Proceedings ArticleDOI
Deep Level Sets for Salient Object Detection
Ping Hu,Bing Shuai,Jun Liu,Gang Wang +3 more
- pp 540-549
Reads0
Chats0
TLDR
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.Abstract:
Deep learning has been applied to saliency detection in recent years. The superior performance has proved that deep networks can model the semantic properties of salient objects. Yet it is difficult for a deep network to discriminate pixels belonging to similar receptive fields around the object boundaries, thus deep networks may output maps with blurred saliency and inaccurate boundaries. To tackle such an issue, in this work, we propose a deep Level Set network to produce compact and uniform saliency maps. Our method drives the network to learn a Level Set function for salient objects so it can output more accurate boundaries and compact saliency. Besides, to propagate saliency information among pixels and recover full resolution saliency map, we extend a superpixel-based guided filter to be a layer in the network. The proposed network has a simple structure and is trained end-to-end. During testing, the network can produce saliency maps by efficiently feedforwarding testing images at a speed over 12FPS on GPUs. Evaluations on benchmark datasets show that the proposed method achieves state-of-the-art performance.read more
Citations
More filters
Book ChapterDOI
Active Contour Model in Deep Learning Era: A Revise and Review
T. Hoang Ngan Le,Khoa Luu,Chi Nhan Duong,Kha Gia Quach,Thanh-Dat Truong,Kyle Sadler,Marios Savvides +6 more
TL;DR: A fundamental of both Active Contour techniques and Deep Learning framework is provided and the state-of-the-art approaches of Active Contours incorporating in Deep learning framework are presented.
Journal ArticleDOI
An automatic feature construction method for salient object detection: A genetic programming approach
TL;DR: A new automatic feature construction method using Genetic Programming (GP) to construct informative high-level saliency features for SOD that achieves consistently high performance compared to twelve state-of-the-art SOD methods.
Journal ArticleDOI
Depth scale balance saliency detection with connective feature pyramid and edge guidance
Zhenshan Tan,Xiaodong Gu +1 more
TL;DR: Scale Balance Network (SBN) based on fully convolutional network is proposed to accurately recognize and comprehensively detect salient objects and a novel progressive pyramid mechanism named Connective Feature Pyramid Module (CFPM), aiming to make the network focus on the balance between the large salient areas and the small ones.
Proceedings ArticleDOI
Saliency Detection Using Fully Convolutional Network
Jianhuan Wei,Baojiang Zhong +1 more
TL;DR: A sophisticated saliency detection method based on a fully convolutional network is proposed, by which an initial saliency map of the input image is yielded and the accuracy of object boundaries is improved by using the fully connected conditional random field.
Posted Content
LevelSet R-CNN: A Deep Variational Method for Instance Segmentation
TL;DR: LevelSet R-CNN is proposed, which combines the best of both worlds by obtaining powerful feature representations that are combined in an end-to-end manner with a variational segmentation framework.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Proceedings ArticleDOI
Densely Connected Convolutional Networks
TL;DR: DenseNet as mentioned in this paper proposes to connect each layer to every other layer in a feed-forward fashion, which can alleviate the vanishing gradient problem, strengthen feature propagation, encourage feature reuse, and substantially reduce the number of parameters.
Book
Partial Differential Equations
TL;DR: In this paper, the authors present a theory for linear PDEs: Sobolev spaces Second-order elliptic equations Linear evolution equations, Hamilton-Jacobi equations and systems of conservation laws.