Paper Group ANR 1503
Deep Learning For Face Recognition: A Critical Analysis. Discriminative Robust Deep Dictionary Learning for Hyperspectral Image Classification. The Seventh Answer Set Programming Competition: Design and Results. Row-Sparse Discriminative Deep Dictionary Learning for Hyperspectral Image Classification. Graph Convolutional Networks: analysis, improve …
Deep Learning For Face Recognition: A Critical Analysis
| Title | Deep Learning For Face Recognition: A Critical Analysis |
| Authors | Andrew Jason Shepley |
| Abstract | Face recognition is a rapidly developing and widely applied aspect of biometric technologies. Its applications are broad, ranging from law enforcement to consumer applications, and industry efficiency and monitoring solutions. The recent advent of affordable, powerful GPUs and the creation of huge face databases has drawn research focus primarily on the development of increasingly deep neural networks designed for all aspects of face recognition tasks, ranging from detection and preprocessing to feature representation and classification in verification and identification solutions. However, despite these improvements, real-time, accurate face recognition is still a challenge, primarily due to the high computational cost associated with the use of Deep Convolutions Neural Networks (DCNN), and the need to balance accuracy requirements with time and resource constraints. Other significant issues affecting face recognition relate to occlusion, illumination and pose invariance, which causes a notable decline in accuracy in both traditional handcrafted solutions and deep neural networks. This survey will provide a critical analysis and comparison of modern state of the art methodologies, their benefits, and their limitations. It provides a comprehensive coverage of both deep and shallow solutions, as they stand today, and highlight areas requiring future development and improvement. This review is aimed at facilitating research into novel approaches, and further development of current methodologies by scientists and engineers, whilst imparting an informative and analytical perspective on currently available solutions to end users in industry, government and consumer contexts. |
| Tasks | Face Recognition |
| Published | 2019-07-12 |
| URL | https://arxiv.org/abs/1907.12739v1 |
| https://arxiv.org/pdf/1907.12739v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-for-face-recognition-a-critical |
| Repo | |
| Framework | |
Discriminative Robust Deep Dictionary Learning for Hyperspectral Image Classification
| Title | Discriminative Robust Deep Dictionary Learning for Hyperspectral Image Classification |
| Authors | Vanika Singhal, Hemant K. Aggarwal, Snigdha Tariyal, Angshul Majumdar |
| Abstract | This work proposes a new framework for deep learning that has been particularly tailored for hyperspectral image classification. We learn multiple levels of dictionaries in a robust fashion. The last layer is discriminative that learns a linear classifier. The training proceeds greedily, at a time a single level of dictionary is learnt and the coefficients used to train the next level. The coefficients from the final level are used for classification. Robustness is incorporated by minimizing the absolute deviations instead of the more popular Euclidean norm. The inbuilt robustness helps combat mixed noise (Gaussian and sparse) present in hyperspectral images. Results show that our proposed techniques outperforms all other deep learning methods Deep Belief Network (DBN), Stacked Autoencoder (SAE) and Convolutional Neural Network (CNN). The experiments have been carried out on benchmark hyperspectral imaging datasets. |
| Tasks | Dictionary Learning, Hyperspectral Image Classification, Image Classification |
| Published | 2019-12-11 |
| URL | https://arxiv.org/abs/1912.10803v1 |
| https://arxiv.org/pdf/1912.10803v1.pdf | |
| PWC | https://paperswithcode.com/paper/discriminative-robust-deep-dictionary |
| Repo | |
| Framework | |
The Seventh Answer Set Programming Competition: Design and Results
| Title | The Seventh Answer Set Programming Competition: Design and Results |
| Authors | Martin Gebser, Marco Maratea, Francesco Ricca |
| Abstract | Answer Set Programming (ASP) is a prominent knowledge representation language with roots in logic programming and non-monotonic reasoning. Biennial ASP competitions are organized in order to furnish challenging benchmark collections and assess the advancement of the state of the art in ASP solving. In this paper, we report on the design and results of the Seventh ASP Competition, jointly organized by the University of Calabria (Italy), the University of Genova (Italy), and the University of Potsdam (Germany), in affiliation with the 14th International Conference on Logic Programming and Non-Monotonic Reasoning (LPNMR 2017). (Under consideration for acceptance in TPLP). |
| Tasks | |
| Published | 2019-04-19 |
| URL | http://arxiv.org/abs/1904.09134v1 |
| http://arxiv.org/pdf/1904.09134v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-seventh-answer-set-programming |
| Repo | |
| Framework | |
Row-Sparse Discriminative Deep Dictionary Learning for Hyperspectral Image Classification
| Title | Row-Sparse Discriminative Deep Dictionary Learning for Hyperspectral Image Classification |
| Authors | Vanika Singhal, Angshul Majumdar |
| Abstract | In recent studies in hyperspectral imaging, biometrics and energy analytics, the framework of deep dictionary learning has shown promise. Deep dictionary learning outperforms other traditional deep learning tools when training data is limited; therefore hyperspectral imaging is one such example that benefits from this framework. Most of the prior studies were based on the unsupervised formulation; and in all cases, the training algorithm was greedy and hence sub-optimal. This is the first work that shows how to learn the deep dictionary learning problem in a joint fashion. Moreover, we propose a new discriminative penalty to the said framework. The third contribution of this work is showing how to incorporate stochastic regularization techniques into the deep dictionary learning framework. Experimental results on hyperspectral image classification shows that the proposed technique excels over all state-of-the-art deep and shallow (traditional) learning based methods published in recent times. |
| Tasks | Dictionary Learning, Hyperspectral Image Classification, Image Classification |
| Published | 2019-12-11 |
| URL | https://arxiv.org/abs/1912.10804v1 |
| https://arxiv.org/pdf/1912.10804v1.pdf | |
| PWC | https://paperswithcode.com/paper/row-sparse-discriminative-deep-dictionary |
| Repo | |
| Framework | |
Graph Convolutional Networks: analysis, improvements and results
| Title | Graph Convolutional Networks: analysis, improvements and results |
| Authors | Ihsan Ullah, Mario Manzo, Mitul Shah, Michael Madden |
| Abstract | In the current era of neural networks and big data, higher dimensional data is processed for automation of different application areas. Graphs represent a complex data organization in which dependencies between more than one object or activity occur. Due to the high dimensionality, this data creates challenges for machine learning algorithms. Graph convolutional networks were introduced to utilize the convolutional models concepts that shows good results. In this context, we enhanced two of the existing Graph convolutional network models by proposing four enhancements. These changes includes: hyper parameters optimization, convex combination of activation functions, topological information enrichment through clustering coefficients measure, and structural redesign of the network through addition of dense layers. We present extensive results on four state-of-art benchmark datasets. The performance is notable not only in terms of lesser computational cost compared to competitors, but also achieved competitive results for three of the datasets and state-of-the-art for the fourth dataset. |
| Tasks | |
| Published | 2019-12-19 |
| URL | https://arxiv.org/abs/1912.09592v1 |
| https://arxiv.org/pdf/1912.09592v1.pdf | |
| PWC | https://paperswithcode.com/paper/graph-convolutional-networks-analysis |
| Repo | |
| Framework | |
Synthetic Augmentation and Feature-based Filtering for Improved Cervical Histopathology Image Classification
| Title | Synthetic Augmentation and Feature-based Filtering for Improved Cervical Histopathology Image Classification |
| Authors | Yuan Xue, Qianying Zhou, Jiarong Ye, L. Rodney Long, Sameer Antani, Carl Cornwell, Zhiyun Xue, Xiaolei Huang |
| Abstract | Cervical intraepithelial neoplasia (CIN) grade of histopathology images is a crucial indicator in cervical biopsy results. Accurate CIN grading of epithelium regions helps pathologists with precancerous lesion diagnosis and treatment planning. Although an automated CIN grading system has been desired, supervised training of such a system would require a large amount of expert annotations, which are expensive and time-consuming to collect. In this paper, we investigate the CIN grade classification problem on segmented epithelium patches. We propose to use conditional Generative Adversarial Networks (cGANs) to expand the limited training dataset, by synthesizing realistic cervical histopathology images. While the synthetic images are visually appealing, they are not guaranteed to contain meaningful features for data augmentation. To tackle this issue, we propose a synthetic-image filtering mechanism based on the divergence in feature space between generated images and class centroids in order to control the feature quality of selected synthetic images for data augmentation. Our models are evaluated on a cervical histopathology image dataset with a limited number of patch-level CIN grade annotations. Extensive experimental results show a significant improvement of classification accuracy from 66.3% to 71.7% using the same ResNet18 baseline classifier after leveraging our cGAN generated images with feature-based filtering, which demonstrates the effectiveness of our models. |
| Tasks | Data Augmentation, Image Classification |
| Published | 2019-07-24 |
| URL | https://arxiv.org/abs/1907.10655v1 |
| https://arxiv.org/pdf/1907.10655v1.pdf | |
| PWC | https://paperswithcode.com/paper/synthetic-augmentation-and-feature-based |
| Repo | |
| Framework | |
Including Physics in Deep Learning – An example from 4D seismic pressure saturation inversion
| Title | Including Physics in Deep Learning – An example from 4D seismic pressure saturation inversion |
| Authors | Jesper Sören Dramsch, Gustavo Corte, Hamed Amini, Colin MacBeth, Mikael Lüthje |
| Abstract | Geoscience data often have to rely on strong priors in the face of uncertainty. Additionally, we often try to detect or model anomalous sparse data that can appear as an outlier in machine learning models. These are classic examples of imbalanced learning. Approaching these problems can benefit from including prior information from physics models or transforming data to a beneficial domain. We show an example of including physical information in the architecture of a neural network as prior information. We go on to present noise injection at training time to successfully transfer the network from synthetic data to field data. |
| Tasks | |
| Published | 2019-04-03 |
| URL | http://arxiv.org/abs/1904.02254v1 |
| http://arxiv.org/pdf/1904.02254v1.pdf | |
| PWC | https://paperswithcode.com/paper/including-physics-in-deep-learning-an-example |
| Repo | |
| Framework | |
Face Recognition in Unconstrained Conditions: A Systematic Review
| Title | Face Recognition in Unconstrained Conditions: A Systematic Review |
| Authors | Andrew Jason Shepley |
| Abstract | Face recognition is a biometric which is attracting significant research, commercial and government interest, as it provides a discreet, non-intrusive way of detecting, and recognizing individuals, without need for the subject’s knowledge or consent. This is due to reduced cost, and evolution in hardware and algorithms which have improved their ability to handle unconstrained conditions. Evidently affordable and efficient applications are required. However, there is much debate over which methods are most appropriate, particularly in the context of the growing importance of deep neural network-based face recognition systems. This systematic review attempts to provide clarity on both issues by organizing the plethora of research and data in this field to clarify current research trends, state-of-the-art methods, and provides an outline of their benefits and shortcomings. Overall, this research covered 1,330 relevant studies, showing an increase of over 200% in research interest in the field of face recognition over the past 6 years. Our results also demonstrated that deep learning methods are the prime focus of modern research due to improvements in hardware databases and increasing understanding of neural networks. In contrast, traditional methods have lost favor amongst researchers due to their inherent limitations in accuracy, and lack of efficiency when handling large amounts of data. |
| Tasks | Face Recognition |
| Published | 2019-07-12 |
| URL | https://arxiv.org/abs/1908.04404v1 |
| https://arxiv.org/pdf/1908.04404v1.pdf | |
| PWC | https://paperswithcode.com/paper/face-recognition-in-unconstrained-conditions |
| Repo | |
| Framework | |
User Preference Prediction in Visual Data on Mobile Devices
| Title | User Preference Prediction in Visual Data on Mobile Devices |
| Authors | A. V. Savchenko, K. V. Demochkin, I. S. Grechikhin |
| Abstract | In this paper we consider the user modeling given the photos and videos from the gallery on a mobile device. We propose the novel user preference prediction engine based on scene understanding, object detection and face recognition. At first, all faces in a gallery are clustered and all private photos and videos with faces from large clusters are processed on the embedded system in offline mode. Other photos are sent to the remote server to be analyzed by very deep models. The visual features of each photo are aggregated into a single user descriptor using the neural attention block. The proposed pipeline is implemented for the Android mobile platform. Experimental results with a subset of Amazon Home and Kitchen, Places2 and Open Images datasets demonstrate the possibility to process images very efficiently without accuracy degradation. |
| Tasks | Face Recognition, Object Detection, Scene Understanding |
| Published | 2019-07-10 |
| URL | https://arxiv.org/abs/1907.04519v1 |
| https://arxiv.org/pdf/1907.04519v1.pdf | |
| PWC | https://paperswithcode.com/paper/user-preference-prediction-in-visual-data-on |
| Repo | |
| Framework | |
A Fine-Grain Error Map Prediction and Segmentation Quality Assessment Framework for Whole-Heart Segmentation
| Title | A Fine-Grain Error Map Prediction and Segmentation Quality Assessment Framework for Whole-Heart Segmentation |
| Authors | Rongzhao Zhang, Albert C. S. Chung |
| Abstract | When introducing advanced image computing algorithms, e.g., whole-heart segmentation, into clinical practice, a common suspicion is how reliable the automatically computed results are. In fact, it is important to find out the failure cases and identify the misclassified pixels so that they can be excluded or corrected for the subsequent analysis or diagnosis. However, it is not a trivial problem to predict the errors in a segmentation mask when ground truth (usually annotated by experts) is absent. In this work, we attempt to address the pixel-wise error map prediction problem and the per-case mask quality assessment problem using a unified deep learning (DL) framework. Specifically, we first formalize an error map prediction problem, then we convert it to a segmentation problem and build a DL network to tackle it. We also derive a quality indicator (QI) from a predicted error map to measure the overall quality of a segmentation mask. To evaluate the proposed framework, we perform extensive experiments on a public whole-heart segmentation dataset, i.e., MICCAI 2017 MMWHS. By 5-fold cross validation, we obtain an overall Dice score of 0.626 for the error map prediction task, and observe a high Pearson correlation coefficient (PCC) of 0.972 between QI and the actual segmentation accuracy (Acc), as well as a low mean absolute error (MAE) of 0.0048 between them, which evidences the efficacy of our method in both error map prediction and quality assessment. |
| Tasks | |
| Published | 2019-07-29 |
| URL | https://arxiv.org/abs/1907.12244v1 |
| https://arxiv.org/pdf/1907.12244v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-fine-grain-error-map-prediction-and |
| Repo | |
| Framework | |
Screening Mammogram Classification with Prior Exams
| Title | Screening Mammogram Classification with Prior Exams |
| Authors | Jungkyu Park, Jason Phang, Yiqiu Shen, Nan Wu, S. Gene Kim, Linda Moy, Kyunghyun Cho, Krzysztof J. Geras |
| Abstract | Radiologists typically compare a patient’s most recent breast cancer screening exam to their previous ones in making informed diagnoses. To reflect this practice, we propose new neural network models that compare pairs of screening mammograms from the same patient. We train and evaluate our proposed models on over 665,000 pairs of images (over 166,000 pairs of exams). Our best model achieves an AUC of 0.866 in predicting malignancy in patients who underwent breast cancer screening, reducing the error rate of the corresponding baseline. |
| Tasks | |
| Published | 2019-07-30 |
| URL | https://arxiv.org/abs/1907.13057v1 |
| https://arxiv.org/pdf/1907.13057v1.pdf | |
| PWC | https://paperswithcode.com/paper/screening-mammogram-classification-with-prior |
| Repo | |
| Framework | |
Tree-gated Deep Regressor Ensemble For Face Alignment In The Wild
| Title | Tree-gated Deep Regressor Ensemble For Face Alignment In The Wild |
| Authors | Estephe Arnaud, Arnaud Dapogny, Kevin Bailly |
| Abstract | Face alignment consists in aligning a shape model on a face in an image. It is an active domain in computer vision as it is a preprocessing for applications like facial expression recognition, face recognition and tracking, face animation, etc. Current state-of-the-art methods already perform well on “easy” datasets, i.e. those that present moderate variations in head pose, expression, illumination or partial occlusions, but may not be robust to “in-the-wild” data. In this paper, we address this problem by using an ensemble of deep regressors instead of a single large regressor. Furthermore, instead of averaging the outputs of each regressor, we propose an adaptive weighting scheme that uses a tree-structured gate. Experiments on several challenging face datasets demonstrate that our approach outperforms the state-of-the-art methods. |
| Tasks | Face Alignment, Face Recognition, Facial Expression Recognition |
| Published | 2019-07-07 |
| URL | https://arxiv.org/abs/1907.03248v2 |
| https://arxiv.org/pdf/1907.03248v2.pdf | |
| PWC | https://paperswithcode.com/paper/tree-gated-deep-regressor-ensemble-for-face |
| Repo | |
| Framework | |
LBP-HOG Descriptor Based on Matrix Projection For Mammogram Classification
| Title | LBP-HOG Descriptor Based on Matrix Projection For Mammogram Classification |
| Authors | Zainab Alhakeem, Se-In Jang |
| Abstract | In image based feature descriptor design, an iterative scanning operation (e.g., convolution) is mainly adopted to extract local information of the image pixels. In this paper, we propose a Matrix based Local Binary Pattern (M-LBP) and a Matrix based Histogram of Oriented Gradients (M-HOG) descriptors based on global matrix projection. An integrated form of M-LBP and M-HOG, namely M-LBP-HOG, is subsequently constructed in a single line of matrix formulation. The proposed descriptors are evaluated using a publicly available mammogram database. The results show promising performance in terms of classification accuracy and computational efficiency. |
| Tasks | |
| Published | 2019-03-30 |
| URL | https://arxiv.org/abs/1904.00187v2 |
| https://arxiv.org/pdf/1904.00187v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-convolution-free-lbp-hog-descriptor-for |
| Repo | |
| Framework | |
Unsupervised Neural Dialect Translation with Commonality and Diversity Modeling
| Title | Unsupervised Neural Dialect Translation with Commonality and Diversity Modeling |
| Authors | Yu Wan, Baosong Yang, Derek F. Wong, Lidia S. Chao, Haihua Du, Ben C. H. Ao |
| Abstract | As a special machine translation task, dialect translation has two main characteristics: 1) lack of parallel training corpus; and 2) possessing similar grammar between two sides of the translation. In this paper, we investigate how to exploit the commonality and diversity between dialects thus to build unsupervised translation models merely accessing to monolingual data. Specifically, we leverage pivot-private embedding, layer coordination, as well as parameter sharing to sufficiently model commonality and diversity among source and target, ranging from lexical, through syntactic, to semantic levels. In order to examine the effectiveness of the proposed models, we collect 20 million monolingual corpus for each of Mandarin and Cantonese, which are official language and the most widely used dialect in China. Experimental results reveal that our methods outperform rule-based simplified and traditional Chinese conversion and conventional unsupervised translation models over 12 BLEU scores. |
| Tasks | Machine Translation |
| Published | 2019-12-11 |
| URL | https://arxiv.org/abs/1912.05134v1 |
| https://arxiv.org/pdf/1912.05134v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-neural-dialect-translation-with |
| Repo | |
| Framework | |
Cooperative Pathfinding based on memory-efficient Multi-agent RRT*
| Title | Cooperative Pathfinding based on memory-efficient Multi-agent RRT* |
| Authors | Jinmingwu Jiang, Kaigui Wu |
| Abstract | In cooperative pathfinding problems, no-conflicts paths that bring several agents from their start location to their destination need to be planned. This problem can be efficiently solved by Multi-agent RRT*(MA-RRT*) algorithm, which is still state-of-the-art in the field of coupled methods. However, the implementation of this algorithm is hindered in systems with limited memory because the number of nodes in the tree grows indefinitely as the paths get optimized. This paper proposes an improved version of MA-RRT*, called Multi-agent RRT* Fixed Node(MA-RRT*FN), which limits the number of nodes stored in the tree by removing the weak nodes on the path which are not likely to reach the goal. The results show that MA-RRT*FN performs close to MA-RRT* in terms of scalability and solution quality while the memory required is much lower and fixed. |
| Tasks | |
| Published | 2019-11-10 |
| URL | https://arxiv.org/abs/1911.03927v3 |
| https://arxiv.org/pdf/1911.03927v3.pdf | |
| PWC | https://paperswithcode.com/paper/cooperative-pathfinding-based-on-memory |
| Repo | |
| Framework | |
