments on four benchmark datasets including MSRA-B, SOD, SED and iCoSeg show the proposed method results in uniform object enhancement and achieve state-of-the-art performance by comparing with nine existing methods.

show abstract

Section: Experimental Results and Analysismentioning

confidence: 99%

Section: Quantitative Comparisonmentioning

confidence: 95%

Section: Visual Comparisonmentioning

confidence: 99%

See 1 more Smart Citation

Salient Object Detection via Adaptive Region Merging

2016

KSII TIIS

View full text Add to dashboard Cite

show abstract

“…Where S is is the saliency map, G is the ground truth. The performance of the proposed method is compared with 9 state-of-art methods, including DRFI [54], HS [10], PCA [55], RC [36], SVO [56], DSR [39], LEGS [57], DS [28], MDF [27], DCL [45], RFCN [44] and DSS [43]. Note that LEGS, DS, MDF, DCL, RFCN and DSS are methods based on deep learning.…”

Section: Evaluation Metricsmentioning

confidence: 99%

Efficient Salient Object Detection Model with Dilated Convolutional Networks

Guo

Yang

Gao

et al. 2020

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

Introduction of Fully Convolutional Networks (FCNs) has made record progress in salient object detection models. However, in order to retain the input resolutions, deconvolutional networks with unpooling are applied on top of FCNs. This will cause the increase of the computation and network model size in segmentation task. In addition, most deep learning based methods always discard effective saliency prior knowledge completely, which are shown effective. Therefore, an efficient salient object detection method based on deep learning is proposed in our work. In this model, dilated convolutions are exploited in the networks to produce the output with high resolution without pooling and adding deconvolutional networks. In this way, the parameters and depth of the network are decreased sharply compared with the traditional FCNs. Furthermore, manifold ranking model is explored for the saliency refinement to keep the spatial consistency and contour preserving. Experimental results verify that performance of our method is superior with other state-of-art methods. Meanwhile, the proposed model occupies the less model size and fastest processing speed, which is more suitable for the wearable processing systems.

show abstract

“…To mimic this property, the saliency detection algorithms are designed to identify the most informative regions of an image by using the priors and characteristics of the HVS. [17][18][19][20][21][22][23][24][25][26] Because this saliency information is useful for many applications of computer vision as stated in the introduction, many researchers proposed various kinds of prior to detect salient region such as center prior, local and global contrast prior, background characteristics, boundary prior, and so on. In this section, we introduce just a few methods among numerous works, which are quite fast and easily exploited for our saliency-based backlight control application: Yang et al 22 adopted a semi-supervised learning scheme, but their algorithm is based on simple node ranking considering whether a node belongs to either background or saliency.…”

Section: Saliency Detection Algorithmmentioning

confidence: 99%

Human visual perception‐based localized backlight scaling method for high dynamic range LCDs

2016

View full text Add to dashboard Cite

This paper presents a backlight control algorithm for liquid crystal display devices, which considers the human visual properties that we are usually attracted to the saliencies in a scene. The saliency means regions or objects that have different contrast or color from the surrounding, and thus attract our attention, which can be measured in various ways from each pixel value and its relation with the surrounding ones. Hence, by keeping or boosting the backlight of salient regions while suppressing in others, the quality of salient regions and overall contrast are enhanced. In addition, power can be saved by backlight dimming in non‐salient regions, without loss of overall quality in terms of human visual perception. In this backlight control process, the amount of energy consumption is regulated so that the proposed method consumes less than or equal energy as before, by developing a power management algorithm based on the bit rate control strategies of MPEG2 video encoders. Precisely, the energy consumption in each backlight unit is controlled by a parameter, so that the sum of energies of overall backlight units is kept within a limit.

show abstract

Fusing generic objectness and visual saliency for salient object detection

Abstract: We

Cited by 124 publications

References 20 publications

Salient Object Detection via Adaptive Region Merging

Salient Object Detection via Adaptive Region Merging

Efficient Salient Object Detection Model with Dilated Convolutional Networks

Human visual perception‐based localized backlight scaling method for high dynamic range LCDs

Contact Info

Product

Resources

About