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
Journal ArticleDOI
Saliency Consistency-Based Image Re-Colorization for Color Blindness
Jinjiang Li,Xiaomei Feng,Hui Fan +2 more
TL;DR: A saliency consistency-based image re-colorization for color blindness using image retrieval methods and co-saliency methods to detect salient areas of standard color images and color-blind simulated images is proposed.
Posted Content
Exploring Reciprocal Attention for Salient Object Detection by Cooperative Learning
TL;DR: A novel cooperative attention mechanism that jointly considers reciprocal relationships between background and foreground for efficient salient object detection is proposed that performs favorably against the state-of-the-art approaches in terms of all compared evaluation metrics.
Posted Content
Deep Learning of Unified Region, Edge, and Contour Models for Automated Image Segmentation.
TL;DR: This thesis proposes an end-to-end trainable image segmentation framework that unifies CNNs and active contour models with learnable parameters for fast and robust object delineation, and a novel approach for disentangling edge and texture processing in segmentation networks.
Proceedings ArticleDOI
Learning Chan-Vese
Orhan Akal,Adrian Barbu +1 more
TL;DR: This paper introduces a generalization of the Chan-Vese method to evolve a curve where the regularization is based on a Fully Convolutional Neural Network and shows how to learn the curve model as a Recurrent Neural Network (RNN) using training examples.
Posted ContentDOI
Combining deep learning and active contours opens the way to robust, automated analysis of brain cytoarchitectonics
Konstantin Thierbach,Pierre-Louis Bazin,Walter de Back,Filippos Gavriilidis,Evgeniya Kirilina,Carsten Jaeger,Markus Morawski,Stefan Geyer,Nikolaus Weiskopf,Nico Scherf +9 more
TL;DR: This work presents a modular strategy for the accurate segmentation of neural cell bodies from light-sheet microscopy combining mixed-scale convolutional neural networks and topology-preserving geometric deformable models and shows that the network can be trained efficiently from simple cell centroid annotations.
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.