• Corpus ID: 235377107

Salient Object Ranking with Position-Preserved Attention

  title={Salient Object Ranking with Position-Preserved Attention},
  author={Haoyang Fang and Daoxin Zhang and Yi Zhang and Minghao Chen and Jiawei Li and Yao Hu and Deng Cai and Xiaofei He},
Instance segmentation can detect where the objects are in an image, but hard to understand the relationship between them. We pay attention to a typical relationship, relative saliency. A closely related task, salient object detection, predicts a binary map highlighting a visually salient region while hard to distinguish multiple objects. Directly combining two tasks by post-processing also leads to poor performance. There is a lack of research on relative saliency at present, limiting the… 

Figures and Tables from this paper


Revisiting Salient Object Detection: Simultaneous Detection, Ranking, and Subitizing of Multiple Salient Objects
A novel deep learning solution is proposed based on a hierarchical representation of relative saliency and stage-wise refinement, and it is shown that the problem of salient object subitizing can be addressed with the same network.
Ranking Video Salient Object Detection
This paper proposes a completely new definition for the salient objects in videos---ranking salient objects, which considers relative saliency ranking assisted with eye fixation points and builds a ranking video salient object dataset (RVSOD).
Non-local Deep Features for Salient Object Detection
A simplified convolutional neural network which combines local and global information through a multi-resolution 4×5 grid structure is proposed which implements a loss function inspired by the Mumford-Shah functional which penalizes errors on the boundary, enabling near real-time, high performance saliency detection.
Inferring Attention Shift Ranks of Objects for Image Saliency
This paper proposes a learning-based CNN to leverage both bottom-up and top-down attention mechanisms to predict the saliency rank, and achieves state-of-the-art performances on salient object rank prediction.
Deep Level Sets for Salient Object Detection
This work proposes a deep Level Set network to produce compact and uniform saliency maps and drives the network to learn a Level Set function for salient objects so it can output more accurate boundaries and compact saliency.
A Stagewise Refinement Model for Detecting Salient Objects in Images
This work proposes to augment feedforward neural networks with a novel pyramid pooling module and a multi-stage refinement mechanism for saliency detection and shows that the proposed method compares favorably against the state-of-the-art approaches.
Unconstrained Salient Object Detection via Proposal Subset Optimization
A salient object detection system that directly outputs a compact set of detection windows, if any, for an input image, that leverages a Convolutional-Neural-Network model to generate location proposals of salient objects.
Stacked Cross Refinement Network for Edge-Aware Salient Object Detection
This framework aims to simultaneously refine multi-level features of salient object detection and edge detection by stacking Cross Refinement Unit (CRU), which outperforms existing state-of-the-art algorithms in both accuracy and efficiency.
Deeply Supervised Salient Object Detection with Short Connections
A new saliency method is proposed by introducing short connections to the skip-layer structures within the HED architecture, which produces state-of-the-art results on 5 widely tested salient object detection benchmarks, with advantages in terms of efficiency, effectiveness, and simplicity over the existing algorithms.
Towards the Success Rate of One: Real-Time Unconstrained Salient Object Detection
This work proposes an efficient and effective approach for unconstrained salient object detection in images using deep convolutional neural networks, which performs saliency map prediction without pixel-level annotations, salient object Detection without object proposals, and salient object subitizing simultaneously, all in a single pass within a unified framework.