Paper Group ANR 259
Cognitive Deep Machine Can Train Itself. TODIM and TOPSIS with Z-numbers. A General Framework for Density Based Time Series Clustering Exploiting a Novel Admissible Pruning Strategy. Deep Learning with Sets and Point Clouds. Optimized clothes segmentation to boost gender classification in unconstrained scenarios. Kernel Bandwidth Selection for SVDD …
Cognitive Deep Machine Can Train Itself
| Title | Cognitive Deep Machine Can Train Itself |
| Authors | András Lőrincz, Máté Csákvári, Áron Fóthi, Zoltán Ádám Milacski, András Sárkány, Zoltán Tősér |
| Abstract | Machine learning is making substantial progress in diverse applications. The success is mostly due to advances in deep learning. However, deep learning can make mistakes and its generalization abilities to new tasks are questionable. We ask when and how one can combine network outputs, when (i) details of the observations are evaluated by learned deep components and (ii) facts and confirmation rules are available in knowledge based systems. We show that in limited contexts the required number of training samples can be low and self-improvement of pre-trained networks in more general context is possible. We argue that the combination of sparse outlier detection with deep components that can support each other diminish the fragility of deep methods, an important requirement for engineering applications. We argue that supervised learning of labels may be fully eliminated under certain conditions: a component based architecture together with a knowledge based system can train itself and provide high quality answers. We demonstrate these concepts on the State Farm Distracted Driver Detection benchmark. We argue that the view of the Study Panel (2016) may overestimate the requirements on years of focused research' and careful, unique construction’ for `AI systems’. | |
| Tasks | Outlier Detection |
| Published | 2016-12-02 |
| URL | http://arxiv.org/abs/1612.00745v1 |
| http://arxiv.org/pdf/1612.00745v1.pdf | |
| PWC | https://paperswithcode.com/paper/cognitive-deep-machine-can-train-itself |
| Repo | |
| Framework | |
TODIM and TOPSIS with Z-numbers
| Title | TODIM and TOPSIS with Z-numbers |
| Authors | R. A. Krohling, Artem dos Santos, A. G. C. Pacheco |
| Abstract | In this paper, we present an approach that is able to handle with Z-numbers in the context of Multi-Criteria Decision Making (MCDM) problems. Z-numbers are composed of two parts, the first one is a restriction on the values that can be assumed, and the second part is the reliability of the information. As human beings we communicate with other people by means of natural language using sentences like: the journey time from home to university takes about half hour, very likely. Firstly, Z-numbers are converted to fuzzy numbers using a standard procedure. Next, the Z-TODIM and Z-TOPSIS are presented as a direct extension of the fuzzy TODIM and fuzzy TOPSIS, respectively. The proposed methods are applied to two case studies and compared with the standard approach using crisp values. Results obtained show the feasibility of the approach. In addition, a graphical interface was built to handle with both methods Z- TODIM and Z-TOPSIS allowing ease of use for user in other areas of knowledge. |
| Tasks | Decision Making |
| Published | 2016-09-19 |
| URL | http://arxiv.org/abs/1609.05705v1 |
| http://arxiv.org/pdf/1609.05705v1.pdf | |
| PWC | https://paperswithcode.com/paper/todim-and-topsis-with-z-numbers |
| Repo | |
| Framework | |
A General Framework for Density Based Time Series Clustering Exploiting a Novel Admissible Pruning Strategy
| Title | A General Framework for Density Based Time Series Clustering Exploiting a Novel Admissible Pruning Strategy |
| Authors | Nurjahan Begum, Liudmila Ulanova, Hoang Anh Dau, Jun Wang, Eamonn Keogh |
| Abstract | Time Series Clustering is an important subroutine in many higher-level data mining analyses, including data editing for classifiers, summarization, and outlier detection. It is well known that for similarity search the superiority of Dynamic Time Warping (DTW) over Euclidean distance gradually diminishes as we consider ever larger datasets. However, as we shall show, the same is not true for clustering. Clustering time series under DTW remains a computationally expensive operation. In this work, we address this issue in two ways. We propose a novel pruning strategy that exploits both the upper and lower bounds to prune off a very large fraction of the expensive distance calculations. This pruning strategy is admissible and gives us provably identical results to the brute force algorithm, but is at least an order of magnitude faster. For datasets where even this level of speedup is inadequate, we show that we can use a simple heuristic to order the unavoidable calculations in a most-useful-first ordering, thus casting the clustering into an anytime framework. We demonstrate the utility of our ideas with both single and multidimensional case studies in the domains of astronomy, speech physiology, medicine and entomology. In addition, we show the generality of our clustering framework to other domains by efficiently obtaining semantically significant clusters in protein sequences using the Edit Distance, the discrete data analogue of DTW. |
| Tasks | Outlier Detection, Time Series, Time Series Clustering |
| Published | 2016-12-02 |
| URL | http://arxiv.org/abs/1612.00637v1 |
| http://arxiv.org/pdf/1612.00637v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-general-framework-for-density-based-time |
| Repo | |
| Framework | |
Deep Learning with Sets and Point Clouds
| Title | Deep Learning with Sets and Point Clouds |
| Authors | Siamak Ravanbakhsh, Jeff Schneider, Barnabas Poczos |
| Abstract | We introduce a simple permutation equivariant layer for deep learning with set structure.This type of layer, obtained by parameter-sharing, has a simple implementation and linear-time complexity in the size of each set. We use deep permutation-invariant networks to perform point-could classification and MNIST-digit summation, where in both cases the output is invariant to permutations of the input. In a semi-supervised setting, where the goal is make predictions for each instance within a set, we demonstrate the usefulness of this type of layer in set-outlier detection as well as semi-supervised learning with clustering side-information. |
| Tasks | Outlier Detection |
| Published | 2016-11-14 |
| URL | http://arxiv.org/abs/1611.04500v3 |
| http://arxiv.org/pdf/1611.04500v3.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-with-sets-and-point-clouds |
| Repo | |
| Framework | |
Optimized clothes segmentation to boost gender classification in unconstrained scenarios
| Title | Optimized clothes segmentation to boost gender classification in unconstrained scenarios |
| Authors | D. Freire-Obregón, M. Castrillón-Santana, J. Lorenzo-Navarro |
| Abstract | Several applications require demographic information of ordinary people in unconstrained scenarios. This is not a trivial task due to significant human appearance variations. In this work, we introduce trixels for clustering image regions, enumerating their advantages compared to superpixels. The classical GrabCut algorithm is later modified to segment trixels instead of pixels in an unsupervised context. Combining with face detection lead us to a clothes segmentation approach close to real time. The study uses the challenging Pascal VOC dataset for segmentation evaluation experiments. A final experiment analyzes the fusion of clothes features with state-of-the-art gender classifiers in ClothesDB, revealing a significant performance improvement in gender classification. |
| Tasks | Face Detection |
| Published | 2016-11-12 |
| URL | http://arxiv.org/abs/1611.03999v1 |
| http://arxiv.org/pdf/1611.03999v1.pdf | |
| PWC | https://paperswithcode.com/paper/optimized-clothes-segmentation-to-boost |
| Repo | |
| Framework | |
Kernel Bandwidth Selection for SVDD: Peak Criterion Approach for Large Data
| Title | Kernel Bandwidth Selection for SVDD: Peak Criterion Approach for Large Data |
| Authors | Sergiy Peredriy, Deovrat Kakde, Arin Chaudhuri |
| Abstract | Support Vector Data Description (SVDD) provides a useful approach to construct a description of multivariate data for single-class classification and outlier detection with various practical applications. Gaussian kernel used in SVDD formulation allows flexible data description defined by observations designated as support vectors. The data boundary of such description is non-spherical and conforms to the geometric features of the data. By varying the Gaussian kernel bandwidth parameter, the SVDD-generated boundary can be made either smoother (more spherical) or tighter/jagged. The former case may lead to under-fitting, whereas the latter may result in overfitting. Peak criterion has been proposed to select an optimal value of the kernel bandwidth to strike the balance between the data boundary smoothness and its ability to capture the general geometric shape of the data. Peak criterion involves training SVDD at various values of the kernel bandwidth parameter. When training datasets are large, the time required to obtain the optimal value of the Gaussian kernel bandwidth parameter according to Peak method can become prohibitively large. This paper proposes an extension of Peak method for the case of large data. The proposed method gives good results when applied to several datasets. Two existing alternative methods of computing the Gaussian kernel bandwidth parameter (Coefficient of Variation and Distance to the Farthest Neighbor) were modified to allow comparison with the proposed method on convergence. Empirical comparison demonstrates the advantage of the proposed method. |
| Tasks | Outlier Detection |
| Published | 2016-10-31 |
| URL | http://arxiv.org/abs/1611.00058v3 |
| http://arxiv.org/pdf/1611.00058v3.pdf | |
| PWC | https://paperswithcode.com/paper/kernel-bandwidth-selection-for-svdd-peak |
| Repo | |
| Framework | |
Binary Codes for Tagging X-Ray Images via Deep De-Noising Autoencoders
| Title | Binary Codes for Tagging X-Ray Images via Deep De-Noising Autoencoders |
| Authors | Antonio Sze-To, Hamid R. Tizhoosh, Andrew K. C. Wong |
| Abstract | A Content-Based Image Retrieval (CBIR) system which identifies similar medical images based on a query image can assist clinicians for more accurate diagnosis. The recent CBIR research trend favors the construction and use of binary codes to represent images. Deep architectures could learn the non-linear relationship among image pixels adaptively, allowing the automatic learning of high-level features from raw pixels. However, most of them require class labels, which are expensive to obtain, particularly for medical images. The methods which do not need class labels utilize a deep autoencoder for binary hashing, but the code construction involves a specific training algorithm and an ad-hoc regularization technique. In this study, we explored using a deep de-noising autoencoder (DDA), with a new unsupervised training scheme using only backpropagation and dropout, to hash images into binary codes. We conducted experiments on more than 14,000 x-ray images. By using class labels only for evaluating the retrieval results, we constructed a 16-bit DDA and a 512-bit DDA independently. Comparing to other unsupervised methods, we succeeded to obtain the lowest total error by using the 512-bit codes for retrieval via exhaustive search, and speed up 9.27 times with the use of the 16-bit codes while keeping a comparable total error. We found that our new training scheme could reduce the total retrieval error significantly by 21.9%. To further boost the image retrieval performance, we developed Radon Autoencoder Barcode (RABC) which are learned from the Radon projections of images using a de-noising autoencoder. Experimental results demonstrated its superior performance in retrieval when it was combined with DDA binary codes. |
| Tasks | Content-Based Image Retrieval, Image Retrieval |
| Published | 2016-04-24 |
| URL | http://arxiv.org/abs/1604.07060v1 |
| http://arxiv.org/pdf/1604.07060v1.pdf | |
| PWC | https://paperswithcode.com/paper/binary-codes-for-tagging-x-ray-images-via |
| Repo | |
| Framework | |
Detecting facial landmarks in the video based on a hybrid framework
| Title | Detecting facial landmarks in the video based on a hybrid framework |
| Authors | Nian Cai, Zhineng Lin, Fu Zhang, Guandong Cen, Han Wang |
| Abstract | To dynamically detect the facial landmarks in the video, we propose a novel hybrid framework termed as detection-tracking-detection (DTD). First, the face bounding box is achieved from the first frame of the video sequence based on a traditional face detection method. Then, a landmark detector detects the facial landmarks, which is based on a cascaded deep convolution neural network (DCNN). Next, the face bounding box in the current frame is estimated and validated after the facial landmarks in the previous frame are tracked based on the median flow. Finally, the facial landmarks in the current frame are exactly detected from the validated face bounding box via the landmark detector. Experimental results indicate that the proposed framework can detect the facial landmarks in the video sequence more effectively and with lower consuming time compared to the frame-by-frame method via the DCNN. |
| Tasks | Face Detection |
| Published | 2016-09-21 |
| URL | http://arxiv.org/abs/1609.06441v1 |
| http://arxiv.org/pdf/1609.06441v1.pdf | |
| PWC | https://paperswithcode.com/paper/detecting-facial-landmarks-in-the-video-based |
| Repo | |
| Framework | |
Depth Estimation from Single Image using Sparse Representations
| Title | Depth Estimation from Single Image using Sparse Representations |
| Authors | Yigit Oktar |
| Abstract | Monocular depth estimation is an interesting and challenging problem as there is no analytic mapping known between an intensity image and its depth map. Recently there has been a lot of data accumulated through depth-sensing cameras, in parallel to that researchers started to tackle this task using various learning algorithms. In this paper, a deep sparse coding method is proposed for monocular depth estimation along with an approach for deterministic dictionary initialization. |
| Tasks | Depth Estimation, Monocular Depth Estimation |
| Published | 2016-06-27 |
| URL | http://arxiv.org/abs/1606.08315v1 |
| http://arxiv.org/pdf/1606.08315v1.pdf | |
| PWC | https://paperswithcode.com/paper/depth-estimation-from-single-image-using |
| Repo | |
| Framework | |
On the Use of Deep Learning for Blind Image Quality Assessment
| Title | On the Use of Deep Learning for Blind Image Quality Assessment |
| Authors | Simone Bianco, Luigi Celona, Paolo Napoletano, Raimondo Schettini |
| Abstract | In this work we investigate the use of deep learning for distortion-generic blind image quality assessment. We report on different design choices, ranging from the use of features extracted from pre-trained Convolutional Neural Networks (CNNs) as a generic image description, to the use of features extracted from a CNN fine-tuned for the image quality task. Our best proposal, named DeepBIQ, estimates the image quality by average pooling the scores predicted on multiple sub-regions of the original image. The score of each sub-region is computed using a Support Vector Regression (SVR) machine taking as input features extracted using a CNN fine-tuned for category-based image quality assessment. Experimental results on the LIVE In the Wild Image Quality Challenge Database and on the LIVE Image Quality Assessment Database show that DeepBIQ outperforms the state-of-the-art methods compared, having a Linear Correlation Coefficient (LCC) with human subjective scores of almost 0.91 and 0.98 respectively. Furthermore, in most of the cases, the quality score predictions of DeepBIQ are closer to the average observer than those of a generic human observer. |
| Tasks | Blind Image Quality Assessment, Image Quality Assessment |
| Published | 2016-02-17 |
| URL | http://arxiv.org/abs/1602.05531v5 |
| http://arxiv.org/pdf/1602.05531v5.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-use-of-deep-learning-for-blind-image |
| Repo | |
| Framework | |
Automatic Sleep Stage Scoring with Single-Channel EEG Using Convolutional Neural Networks
| Title | Automatic Sleep Stage Scoring with Single-Channel EEG Using Convolutional Neural Networks |
| Authors | Orestis Tsinalis, Paul M. Matthews, Yike Guo, Stefanos Zafeiriou |
| Abstract | We used convolutional neural networks (CNNs) for automatic sleep stage scoring based on single-channel electroencephalography (EEG) to learn task-specific filters for classification without using prior domain knowledge. We used an openly available dataset from 20 healthy young adults for evaluation and applied 20-fold cross-validation. We used class-balanced random sampling within the stochastic gradient descent (SGD) optimization of the CNN to avoid skewed performance in favor of the most represented sleep stages. We achieved high mean F1-score (81%, range 79-83%), mean accuracy across individual sleep stages (82%, range 80-84%) and overall accuracy (74%, range 71-76%) over all subjects. By analyzing and visualizing the filters that our CNN learns, we found that rules learned by the filters correspond to sleep scoring criteria in the American Academy of Sleep Medicine (AASM) manual that human experts follow. Our method’s performance is balanced across classes and our results are comparable to state-of-the-art methods with hand-engineered features. We show that, without using prior domain knowledge, a CNN can automatically learn to distinguish among different normal sleep stages. |
| Tasks | EEG |
| Published | 2016-10-05 |
| URL | http://arxiv.org/abs/1610.01683v1 |
| http://arxiv.org/pdf/1610.01683v1.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-sleep-stage-scoring-with-single |
| Repo | |
| Framework | |
Automatic Lymphocyte Detection in H&E Images with Deep Neural Networks
| Title | Automatic Lymphocyte Detection in H&E Images with Deep Neural Networks |
| Authors | Jianxu Chen, Chukka Srinivas |
| Abstract | Automatic detection of lymphocyte in H&E images is a necessary first step in lots of tissue image analysis algorithms. An accurate and robust automated lymphocyte detection approach is of great importance in both computer science and clinical studies. Most of the existing approaches for lymphocyte detection are based on traditional image processing algorithms and/or classic machine learning methods. In the recent years, deep learning techniques have fundamentally transformed the way that a computer interprets images and have become a matchless solution in various pattern recognition problems. In this work, we design a new deep neural network model which extends the fully convolutional network by combining the ideas in several recent techniques, such as shortcut links. Also, we design a new training scheme taking the prior knowledge about lymphocytes into consideration. The training scheme not only efficiently exploits the limited amount of free-form annotations from pathologists, but also naturally supports efficient fine-tuning. As a consequence, our model has the potential of self-improvement by leveraging the errors collected during real applications. Our experiments show that our deep neural network model achieves good performance in the images of different staining conditions or different types of tissues. |
| Tasks | |
| Published | 2016-12-09 |
| URL | http://arxiv.org/abs/1612.03217v1 |
| http://arxiv.org/pdf/1612.03217v1.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-lymphocyte-detection-in-he-images |
| Repo | |
| Framework | |
Camera Pose Estimation from Lines using Plücker Coordinates
| Title | Camera Pose Estimation from Lines using Plücker Coordinates |
| Authors | Bronislav Přibyl, Pavel Zemčík, Martin Čadík |
| Abstract | Correspondences between 3D lines and their 2D images captured by a camera are often used to determine position and orientation of the camera in space. In this work, we propose a novel algebraic algorithm to estimate the camera pose. We parameterize 3D lines using Pl"ucker coordinates that allow linear projection of the lines into the image. A line projection matrix is estimated using Linear Least Squares and the camera pose is then extracted from the matrix. An algebraic approach to handle mismatched line correspondences is also included. The proposed algorithm is an order of magnitude faster yet comparably accurate and robust to the state-of-the-art, it does not require initialization, and it yields only one solution. The described method requires at least 9 lines and is particularly suitable for scenarios with 25 and more lines, as also shown in the results. |
| Tasks | Pose Estimation |
| Published | 2016-08-09 |
| URL | http://arxiv.org/abs/1608.02824v1 |
| http://arxiv.org/pdf/1608.02824v1.pdf | |
| PWC | https://paperswithcode.com/paper/camera-pose-estimation-from-lines-using |
| Repo | |
| Framework | |
Faster Sublinear Algorithms using Conditional Sampling
| Title | Faster Sublinear Algorithms using Conditional Sampling |
| Authors | Themistoklis Gouleakis, Christos Tzamos, Manolis Zampetakis |
| Abstract | A conditional sampling oracle for a probability distribution D returns samples from the conditional distribution of D restricted to a specified subset of the domain. A recent line of work (Chakraborty et al. 2013 and Cannone et al. 2014) has shown that having access to such a conditional sampling oracle requires only polylogarithmic or even constant number of samples to solve distribution testing problems like identity and uniformity. This significantly improves over the standard sampling model where polynomially many samples are necessary. Inspired by these results, we introduce a computational model based on conditional sampling to develop sublinear algorithms with exponentially faster runtimes compared to standard sublinear algorithms. We focus on geometric optimization problems over points in high dimensional Euclidean space. Access to these points is provided via a conditional sampling oracle that takes as input a succinct representation of a subset of the domain and outputs a uniformly random point in that subset. We study two well studied problems: k-means clustering and estimating the weight of the minimum spanning tree. In contrast to prior algorithms for the classic model, our algorithms have time, space and sample complexity that is polynomial in the dimension and polylogarithmic in the number of points. Finally, we comment on the applicability of the model and compare with existing ones like streaming, parallel and distributed computational models. |
| Tasks | |
| Published | 2016-08-16 |
| URL | http://arxiv.org/abs/1608.04759v1 |
| http://arxiv.org/pdf/1608.04759v1.pdf | |
| PWC | https://paperswithcode.com/paper/faster-sublinear-algorithms-using-conditional |
| Repo | |
| Framework | |
Deep Learning for the Classification of Lung Nodules
| Title | Deep Learning for the Classification of Lung Nodules |
| Authors | He Yang, Hengyong Yu, Ge Wang |
| Abstract | Deep learning, as a promising new area of machine learning, has attracted a rapidly increasing attention in the field of medical imaging. Compared to the conventional machine learning methods, deep learning requires no hand-tuned feature extractor, and has shown a superior performance in many visual object recognition applications. In this study, we develop a deep convolutional neural network (CNN) and apply it to thoracic CT images for the classification of lung nodules. We present the CNN architecture and classification accuracy for the original images of lung nodules. In order to understand the features of lung nodules, we further construct new datasets, based on the combination of artificial geometric nodules and some transformations of the original images, as well as a stochastic nodule shape model. It is found that simplistic geometric nodules cannot capture the important features of lung nodules. |
| Tasks | Object Recognition |
| Published | 2016-11-21 |
| URL | http://arxiv.org/abs/1611.06651v2 |
| http://arxiv.org/pdf/1611.06651v2.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-for-the-classification-of-lung |
| Repo | |
| Framework | |
