Towards the Success Rate of One: Real-Time Unconstrained Salient Object Detection

  title={Towards the Success Rate of One: Real-Time Unconstrained Salient Object Detection},
  author={Mahyar Najibi and Fan Yang and Qiaosong Wang and Robinson Piramuthu},
  journal={2018 IEEE Winter Conference on Applications of Computer Vision (WACV)},
In this work, we propose an efficient and effective approach for unconstrained salient object detection in images using deep convolutional neural networks. Instead of generating thousands of candidate bounding boxes and refining them, our network directly learns to generate the saliency map containing the exact number of salient objects. During training, we convert the ground-truth rectangular boxes to Gaussian distributions that better capture the ROI regarding individual salient objects… Expand
Salient Object Detection in Video using Deep Non-Local Neural Networks
Revisiting Salient Object Detection: Simultaneous Detection, Ranking, and Subitizing of Multiple Salient Objects
Salient Object Ranking with Position-Preserved Attention
Relative Saliency and Ranking: Models, Metrics, Data and Benchmarks
AutoFocus: Efficient Multi-Scale Inference
Detecting Lesion Bounding Ellipses With Gaussian Proposal Networks
  • Y. Li
  • Computer Science
  • 2019
Image aesthetic assessment using a saliency symbiosis network


Unconstrained Salient Object Detection via Proposal Subset Optimization
Looking Beyond the Image: Unsupervised Learning for Object Saliency and Detection
You Only Look Once: Unified, Real-Time Object Detection
Scalable Object Detection Using Deep Neural Networks
SSD: Single Shot MultiBox Detector
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
DHSNet: Deep Hierarchical Saliency Network for Salient Object Detection
  • Nian Liu, Junwei Han
  • Computer Science
  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
Saliency detection by multi-context deep learning
Salient Object Detection: A Discriminative Regional Feature Integration Approach