Center-surround divergence of feature statistics for salient object detection

By Dominik A. Klein, Simone Frintrop. Vision, 2011

382 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/00a79a013a244b512b3dd5343197ee9155928e8a

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

In Computer Vision and Pattern Recognition

Citations in the corpus

Salient Object Detection via Structured Matrix Decomposition (2017, background): “the theories by taking account of local [43], [44], regional [45], and global [46] contrast cues, or by searching for saliency cues in the frequency domain [14], [47].”
DHSNet: Deep Hierarchical Saliency Network for Salient Object Detection (2016, background): “Local contrast based methods [5, 6] typically tend to highlight object boundaries while often miss object interiors.”
Geodesic Saliency Using Background Priors (2012, methodology): “Local methods compute various contrast measures in a local neighborhood of the pixel/patch, such as edge contrast [8], center-surround discriminative power [7], center-surround differences [1, 8, 13], curvature [10] and self information [6].”
RGBD Salient Object Detection via Deep Fusion (2016, methodology): “In [31], the authors propose an information-theoretic way to estimate the contrast between”
EGNet: Edge Guidance Network for Salient Object Detection (2019, methodology): “Early methods predicted the saliency map using a bottom-up pattern by the hand-craft feature, such as contrast [5], boundary background [57, 68], center prior [24, 44] and so on [22, 44, 51].”
PiCANet: Learning Pixel-Wise Contextual Attention for Saliency Detection (2017, methodology): “Traditional saliency models mainly rely on various saliency cues to detect salient objects, including local contrast [15], global contrast [4], and background prior [43].”
Deep Contrast Learning for Salient Object Detection (2016, background): “Salient object detection can be performed either in a bottom-up fashion using low-level features [14, 1, 30, 23, 39, 49, 21, 51, 8] or in a top-down fashion via the incorporation of high-level knowledge [22, 5, 17, 41, 29, 19, 28].”
Consistent Video Saliency Using Local Gradient Flow Optimization and Global Refinement (2015, background): “Klein and Frintrop [40] presented a framework for saliency detection based on the efﬁcient fusion of different feature channels and the local center-surround hypothesis.”
DeepSaliency: Multi-Task Deep Neural Network Model for Salient Object Detection (2015, background): “As shown in Figure 4(c), our network is able to detect objects with a high contrast to the surroundings [20] (i.”
Learning Uncertain Convolutional Features for Accurate Saliency Detection (2017, background): “Although significant progress has been made [15, 1, 30, 21, 33, 46], saliency detection remains very challenging due to complex factors in real world scenarios.”
Salient Object Detection: A Discriminative Regional Feature Integration Approach (2013, background): “An information theory perspective is introduced to yield a sound mathematical formulation, computing the center-surround divergence based on feature statistics [27].”
Deeply Supervised Salient Object Detection with Short Connections (2016, background): “The majority of salient object detection methods are based on hand-crafted local features [22, 25, 50], global features [7, 42, 37, 24], or both (e.”
Hierarchical Image Saliency Detection on Extended CSSD (2016, methodology): “We also construct an extended Complex Scene Saliency Dataset (ECSSD) to include complex but general natural images.”
Hierarchical Saliency Detection (2013, methodology): “Local methods [13, 10, 1, 15] rely on pixel/region difference in the vicinity, while global methods [2, 4, 23, 30] rely mainly on color uniqueness in terms of global statistics.”
What Do Different Evaluation Metrics Tell Us About Saliency Models? (2016, methodology): “Consider a detection application of saliency such as object and motion detection, surveillance, localization and mapping, and segmentation [1], [17], [27], [28], [43], [50], [59], [91].”
Saliency-Aware Video Object Segmentation (2018, methodology): “Goferman et al. [42] presented a saliency method based on the fusion of different feature channels and local center-surround hypothesis.”