DeepSaliency: Multi-Task Deep Neural Network Model for Salient Object Detection

  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 Yueting Zhuang and Haibin Ling and Jingdong Wang},
  journal={IEEE Transactions on Image Processing},
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… 

MSDNN: Multi-Scale Deep Neural Network for Salient Object Detection

A multi-scale deep neural network (MSDNN) for salient object detection is proposed that significantly outperforms other 12 state-of-the-art approaches and investigates a fusion convolution module (FCM) to build a final pixel level saliency map.

Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detection

Amulet is presented, a generic aggregating multi-level convolutional feature framework for salient object detection that provides accurate salient object labeling and performs favorably against state-of-the-art approaches in terms of near all compared evaluation metrics.

Deep Salient Object Detection by Integrating Multi-level Cues

A fully convolutional neural network based approach empowered with multi-level fusion to salient object detection empowered with super-pixel level coherency in saliency is exploited and outperforms the state-of-the-art approaches.

Integrated deep and shallow networks for salient object detection

This paper takes results of unsupervised saliency and normalized color images as inputs, and directly learns an end-to-end mapping between inputs and the corresponding saliency maps to obtain a spatially consistent saliency map with sharp object boundaries.

Contrast-Oriented Deep Neural Networks for Salient Object Detection

  • Guanbin LiYizhou Yu
  • Computer Science
    IEEE Transactions on Neural Networks and Learning Systems
  • 2018
This paper develops hybrid contrast-oriented deep neural networks that can significantly outperform the state of the art in terms of all popular evaluation metrics.

Deep Sub-Region Network for Salient Object Detection

A novel deep sub-region network equipped with a sequence of sub- Region dilated blocks (SRDB) by aggregating multi-scale salient context information of multiple sub-regions, such that the global context information from the whole image and local contexts from sub-Regions are fused together, making the saliency prediction more accurate.

Hierarchical Salient Object Detection Network with Dense Connections

This work proposes a novel pixel-wise salient object detection network based on FCN by aggregating multi-level feature maps and introduces skip-layer structure for providing a better feature representation and helping shallow side outputs locate salient objects.

Attention to the Scale: Deep Multi-Scale Salient Object Detection

This paper investigates how different scales of context information affect the performance of salient object detection by building an attention-to-scale model and a saliency fusion stage on a pyramid spatial pooling network.



Saliency detection by multi-context deep learning

This paper proposes a multi-context deep learning framework for salient object detection that employs deep Convolutional Neural Networks to model saliency of objects in images and investigates different pre-training strategies to provide a better initialization for training the deep neural networks.

Visual saliency based on multiscale deep features

  • Guanbin LiYizhou Yu
  • Computer Science
    2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2015
This paper discovers that a high-quality visual saliency model can be learned from multiscale features extracted using deep convolutional neural networks (CNNs), which have had many successes in visual recognition tasks.

Deep networks for saliency detection via local estimation and global search

This method presents two interesting insights: first, local features learned by a supervised scheme can effectively capture local contrast, texture and shape information for saliency detection and second, the complex relationship between different global saliency cues can be captured by deep networks and exploited principally rather than heuristically.

Salient Object Detection: A Discriminative Regional Feature Integration Approach

This paper presents a principled extension, supervised feature integration, which learns a random forest regressor to discriminatively integrate the saliency features for saliency computation and significantly outperforms state-of-the-art methods on seven benchmark datasets.

SALICON: Reducing the Semantic Gap in Saliency Prediction by Adapting Deep Neural Networks

This paper presents a focused study to narrow the semantic gap with an architecture based on Deep Neural Network (DNN), which leverages the representational power of high-level semantics encoded in DNNs pretrained for object recognition.

Fusing generic objectness and visual saliency for salient object detection

Experimental results on two benchmark datasets demonstrate that the proposed model can simultaneously yield a saliency map of better quality and a more meaningful objectness output for salient object detection.

A unified approach to salient object detection via low rank matrix recovery

  • Xiaohui ShenYing Wu
  • Computer Science
    2012 IEEE Conference on Computer Vision and Pattern Recognition
  • 2012
A unified model to incorporate traditional low-level features with higher-level guidance to detect salient objects and can be considered as a prototype framework not only for general salient object detection, but also for potential task-dependent saliency applications.

Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs

This work brings together methods from DCNNs and probabilistic graphical models for addressing the task of pixel-level classification by combining the responses at the final DCNN layer with a fully connected Conditional Random Field (CRF).

Hierarchical Saliency Detection

This work tackles saliency detection from a scale point of view and proposes a multi-layer approach to analyze saliency cues, by finding saliency values optimally in a tree model.

Fully convolutional networks for semantic segmentation

The key insight is to build “fully convolutional” networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning.