Multiscale Fully Convolutional DenseNet for Semantic Segmentation

In the computer vision field, semantic segmentation represents a very interesting task. Convolutional Neural Network methods have shown their great performances in comparison with other semantic segmentation methods. In this paper, we propose a multiscale fully convolutional DenseNet approach for semantic segmentation. Our approach is based on the successful fully convolutional DenseNet method. It is reinforced by integrating a multiscale kernel prediction after the last dense block which performs model averaging over different spatial scales and provides more flexibility of our network to presume more information. Experiments on two semantic segmentation benchmarks: CamVid and Cityscapes have shown the effectiveness of our approach which has outperformed many recent works.

[1]  Haytham Elghazel,et al.  Graph modeling based video event detection , 2011, 2011 International Conference on Innovations in Information Technology.

[2]  Chokri Ben Amar,et al.  Graph Aggregation Based Image Modeling and Indexing for Video Annotation , 2011, CAIP.

[3]  Iasonas Kokkinos,et al.  DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Jian Sun,et al.  Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[5]  Eugenio Culurciello,et al.  ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation , 2016, ArXiv.

[6]  Yoshua Bengio,et al.  ReNet: A Recurrent Neural Network Based Alternative to Convolutional Networks , 2015, ArXiv.

[7]  Anton van den Hengel,et al.  Wider or Deeper: Revisiting the ResNet Model for Visual Recognition , 2016, Pattern Recognit..

[8]  Vladlen Koltun,et al.  Multi-Scale Context Aggregation by Dilated Convolutions , 2015, ICLR.

[9]  Chokri Ben Amar,et al.  Improved Very Deep Recurrent Convolutional Neural Network for Object Recognition , 2018, SMC.

[10]  Chokri Ben Amar,et al.  Multiresolution motion estimation and compensation for video coding , 2010, IEEE 10th INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING PROCEEDINGS.

[11]  Yoshua Bengio,et al.  The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[12]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Roberto Cipolla,et al.  Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding , 2015, BMVC.

[14]  Sebastian Ramos,et al.  The Cityscapes Dataset , 2015, CVPR 2015.

[15]  Yoshua Bengio,et al.  ReSeg: A Recurrent Neural Network-Based Model for Semantic Segmentation , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[16]  Chokri Ben Amar,et al.  Facial expression recognition based on a mlp neural network using constructive training algorithm , 2014, Multimedia Tools and Applications.

[17]  Bertrand Le Saux,et al.  Semantic Segmentation of Earth Observation Data Using Multimodal and Multi-scale Deep Networks , 2016, ACCV.

[18]  Andreas Geiger,et al.  Augmented Reality meets Deep Learning , 2017, BMVC.

[19]  Chokri Ben Amar,et al.  Indexing and images retrieval by content , 2011, 2011 International Conference on High Performance Computing & Simulation.

[20]  Roberto Cipolla,et al.  Semantic object classes in video: A high-definition ground truth database , 2009, Pattern Recognit. Lett..

[21]  B. S. Manjunath,et al.  Weakly Supervised Graph Based Semantic Segmentation by Learning Communities of Image-Parts , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[22]  Wenbin Zou,et al.  Semantic segmentation via sparse coding over hierarchical regions , 2012, 2012 19th IEEE International Conference on Image Processing.

[23]  Wen-June Wang,et al.  Learning based semantic segmentation for robot navigation in outdoor environment , 2017, 2017 Joint 17th World Congress of International Fuzzy Systems Association and 9th International Conference on Soft Computing and Intelligent Systems (IFSA-SCIS).

[24]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[25]  Chokri Ben Amar,et al.  A New System for Event Detection from Video Surveillance Sequences , 2010, ACIVS.

[26]  Roberto Cipolla,et al.  SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[27]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[28]  Chokri Ben Amar,et al.  Graph-based approach for human action recognition using spatio-temporal features , 2014, J. Vis. Commun. Image Represent..

[29]  Ji Wan,et al.  Deep Learning for Content-Based Image Retrieval: A Comprehensive Study , 2014, ACM Multimedia.

[30]  Sheng Zeng,et al.  Semantic Segmentation Using Multiple Graphs with Block-Diagonal Constraints , 2014, AAAI.

[31]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[32]  Chokri Ben Amar,et al.  Wavelet Transform Based Motion Estimation and Compensation for Video Coding , 2012 .

[33]  Chokri Ben Amar,et al.  Bag of frequent subgraphs approach for image classification , 2015, Intell. Data Anal..

[34]  José García Rodríguez,et al.  A Review on Deep Learning Techniques Applied to Semantic Segmentation , 2017, ArXiv.

[35]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.