DeepSaliency: Multi-Task Deep Neural Network Model for Salient Object Detection
@article{Li2016DeepSaliencyMD, title={DeepSaliency: Multi-Task Deep Neural Network Model for Salient Object Detection}, author={Xi Li and Liming Zhao and Lina Wei and Ming-Hsuan Yang and Fei Wu and Y. Zhuang and Haibin Ling and Jingdong Wang}, journal={IEEE Transactions on Image Processing}, year={2016}, volume={25}, pages={3919-3930} }
A key problem in salient object detection is how to effectively model the semantic properties of salient objects in a data-driven manner. In this paper, we propose a multi-task deep saliency model based on a fully convolutional neural network with global input (whole raw images) and global output (whole saliency maps). In principle, the proposed saliency model takes a data-driven strategy for encoding the underlying saliency prior information, and then sets up a multi-task learning scheme for… CONTINUE READING
Figures, Tables, and Topics from this paper
374 Citations
Multi-Path Feature Fusion Network for Saliency Detection
- Computer Science
- 2018 IEEE International Conference on Multimedia and Expo (ICME)
- 2018
- 1
- PDF
Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detection
- Computer Science
- 2017 IEEE International Conference on Computer Vision (ICCV)
- 2017
- 353
- PDF
Deep Salient Object Detection by Integrating Multi-level Cues
- Computer Science
- 2017 IEEE Winter Conference on Applications of Computer Vision (WACV)
- 2017
- 13
- Highly Influenced
- PDF
Integrated deep and shallow networks for salient object detection
- Computer Science
- 2017 IEEE International Conference on Image Processing (ICIP)
- 2017
- 9
- Highly Influenced
- PDF
Attentive feature integration network for detecting salient objects in images
- Computer Science
- Neurocomputing
- 2020
Multi-level and multi-scale deep saliency network for salient object detection
- Computer Science
- J. Vis. Commun. Image Represent.
- 2019
- 2
Contrast-Oriented Deep Neural Networks for Salient Object Detection
- Computer Science, Medicine
- IEEE Transactions on Neural Networks and Learning Systems
- 2018
- 52
- PDF
Attention to the Scale: Deep Multi-Scale Salient Object Detection
- Computer Science
- 2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA)
- 2017
- 2
- Highly Influenced
References
SHOWING 1-10 OF 64 REFERENCES
Saliency detection by multi-context deep learning
- Computer Science
- 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- 2015
- 659
- PDF
Visual saliency based on multiscale deep features
- Computer Science
- 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- 2015
- 673
- PDF
Deep networks for saliency detection via local estimation and global search
- Computer Science
- 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- 2015
- 452
- PDF
Salient Object Detection: A Discriminative Regional Feature Integration Approach
- Computer Science
- 2013 IEEE Conference on Computer Vision and Pattern Recognition
- 2013
- 781
- PDF
SALICON: Reducing the Semantic Gap in Saliency Prediction by Adapting Deep Neural Networks
- Computer Science
- 2015 IEEE International Conference on Computer Vision (ICCV)
- 2015
- 360
- PDF
Fusing generic objectness and visual saliency for salient object detection
- Computer Science
- 2011 International Conference on Computer Vision
- 2011
- 344
- Highly Influential
- PDF
A unified approach to salient object detection via low rank matrix recovery
- Mathematics, Computer Science
- 2012 IEEE Conference on Computer Vision and Pattern Recognition
- 2012
- 661
- Highly Influential
- PDF
Deep Gaze I: Boosting Saliency Prediction with Feature Maps Trained on ImageNet
- Computer Science, Biology
- ICLR
- 2015
- 267
- PDF
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Computer Science, Medicine
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- 2015
- 21,124
- PDF
Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
- Computer Science
- ICLR
- 2015
- 2,615
- PDF