Progressive Attention Guided Recurrent Network for Salient Object Detection

Zhang, Xiaoning; Wang, Tiantian; Qi, Jinqing; Lu, Huchuan; Wang, Gang

doi:10.1109/cvpr.2018.00081

Cited by 596 publications

(388 citation statements)

References 25 publications

Supporting

Mentioning

383

Contrasting

Unclassified

Order By: Relevance

“…The higher that S-measure and E-measure are, the better results are the methods. For comparison with other salient region detection methods, we performed a horizontal evaluation with 12 classic or stateof-the-art methods, including GC [65], GMR [58], DRFI [66], FT [59], BMS [37], MDF [10], MTDNN [39], DCL [28], MSRNet [18], DSS [67], PAGR [68] and [69]. Among these methods, the first five are implemented based on traditional machine learning, while the rest of approaches operate using deep learning models.…”

Section: B Results and Comparisonsmentioning

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

Section: B Results and Comparisonsmentioning

confidence: 99%

Salient instance segmentation via subitizing and clustering

et al. 2020

View full text Add to dashboard Cite

show abstract

“…We compare our method with 16 previous state-of-the-art methods, namely MDF [28], RFCN [18], UCF [20], Amulet [13], NLDF [12], DSS [31], BMPM [21], PAGR [50], PiCANet [51], SRM [16], DGRL [32], MLMS [52], AFNet [53], CapSal [54], BASNet [15], and CPD [55]. For a fair comparison, we use the saliency maps provided by the authors.…”

Section: Comparison With the State-of-the-artmentioning

confidence: 99%

“…The unit of the total number of parameters (denoted as #Par) is million. Note that the authors of [50] did not release the code, and they just provided the saliency maps, and thus reporting the total number of parameters is not possible for this method. (RRM).…”

Section: Ablation Analysismentioning

confidence: 99%

CAGNet: Content-Aware Guidance for Salient Object Detection

Mohammadi

Noori

Bahri

et al. 2020

Pattern Recognition

109

View full text Add to dashboard Cite

Beneficial from Fully Convolutional Neural Networks (FCNs), saliency detection methods have achieved promising results. However, it is still challenging to learn effective features for detecting salient objects in complicated scenarios, in which i) non-salient regions may have "salient-like" appearance; ii) the salient objects may have differentlooking regions. To handle these complex scenarios, we propose a Feature Guide Network which exploits the nature of low-level and high-level features to i) make foreground and background regions more distinct and suppress the non-salient regions which have "salient-like" appearance; ii) assign foreground label to different-looking salient regions.Furthermore, we utilize a Multi-scale Feature Extraction Module (MFEM) for each level of abstraction to obtain multi-scale contextual information. Finally, we design a loss function which outperforms the widely-used Cross-entropy loss. By adopting four different pre-trained models as the backbone, we prove that our method is very general with respect to the choice of the backbone model. Experiments on five challenging datasets demonstrate that our method achieves the state-of-the-art performance in terms of different evaluation metrics. Additionally, our approach contains fewer parameters than the existing ones, does not need any post-processing, and runs fast at a real-time speed of 28 FPS when processing a 480 × 480 image.

show abstract

“…We compare the proposed saliency detection method against previous 18 state-of-the-art methods, namely, MDF [13], RFCN [31], DHS [32], UCF [46], Amulet [34], NLDF [47], DSS [48], RAS [49], BMPM [33], PAGR [50], PiCANet [51], SRM [18], DGRL [17], MLMS [52], AFNet [53], CapSal [54], BASNet [55], and CPD [16]. We perform comparisons on five challenging datasets.…”

Section: Comparison With the State-of-the-artmentioning

confidence: 99%

“…The unit of the total number of parameters (denoted as #Par) is million. Note that the authors of[50] did not release the code, and they just provided the saliency maps, and thus reporting the total number of parameters is not possible for this method.…”

mentioning

confidence: 99%

DFNet: Discriminative feature extraction and integration network for salient object detection

Noori

Mohammadi

Majelan

et al. 2020

Engineering Applications of Artificial Intelligence

View full text Add to dashboard Cite

Despite the powerful feature extraction capability of Convolutional Neural Networks, there are still some challenges in saliency detection. In this paper, we focus on two aspects of challenges: i) Since salient objects appear in various sizes, using single-scale convolution would not capture the right size. Moreover, using multi-scale convolutions without considering their importance may confuse the model. ii) Employing multilevel features helps the model use both local and global context. However, treating all features equally results in information redundancy. Therefore, there needs to be a mechanism to intelligently select which features in different levels are useful. To address the first challenge, we propose a Multi-scale Attention Guided Module. This module not only extracts multi-scale features effectively but also gives more attention to more discriminative feature maps corresponding to the scale of the salient object. To address the second challenge, we propose an Attention-based Multi-level Integrator Module to give the model the ability to assign different weights to multi-level feature maps. Furthermore, our Sharpening Loss function guides our network to output saliency maps with higher certainty and less blurry salient objects, and it has far better performance than the Cross-entropy loss. For the first time, we adopt four different backbones to show the generalization of our method. Experiments on five challenging datasets prove that our method achieves the state-of-the-art performance. Our approach is fast as well and can run at a real-time speed.

show abstract

Progressive Attention Guided Recurrent Network for Salient Object Detection

Cited by 596 publications

References 25 publications

Salient instance segmentation via subitizing and clustering

Salient instance segmentation via subitizing and clustering

CAGNet: Content-Aware Guidance for Salient Object Detection

DFNet: Discriminative feature extraction and integration network for salient object detection

Contact Info

Product

Resources

About