Cluster-based Co-saliency Detection

By Huan Fu, Xiaochun Cao, Zhuowen Tu. IEEE Transactions on Image Processing, 2013

411 citations recorded by the source corpus.

Co-saliency is used to discover the common saliency on the multiple images, which is a relatively underexplored area. In this paper, we introduce a new cluster-based algorithm for co-saliency detection. Global correspondence between the multiple images is implicitly learned during the clustering process. Three visual attention cues: contrast, spatial, and corresponding, are devised to effectively measure the cluster saliency. The final co-saliency maps are generated by fusing the single image saliency and multiimage saliency. The advantage of our method is mostly bottom-up without heavy learning, and has the property of being simple, general, efficient, and effective. Quantitative and qualitative experiments result in a variety of benchmark datasets demonstrating the advantages of the proposed method over the competing co-saliency methods. Our method on single image also outperforms most the state-of-the-art saliency detection methods. Furthermore, we apply the co-saliency method on four vision applications: co-segmentation, robust image distance, weakly supervised learning, and video foreground detection, which demonstrate the potential usages of the co-saliency map.

Subfields: Computer Vision and Pattern Recognition, Sensory Systems

View Paper: https://www.semanticscholar.org/paper/2a93529db315d303d4a377bf32cff419fa43aeff

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

Revisiting Video Saliency Prediction in the Deep Learning Era (2021, background): “A related topic is salient object detection [63], [64] that uniformly highlights salient object regions in images [65], [66], [67], [68], [69], videos [70], [71], [72], [73], image/video groups [74], or RGBD data [75], [76].”
Pyramid Dilated Deeper ConvLSTM for Video Salient Object Detection (2018, methodology): “Conventional video salient object detection methods [8, 9, 28, 42] extract spatial and temporal features separately and then integrate them together to generate a spatiotemporal saliency map.”
Co-Saliency Detection via a Self-Paced Multiple-Instance Learning Framework (2017, methodology): “To further detect co-saliency from multiple images, the second wave of interest [5], [6], [7], [8], [9] appeared in 2013 with the work of Li et al. [5].”
Text-Attentional Convolutional Neural Network for Scene Text Detection (2015, methodology): “Then the contrast region is defined by fusing both cues as [49].”
Review of Visual Saliency Detection With Comprehensive Information (2018, methodology): “For evaluating the running time, we tested the typical saliency detection methods, including single image saliency (DCLC [28] and SMD [29]), RGBD saliency (DF [60]), cosaliency (CCS [80]), and RGBD co-saliency (MCLP [91]), on a Quad Core 3.”
Learning to Detect Salient Objects with Image-Level Supervision (2017, background): “In co-saliency [10, 54], the assumption that a group of images contain common objects serves as a form of weak supervision.”
Depth Enhanced Saliency Detection Method (2014, methodology): “We also compare our method with six state-of-the-art algorithms, RC [3], HC [3], FT [1], FU [4], HS [13], and GBMR [14].”
Saliency-Aware Video Object Segmentation (2018, methodology): “Fu et al. [48] proposed a cluster-based saliency method, where three visual attention cues, contrast, spatial, and global correspondence, are devised to measure the cluster saliency.”
A Self-Paced Multiple-Instance Learning Framework for Co-Saliency Detection (2015, methodology): “To extend to detect co-saliency from multiple images, several novel methods [1, 21-24, 46] were proposed lately.”
Revealing Event Saliency in Unconstrained Video Collection (2017, neutral): “Fu et al. [18] proposed to explore the contrast cue, the spatial cue, and the corresponding cue to detect the co-salient regions in multiple related images.”
Cosaliency Detection Based on Intrasaliency Prior Transfer and Deep Intersaliency Mining (2016, background): “Digital Object Identifier 10.1109/TNNLS.2015.2495161 people love taking photographs, and there is a rich collection of related pictures sharing the common foreground regions of the same object or event [4].”
Uniqueness-Driven Saliency Analysis for Automated Lesion Detection with Applications to Retinal Diseases (2018, positive): “The concept of saliency is that an object stands out relative to its neighbors by virtue of its uniqueness or rarity features [1,2].”
Consistent Video Saliency Using Local Gradient Flow Optimization and Global Refinement (2015, methodology): “The performance of CS [49] is also not satisfactory, even though it considers the correspondence of objects across the video sequence.”
Saliency-aware geodesic video object segmentation (2015, background): “Even though it is not the final goal of our proposed algorithm, we still evaluate the effectiveness of our approach by comparing our spatiotemporal saliency results against the stateof-art saliency methods [31, 13, 28, 14] on the SegTrack dataset [29].”
Detection of Co-salient Objects by Looking Deep and Wide (2016, methodology): “As assumed in Fu et al. (2013), most frames in a video clip would contain the common foreground object.”