Global contrast based salient region detection

By Ming-Ming Cheng, Guo-Xin Zhang, Niloy J. Mitra, Xiaolei Huang, Shimin Hu. Computer Vision and Pattern Recognition, 2011

3,834 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Sensory Systems

View Paper: https://www.semanticscholar.org/paper/7670e3c493126c8b2f211ddfc45f89de905f1d38

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Sensory Systems

Citations in the corpus

Label Decoupling Framework for Salient Object Detection (2020, background): “Salient object detection (SOD) [1, 6, 10, 11, 12] aims at identifying the most visually attractive objects or parts in an image or video, which is widely applied as a pre-processing”
Semantic Object Selection (2014, methodology): “The method in [4] uses similar contrast and loca- tion terms, and then computes a binary segmentation by including the computed saliency in a variant of GrabCut [20].”
JL-DCF: Joint Learning and Densely-Cooperative Fusion Framework for RGB-D Salient Object Detection (2020, background): “Salient object detection (SOD) aims at detecting the objects in a scene that humans would naturally focus on [2, 9, 78].”
Weakly- and Semi-Supervised Panoptic Segmentation (2018, methodology): “Note that saliency priors, used by many works such as [10, 31, 32] on Pascal VOC, are not suitable for “stuff” classes as popular saliency datasets [34–36] only consider “things” to be salient.”
Depth Enhanced Saliency Detection Method (2014, methodology): “Other saliency maps by RC [3] (d), HC [3] (e), FT [1] (f), FU [4] (g), HS [13] (h), and GBMR [14] (i).”
STC: A Simple to Complex Framework for Weakly-Supervised Semantic Segmentation (2015, methodology): “Therefore, directly applying SaliencyCut [20] to generate segmentation masks will introduce many nosies, which is harmful for training the I-DCNN.”
Salient Object Detection With Pyramid Attention and Salient Edges (2019, methodology): “Since then, numerous subsequent works have been reported, mainly using contrast based assumption [9, 49, 17] and background prior [46, 58].”
Predicting the Driver's Focus of Attention: The DR(eye)VE Project (2017, background): “In this context, computational models focus on spotting visual discontinuities, either by clustering features or considering the rarity of image regions, locally [36], [50] or globally [1], [10], [65].”
Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detection (2017, methodology): “Datasets: For the training, we utilize the MSRA10K dataset [5], which includes 10,000 images with high quality pixel-wise annotations.”
Deep networks for saliency detection via local estimation and global search (2015, methodology): “(d) Saliency maps by a global method [7].”
Salient Object Subitizing (2015, methodology): “Given a test image, some methods (Achanta et al. 2009; Cheng et al. 2011; Shen and Wu 2012; Zhang et al. 2015b) generate a saliency map that highlights the overall region of salient objects; other methods (Liu et al.”
Visual Saliency Based on Scale-Space Analysis in the Frequency Domain (2013, neutral): “F”
Distilling Localization for Self-Supervised Representation Learning (2020, background): “Useful priors include background priors [20], color contrast priors [5], and objectness [24].”
GrabCut in One Cut (2013, methodology): “Optimizing E3(S) results in precision = 91%, recall = 85% and F-measure = 86%, whereas incorporating the appearance term in E4(S) yields precision = 89%, recall = 89% and F-measure = 89%, which is comparable to the state-of-the-art results reported in literature [7](precision = 90%, recall = 90%, F-”
Understanding Deep Learning Techniques for Image Segmentation (2019, background): “umour Segmentation [74] BACH: Breast Cancer Histology [6] IDRiD: Indian Diabetic Retinopathy Image Dataset [169] ISLES: Ischemic Stroke Lesion Segmentation [135] Saliency MSRA Salient Object Database [37] Detection ECSSD: Extended Complex Scene Saliency Dataset [187] PASCAL-S DATASET [117] THUR15K: ”
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].”
A unified approach to salient object detection via low rank matrix recovery (2012, methodology): “which has motivated various models and methods that combine local, regional and global contrast-based features [17, 23, 27, 18, 8, 4, 16].”