Unsupervised Salient Object Detection via Inferring From Imperfect Saliency Models

Ma, Rong Quan; Han, Junwei; Zhang, Dingwen; Nie, Feiping; Qian, Xueming; Li, Xuelong

doi:10.1109/tmm.2017.2763780

Cited by 34 publications

(10 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Bottom-up data-driven models take the underlying image features and some priors [13]- [21] into consideration, such as color, orientation, texture, boundary, and contrast. Then Gopalakrishnan et al [14] performed Markov random walks on a complete graph and a k-regular graph to detect the salient object.…”

Section: Related Work a Rgb Image Saliency Detectionmentioning

confidence: 99%

RGB-T Image Saliency Detection via Collaborative Graph Learning

Xia

et al. 2020

IEEE Trans. Multimedia

157

View full text Add to dashboard Cite

Image saliency detection is an active research topic in the community of computer vision and multimedia. Fusing complementary RGB and thermal infrared data has been proven to be effective for image saliency detection. In this paper, we propose an effective approach for RGB-T image saliency detection. Our approach relies on a novel collaborative graph learning algorithm. In particular, we take superpixels as graph nodes, and collaboratively use hierarchical deep features to jointly learn graph affinity and node saliency in a unified optimization framework. Moreover, we contribute a more challenging dataset for the purpose of RGB-T image saliency detection, which contains 1000 spatially aligned RGB-T image pairs and their ground truth annotations. Extensive experiments on the public dataset and the newly created dataset suggest that the proposed approach performs favorably against the state-of-the-art RGB-T saliency detection methods.

show abstract

Section: Related Work a Rgb Image Saliency Detectionmentioning

confidence: 99%

RGB-T Image Saliency Detection via Collaborative Graph Learning

Xia

et al. 2020

IEEE Trans. Multimedia

157

View full text Add to dashboard Cite

show abstract

“…Besides, each superpixel on the image is assumed to possess difficulty for saliency assessment, namely π n . In recent saliency integration approaches [48], [49], the concept of superpixel difficulty are adopted in the process of computing the expertise of the candidate saliency map. The expertise β p as well as the difficulty of the superpixel π n are assumed as latent variables and are solved by optimizations.…”

Section: B Latent-variable-based Expertisementioning

confidence: 99%

“…However, as shown by the experimental results [37], the M-estimators perform similarly to average weighting, indicating that the computed weights are far from accurately specifying the expertise of the candidate models. Recently, some integration approaches [48], [49] explore expertise estimation by bringing the concept of superpixel difficulty, as each superpixel of an image may possess different difficulty for saliency assessment. This concept of using superpixel difficulty together with model expertise as hidden variables facilitates the expertise estimation process from a more refined superpixel level.…”

Section: Introductionmentioning

confidence: 99%

Saliency Integration: An Arbitrator Model

Hong

Porikli

et al. 2019

IEEE Trans. Multimedia

View full text Add to dashboard Cite

Saliency integration has attracted much attention on unifying saliency maps from multiple saliency models. Previous offline integration methods usually face two challenges: 1. if most of the candidate saliency models misjudge the saliency on an image, the integration result will lean heavily on those inferior candidate models; 2. an unawareness of the ground truth saliency labels brings difficulty in estimating the expertise of each candidate model. To address these problems, in this paper, we propose an arbitrator model (AM) for saliency integration. Firstly, we incorporate the consensus of multiple saliency models and the external knowledge into a reference map to effectively rectify the misleading by candidate models. Secondly, our quest for ways of estimating the expertise of the saliency models without ground truth labels gives rise to two distinct online model-expertise estimation methods. Finally, we derive a Bayesian integration framework to reconcile the saliency models of varying expertise and the reference map. To extensively evaluate the proposed AM model, we test twenty-seven state-of-the-art saliency models, covering both traditional and deep learning ones, on various combinations over four datasets. The evaluation results show that the AM model improves the performance substantially compared to the existing state-of-the-art integration methods, regardless of the chosen candidate saliency models.

show abstract

“…Over the past two decades, saliency detection has played an increasingly important role in computer vision problems. The accuracy of salient object detection has improved rapidly due to the renaissance of convolutional neural network (CNN) models [9], [10], which have shown superior performance over traditional solutions [11]- [13]. Due to the multilevel and multiscale features extracted by CNNs, the most salient objects can be captured with high precision [14].…”

Section: Introductionmentioning

confidence: 99%

Salient instance segmentation via subitizing and clustering

et al. 2020

View full text Add to dashboard Cite

The goal of salient region detection is to identify the regions of an image that attract the most attention. Many methods have achieved state-of-the-art performance levels on this task. Recently, salient instance segmentation has become an even more challenging task than traditional salient region detection; however, few of the existing methods have concentrated on this underexplored problem. Unlike the existing methods, which usually employ object proposals to roughly count and locate object instances, our method applies salient objects subitizing to predict an accurate number of instances for salient instance segmentation. In this paper, we propose a multitask densely connected neural network (MDNN) to segment salient instances in an image. In contrast to existing approaches, our framework is proposal-free and category-independent. The MDNN contains two parallel branches: the first is a densely connected subitizing network (DSN) used for subitizing prediction; the second is a densely connected fully convolutional network (DFCN) used for salient region detection. The MDNN simultaneously outputs saliency maps and salient object subitizing. Then, an adaptive deep feature-based spectral clustering operation segments the salient regions into instances based on the subitizing and saliency maps. The experimental results on both salient region detection and salient instance segmentation datasets demonstrate the satisfactory performance of our framework. Notably, its AP r @0.7 reaches 60.14% in the salient instance dataset, surpasses the state-of-the-art methods by about 5%.

show abstract

Unsupervised Salient Object Detection via Inferring From Imperfect Saliency Models

Cited by 34 publications

References 37 publications

RGB-T Image Saliency Detection via Collaborative Graph Learning

RGB-T Image Saliency Detection via Collaborative Graph Learning

Saliency Integration: An Arbitrator Model

Salient instance segmentation via subitizing and clustering

Contact Info

Product

Resources

About