Visual Saliency Detection via Kernelized Subspace Ranking With Active Learning

Zhang, Lihe; Sun, Jiayu; Wang, Tiantian; Min, Yifan; Lu, Huchuan

doi:10.1109/tip.2019.2945679

Cited by 16 publications

(2 citation statements)

References 74 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SF (Supervision by Fusion) [34], DCL (Deep Contrast Learning) [35], MC (Multi-context Deep Learning) [36], MTDS (Multi-Task Deep Neural Network) [26], ELD (Encoded Low Level Distance Map and High Level Features) [37], LEGS (Local Estimation and Global Search) [21], MDF (Multi-scale deep CNN Features) [38], KSR (Kernelized Subspace Ranking) [39], DRFI (Discriminative Regional Feature Integration) [40], SMD (Structured Matrix Decomposition) [41] and RR (Regularized Random Walks ranking) [42]. For equitable comparison, the saliency results of compared model are provided by the authors.…”

Section: Comparison Of Performancementioning

confidence: 99%

A new frog leaping algorithm-oriented fully convolutional neural network for dance motion object saliency detection

Lyu

Zhang

2022

COMSIS J

View full text Add to dashboard Cite

Image saliency detection is an important research topic in the field of computer vision. With the traditional saliency detection models, the texture detail s are not obvious and the edge contour is not complete. The accuracy and recall rate of object detection are low, which are mostly based on the manual features and prior information. With the rise of deep convolutional neural networks, saliency detection has been rapidly developed. However, the existing saliency methods still have some common shortcomings, and it is difficult to uniformly highlight the clear boundary and internal region of the whole object in complex images, mainly because of the lack of sufficient and rich features. In this paper, a new frog leaping algorithm-oriented fully convolutional neural network is proposed for dance motion object saliency detection. The VGG (Visual Geometry Group) model is improved. The final full connection layer is removed, and the jump connection layer is used for the saliency prediction, which can effectively combine the multi-scale information from different convolution layers in the convolutional neural network. Meanwhile, an improved frog leaping algorithm is used to optimize the selection of initial weights during network initialization. In the process of network iteration, the forward propagation loss of convolutional neural network is calculated, and the anomaly weight is corrected by using the improved frog leaping algorithm. When the network satisfies the terminal conditions, the final weight is optimized by one frog leaping to make the network weight further optimization. In addition, the new network can combine high-level semantic information and low-level detail information in a data-driven framework. In order to preserve the unity of the object boundary and inner region effectively, the fully connected conditional random field (CRF) model is used to adjust the obtained saliency feature map. In this paper, the precision recall (PR) curve, F-measure, maximum F-measure, weighted F-measure and mean absolute error (MAE) are tested on six widely used public data sets. Com pared with other most advanced and representative methods, the results show that the proposed method achieves better performance and it is superior to most representative methods. The presented method reveals that it has strong robustness for image saliency detection with various scenes, and can make the boundary and inner region of the saliency object more uniform and the detection results more accurate.

show abstract

Section: Comparison Of Performancementioning

confidence: 99%

A new frog leaping algorithm-oriented fully convolutional neural network for dance motion object saliency detection

Lyu

Zhang

2022

COMSIS J

View full text Add to dashboard Cite

show abstract

“…In this paper, we will mainly focus on developing robust learning algorithm to detect salient objects from complex scenes. Extensive works can be found in the literature to address this problem [13]- [15], but the performance in open-world scenarios still needs further improvement. It is usually difficult to learn a universal model from limited prior knowledge suitable for diversified situations.…”

Section: Introductionmentioning

confidence: 99%

Joint Learning of Discriminative Metric Space From Multi-Context Visual Scene for Unsupervised Salient Object Detection

Wang

2022

IEEE Access

View full text Add to dashboard Cite

Mimicking the biological visual attention mechanism to discriminate visually appealing regions in natural scenes has been a hot research topic in recent years. However, designing computational models with self-driven capability for open world scenarios remains a challenging task which deserves to be further studied. In this paper, we propose an unsupervised learning approach to detect salient objects from images by fully exploiting the multi-context semantic information of the scenes. Specifically, a selfdriven model combing the idea of discriminative metric learning and structured sparse constraint is designed to find an optimal semantic mapping space for robust scene specific saliency prediction from complex environments. Meanwhile, a heuristic alternating optimization algorithm is developed to remove the ambiguity in the coarse geometric prior to generate a fine-grained discriminative model for saliency. On the basis of this, multi-context visual scenes are jointly modeled and fused to capture the image hierarchical structures for high-quality saliency map generation. Finally, we conduct experiments to verify the effectiveness of the proposed approach on four saliency benchmark datasets and compare it with 18 stateof-the-art saliency detection methods. Both qualitative saliency map and quantitative numerical index results indicate that our method has superior detection performance than the other counterparts under diversified scenes. Also, the proposed approach is applied to model wide synthetic aperture radar images for rapid target detection and promising results are obtained.INDEX TERMS Heuristic alternating optimization, salient object detection (SOD), SAR target detection, unsupervised learning.

show abstract

Over-sampling strategy-based class-imbalanced salient object detection and its application in underwater scene

Pang

et al. 2022

Vis Comput

View full text Add to dashboard Cite

Visual Saliency Detection via Kernelized Subspace Ranking With Active Learning

Cited by 16 publications

References 74 publications

A new frog leaping algorithm-oriented fully convolutional neural network for dance motion object saliency detection

A new frog leaping algorithm-oriented fully convolutional neural network for dance motion object saliency detection

Joint Learning of Discriminative Metric Space From Multi-Context Visual Scene for Unsupervised Salient Object Detection

Over-sampling strategy-based class-imbalanced salient object detection and its application in underwater scene

Contact Info

Product

Resources

About