A Novel Image Tag Completion Method Based on Convolutional Neural Transformation

In the problems of image retrieval and annotation, complete textual tag lists of images play critical roles. However, in real-world applications, the image tags are usually incomplete, thus it is important to learn the complete tags for images. In this paper, we study the problem of image tag complete and proposed a novel method for this problem based on a popular image representation method, convolutional neural network (CNN). The method estimates the complete tags from the convolutional filtering outputs of images based on a linear predictor. The CNN parameters, linear predictor, and the complete tags are learned jointly by our method. We build a minimization problem to encourage the consistency between the complete tags and the available incomplete tags, reduce the estimation error, and reduce the model complexity. An iterative algorithm is developed to solve the minimization problem. Experiments over benchmark image data sets show its effectiveness.

[1]  Pin Zhang,et al.  Detecting Image Tampering Using Feature Fusion , 2009, 2009 International Conference on Availability, Reliability and Security.

[2]  Huafeng Liu,et al.  A convex neighbor-constrained active contour model for image segmentation , 2010, 2010 IEEE International Conference on Image Processing.

[3]  Wei Cai,et al.  Optimization of a GPU Implementation of Multi-Dimensional RF Pulse Design Algorithm , 2011, 2011 5th International Conference on Bioinformatics and Biomedical Engineering.

[4]  Ruofeng Tong,et al.  Connectivity-Based Segmentation for GPU-Accelerated Mesh Decompression , 2012, Journal of Computer Science and Technology.

[5]  Jianmin Wang,et al.  Image Tag Completion via Image-Specific and Tag-Specific Linear Sparse Reconstructions , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[6]  Lei Wu,et al.  Tag Completion for Image Retrieval , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Shuzhi Sam Ge,et al.  Image tag completion via dual-view linear sparse reconstructions , 2014, Comput. Vis. Image Underst..

[8]  Spyros Kotoulas,et al.  Robust and Efficient Large-Large Table Outer Joins on Distributed Infrastructures , 2014, Euro-Par.

[9]  Jun Wang,et al.  Doubly Regularized Portfolio with Risk Minimization , 2014, AAAI.

[10]  Rong Jin,et al.  Image Tag Completion by Noisy Matrix Recovery , 2014, ECCV.

[11]  Spyros Kotoulas,et al.  Robust and Skew-resistant Parallel Joins in Shared-Nothing Systems , 2014, CIKM.

[12]  Jianping Fan,et al.  A regularized optimization framework for tag completion and image retrieval , 2015, Neurocomputing.

[13]  Tao Mei,et al.  Relaxing from Vocabulary: Robust Weakly-Supervised Deep Learning for Vocabulary-Free Image Tagging , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[14]  Jun Wang,et al.  Transaction Costs-Aware Portfolio Optimization via Fast Lowner-John Ellipsoid Approximation , 2015, AAAI.

[15]  John J. Squiers,et al.  Burn injury diagnostic imaging device's accuracy improved by outlier detection and removal , 2015, Defense + Security Symposium.

[16]  Xiaohong Yang,et al.  Completing tags by local learning: a novel image tag completion method based on neighborhood tag vector predictor , 2016, Neural Computing and Applications.

[17]  Jeffrey E. Thatcher,et al.  Outlier detection and removal improves accuracy of machine learning approach to multispectral burn diagnostic imaging , 2015, Journal of biomedical optics.

[18]  Jeffrey E. Thatcher,et al.  Surgical wound debridement sequentially characterized in a porcine burn model with multispectral imaging. , 2015, Burns : journal of the International Society for Burn Injuries.

[19]  Rachit Mohan,et al.  The importance of illumination in a non-contact photoplethysmography imaging system for burn wound assessment , 2015, Photonics West - Biomedical Optics.

[20]  Jun Wang,et al.  Portfolio Choices with Orthogonal Bandit Learning , 2015, IJCAI.

[21]  Zonghua Li,et al.  Nuclear norm regularized convolutional Max Pos@Top machine , 2016, Neural Computing and Applications.

[22]  Jundong Liu,et al.  Nonlinear Metric Learning for Semi-Supervised Learning via Coherent Point Drifting , 2016, 2016 15th IEEE International Conference on Machine Learning and Applications (ICMLA).

[23]  Yi Gu,et al.  Optimizing top precision performance measure of content-based image retrieval by learning similarity function , 2016, 2016 23rd International Conference on Pattern Recognition (ICPR).

[24]  Jeffrey E. Thatcher,et al.  Multispectral and Photoplethysmography Optical Imaging Techniques Identify Important Tissue Characteristics in an Animal Model of Tangential Burn Excision , 2016, Journal of burn care & research : official publication of the American Burn Association.

[25]  Min Tan,et al.  Robust object recognition via weakly supervised metric and template learning , 2016, Neurocomputing.

[26]  Jundong Liu,et al.  Quad-mesh based radial distance biomarkers for Alzheimer's disease , 2016, 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI).

[27]  Weizhi Li,et al.  A Novel Transfer Learning Method Based on Common Space Mapping and Weighted Domain Matching , 2016, 2016 IEEE 28th International Conference on Tools with Artificial Intelligence (ICTAI).

[28]  Xue Li,et al.  Low-rank image tag completion with dual reconstruction structure preserved , 2016, Neurocomputing.

[29]  Cheng Li,et al.  LOW POWER SI-BASED POWER AMPLIFIER FOR HEALTHCARE APPLICATION , 2016 .

[30]  Wei Cai,et al.  2.4GHZ Class AB power Amplifier For Healthcare Application , 2016, ArXiv.

[31]  Jun Wang,et al.  Portfolio Blending via Thompson Sampling , 2016, IJCAI.

[32]  Edilson de Aguiar,et al.  Facial expression recognition with Convolutional Neural Networks: Coping with few data and the training sample order , 2017, Pattern Recognit..

[33]  Jim Jing-Yan Wang,et al.  Learning convolutional neural network to maximize Pos@Top performance measure , 2016, ESANN.

[34]  Jun Wang,et al.  Portfolio Selection via Subset Resampling , 2017, AAAI.

[35]  Jinlian Ma,et al.  A pre‐trained convolutional neural network based method for thyroid nodule diagnosis , 2017, Ultrasonics.

[36]  Qianjin Feng,et al.  Cascade of multi-scale convolutional neural networks for bone suppression of chest radiographs in gradient domain , 2017, Medical Image Anal..

[37]  Jundong Liu,et al.  Nonlinear feature transformation and deep fusion for Alzheimer's Disease staging analysis , 2017, Pattern Recognit..