Paper Group ANR 193
Analyzing the group sparsity based on the rank minimization methods. How can one sample images with sampling rates close to the theoretical minimum?. Multilingual Modal Sense Classification using a Convolutional Neural Network. Preoperative Volume Determination for Pituitary Adenoma. Computing threshold functions using dendrites. A self-tuning Fire …
Analyzing the group sparsity based on the rank minimization methods
| Title | Analyzing the group sparsity based on the rank minimization methods |
| Authors | Zhiyuan Zha, Xin Liu, Xiaohua Huang, Henglin Shi, Yingyue Xu, Qiong Wang, Lan Tang, Xinggan Zhang |
| Abstract | Sparse coding has achieved a great success in various image processing studies. However, there is not any benchmark to measure the sparsity of image patch/group because sparse discriminant conditions cannot keep unchanged. This paper analyzes the sparsity of group based on the strategy of the rank minimization. Firstly, an adaptive dictionary for each group is designed. Then, we prove that group-based sparse coding is equivalent to the rank minimization problem, and thus the sparse coefficient of each group is measured by estimating the singular values of each group. Based on that measurement, the weighted Schatten $p$-norm minimization (WSNM) has been found to be the closest solution to the real singular values of each group. Thus, WSNM can be equivalently transformed into a non-convex $\ell_p$-norm minimization problem in group-based sparse coding. To make the proposed scheme tractable and robust, the alternating direction method of multipliers (ADMM) is used to solve the $\ell_p$-norm minimization problem. Experimental results on two applications: image inpainting and image compressive sensing (CS) recovery have shown that the proposed scheme outperforms many state-of-the-art methods. |
| Tasks | Compressive Sensing, Image Inpainting |
| Published | 2016-11-28 |
| URL | http://arxiv.org/abs/1611.08983v12 |
| http://arxiv.org/pdf/1611.08983v12.pdf | |
| PWC | https://paperswithcode.com/paper/analyzing-the-group-sparsity-based-on-the |
| Repo | |
| Framework | |
How can one sample images with sampling rates close to the theoretical minimum?
| Title | How can one sample images with sampling rates close to the theoretical minimum? |
| Authors | Leonid Yaroslavsky |
| Abstract | A problem is addressed of minimization of the number of measurements needed for digital image acquisition and reconstruction with a given accuracy. A sampling theory based method of image sampling and reconstruction is suggested that allows to draw near the minimal rate of image sampling defined by the sampling theory. Presented and discussed are also results of experimental verification of the method and its possible applicability extensions. |
| Tasks | |
| Published | 2016-01-03 |
| URL | http://arxiv.org/abs/1601.00311v4 |
| http://arxiv.org/pdf/1601.00311v4.pdf | |
| PWC | https://paperswithcode.com/paper/how-can-one-sample-images-with-sampling-rates |
| Repo | |
| Framework | |
Multilingual Modal Sense Classification using a Convolutional Neural Network
| Title | Multilingual Modal Sense Classification using a Convolutional Neural Network |
| Authors | Ana Marasović, Anette Frank |
| Abstract | Modal sense classification (MSC) is a special WSD task that depends on the meaning of the proposition in the modal’s scope. We explore a CNN architecture for classifying modal sense in English and German. We show that CNNs are superior to manually designed feature-based classifiers and a standard NN classifier. We analyze the feature maps learned by the CNN and identify known and previously unattested linguistic features. We benchmark the CNN on a standard WSD task, where it compares favorably to models using sense-disambiguated target vectors. |
| Tasks | |
| Published | 2016-08-18 |
| URL | http://arxiv.org/abs/1608.05243v1 |
| http://arxiv.org/pdf/1608.05243v1.pdf | |
| PWC | https://paperswithcode.com/paper/multilingual-modal-sense-classification-using |
| Repo | |
| Framework | |
Preoperative Volume Determination for Pituitary Adenoma
| Title | Preoperative Volume Determination for Pituitary Adenoma |
| Authors | Dzenan Zukic, Jan Egger, Miriam H. A. Bauer, Daniela Kuhnt, Barbara Carl, Bernd Freisleben, Andreas Kolb, Christopher Nimsky |
| Abstract | The most common sellar lesion is the pituitary adenoma, and sellar tumors are approximately 10-15% of all intracranial neoplasms. Manual slice-by-slice segmentation takes quite some time that can be reduced by using the appropriate algorithms. In this contribution, we present a segmentation method for pituitary adenoma. The method is based on an algorithm that we have applied recently to segmenting glioblastoma multiforme. A modification of this scheme is used for adenoma segmentation that is much harder to perform, due to lack of contrast-enhanced boundaries. In our experimental evaluation, neurosurgeons performed manual slice-by-slice segmentation of ten magnetic resonance imaging (MRI) cases. The segmentations were compared to the segmentation results of the proposed method using the Dice Similarity Coefficient (DSC). The average DSC for all datasets was 75.92% +/- 7.24%. A manual segmentation took about four minutes and our algorithm required about one second. |
| Tasks | |
| Published | 2016-02-05 |
| URL | http://arxiv.org/abs/1602.02022v1 |
| http://arxiv.org/pdf/1602.02022v1.pdf | |
| PWC | https://paperswithcode.com/paper/preoperative-volume-determination-for |
| Repo | |
| Framework | |
Computing threshold functions using dendrites
| Title | Computing threshold functions using dendrites |
| Authors | Romain Cazé, Bartozs Teleńczuk, Alain Destexhe |
| Abstract | Neurons, modeled as linear threshold unit (LTU), can in theory compute all thresh- old functions. In practice, however, some of these functions require synaptic weights of arbitrary large precision. We show here that dendrites can alleviate this requirement. We introduce here the non-Linear Threshold Unit (nLTU) that integrates synaptic input sub-linearly within distinct subunits to take into account local saturation in dendrites. We systematically search parameter space of the nTLU and TLU to compare them. Firstly, this shows that the nLTU can compute all threshold functions with smaller precision weights than the LTU. Secondly, we show that a nLTU can compute significantly more functions than a LTU when an input can only make a single synapse. This work paves the way for a new generation of network made of nLTU with binary synapses. |
| Tasks | |
| Published | 2016-11-10 |
| URL | http://arxiv.org/abs/1611.03321v1 |
| http://arxiv.org/pdf/1611.03321v1.pdf | |
| PWC | https://paperswithcode.com/paper/computing-threshold-functions-using-dendrites |
| Repo | |
| Framework | |
A self-tuning Firefly algorithm to tune the parameters of Ant Colony System (ACSFA)
| Title | A self-tuning Firefly algorithm to tune the parameters of Ant Colony System (ACSFA) |
| Authors | M. K. A. Ariyaratne, T. G. I. Fernando, S. Weerakoon |
| Abstract | Ant colony system (ACS) is a promising approach which has been widely used in problems such as Travelling Salesman Problems (TSP), Job shop scheduling problems (JSP) and Quadratic Assignment problems (QAP). In its original implementation, parameters of the algorithm were selected by trial and error approach. Over the last few years, novel approaches have been proposed on adapting the parameters of ACS in improving its performance. The aim of this paper is to use a framework introduced for self-tuning optimization algorithms combined with the firefly algorithm (FA) to tune the parameters of the ACS solving symmetric TSP problems. The FA optimizes the problem specific parameters of ACS while the parameters of the FA are tuned by the selected framework itself. With this approach, the user neither has to work with the parameters of ACS nor the parameters of FA. Using common symmetric TSP problems we demonstrate that the framework fits well for the ACS. A detailed statistical analysis further verifies the goodness of the new ACS over the existing ACS and also of the other techniques used to tune the parameters of ACS. |
| Tasks | |
| Published | 2016-10-26 |
| URL | http://arxiv.org/abs/1610.08222v1 |
| http://arxiv.org/pdf/1610.08222v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-self-tuning-firefly-algorithm-to-tune-the |
| Repo | |
| Framework | |
Modelling Temporal Information Using Discrete Fourier Transform for Video Classification
| Title | Modelling Temporal Information Using Discrete Fourier Transform for Video Classification |
| Authors | Haimin Zhang |
| Abstract | Recently, video classification attracts intensive research efforts. However, most existing works are based on framelevel visual features, which might fail to model the temporal information, e.g. characteristics accumulated along time. In order to capture video temporal information, we propose to analyse features in frequency domain transformed by discrete Fourier transform (DFT features). Frame-level features are firstly extract by a pre-trained deep convolutional neural network (CNN). Then, time domain features are transformed and interpolated into DFT features. CNN and DFT features are further encoded by using different pooling methods and fused for video classification. In this way, static image features extracted from a pre-trained deep CNN and temporal information represented by DFT features are jointly considered for video classification. We test our method for video emotion classification and action recognition. Experimental results demonstrate that combining DFT features can effectively capture temporal information and therefore improve the performance of both video emotion classification and action recognition. Our approach has achieved a state-of-the-art performance on the largest video emotion dataset (VideoEmotion-8 dataset) and competitive results on UCF-101. |
| Tasks | Emotion Classification, Temporal Action Localization, Video Classification |
| Published | 2016-03-20 |
| URL | http://arxiv.org/abs/1603.06182v5 |
| http://arxiv.org/pdf/1603.06182v5.pdf | |
| PWC | https://paperswithcode.com/paper/modelling-temporal-information-using-discrete-1 |
| Repo | |
| Framework | |
Geometry Aware Mappings for High Dimensional Sparse Factors
| Title | Geometry Aware Mappings for High Dimensional Sparse Factors |
| Authors | Avradeep Bhowmik, Nathan Liu, Erheng Zhong, Badri Narayan Bhaskar, Suju Rajan |
| Abstract | While matrix factorisation models are ubiquitous in large scale recommendation and search, real time application of such models requires inner product computations over an intractably large set of item factors. In this manuscript we present a novel framework that uses the inverted index representation to exploit structural properties of sparse vectors to significantly reduce the run time computational cost of factorisation models. We develop techniques that use geometry aware permutation maps on a tessellated unit sphere to obtain high dimensional sparse embeddings for latent factors with sparsity patterns related to angular closeness of the original latent factors. We also design several efficient and deterministic realisations within this framework and demonstrate with experiments that our techniques lead to faster run time operation with minimal loss of accuracy. |
| Tasks | |
| Published | 2016-05-16 |
| URL | http://arxiv.org/abs/1605.04764v1 |
| http://arxiv.org/pdf/1605.04764v1.pdf | |
| PWC | https://paperswithcode.com/paper/geometry-aware-mappings-for-high-dimensional |
| Repo | |
| Framework | |
Learning the image processing pipeline
| Title | Learning the image processing pipeline |
| Authors | Haomiao Jiang, Qiyuan Tian, Joyce Farrell, Brian Wandell |
| Abstract | Many creative ideas are being proposed for image sensor designs, and these may be useful in applications ranging from consumer photography to computer vision. To understand and evaluate each new design, we must create a corresponding image processing pipeline that transforms the sensor data into a form that is appropriate for the application. The need to design and optimize these pipelines is time-consuming and costly. We explain a method that combines machine learning and image systems simulation that automates the pipeline design. The approach is based on a new way of thinking of the image processing pipeline as a large collection of local linear filters. We illustrate how the method has been used to design pipelines for novel sensor architectures in consumer photography applications. |
| Tasks | |
| Published | 2016-05-30 |
| URL | http://arxiv.org/abs/1605.09336v1 |
| http://arxiv.org/pdf/1605.09336v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-the-image-processing-pipeline |
| Repo | |
| Framework | |
Interactive and Scale Invariant Segmentation of the Rectum/Sigmoid via User-Defined Templates
| Title | Interactive and Scale Invariant Segmentation of the Rectum/Sigmoid via User-Defined Templates |
| Authors | Tobias Lüddemann, Jan Egger |
| Abstract | Among all types of cancer, gynecological malignancies belong to the 4th most frequent type of cancer among women. Besides chemotherapy and external beam radiation, brachytherapy is the standard procedure for the treatment of these malignancies. In the progress of treatment planning, localization of the tumor as the target volume and adjacent organs of risks by segmentation is crucial to accomplish an optimal radiation distribution to the tumor while simultaneously preserving healthy tissue. Segmentation is performed manually and represents a time-consuming task in clinical daily routine. This study focuses on the segmentation of the rectum/sigmoid colon as an Organ-At-Risk in gynecological brachytherapy. The proposed segmentation method uses an interactive, graph-based segmentation scheme with a user-defined template. The scheme creates a directed two dimensional graph, followed by the minimal cost closed set computation on the graph, resulting in an outlining of the rectum. The graphs outline is dynamically adapted to the last calculated cut. Evaluation was performed by comparing manual segmentations of the rectum/sigmoid colon to results achieved with the proposed method. The comparison of the algorithmic to manual results yielded to a Dice Similarity Coefficient value of 83.85+/-4.08%, in comparison to 83.97+/-8.08% for the comparison of two manual segmentations of the same physician. Utilizing the proposed methodology resulted in a median time of 128 seconds per dataset, compared to 300 seconds needed for pure manual segmentation. |
| Tasks | |
| Published | 2016-03-03 |
| URL | http://arxiv.org/abs/1603.00961v1 |
| http://arxiv.org/pdf/1603.00961v1.pdf | |
| PWC | https://paperswithcode.com/paper/interactive-and-scale-invariant-segmentation |
| Repo | |
| Framework | |
A Modified Activation Function with Improved Run-Times For Neural Networks
| Title | A Modified Activation Function with Improved Run-Times For Neural Networks |
| Authors | Vincent Ike Anireh, Emmanuel Ndidi Osegi |
| Abstract | In this paper we present a modified version of the Hyperbolic Tangent Activation Function as a learning unit generator for neural networks. The function uses an integer calibration constant as an approximation to the Euler number, e, based on a quadratic Real Number Formula (RNF) algorithm and an adaptive normalization constraint on the input activations to avoid the vanishing gradient. We demonstrate the effectiveness of the proposed modification using a hypothetical and real world dataset and show that lower run-times can be achieved by learning algorithms using this function leading to improved speed-ups and learning accuracies during training. |
| Tasks | Calibration |
| Published | 2016-07-06 |
| URL | http://arxiv.org/abs/1607.01691v1 |
| http://arxiv.org/pdf/1607.01691v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-modified-activation-function-with-improved |
| Repo | |
| Framework | |
Active Regression with Adaptive Huber Loss
| Title | Active Regression with Adaptive Huber Loss |
| Authors | Jacopo Cavazza, Vittorio Murino |
| Abstract | This paper addresses the scalar regression problem through a novel solution to exactly optimize the Huber loss in a general semi-supervised setting, which combines multi-view learning and manifold regularization. We propose a principled algorithm to 1) avoid computationally expensive iterative schemes while 2) adapting the Huber loss threshold in a data-driven fashion and 3) actively balancing the use of labelled data to remove noisy or inconsistent annotations at the training stage. In a wide experimental evaluation, dealing with diverse applications, we assess the superiority of our paradigm which is able to combine robustness towards noise with both strong performance and low computational cost. |
| Tasks | MULTI-VIEW LEARNING |
| Published | 2016-06-05 |
| URL | http://arxiv.org/abs/1606.01568v2 |
| http://arxiv.org/pdf/1606.01568v2.pdf | |
| PWC | https://paperswithcode.com/paper/active-regression-with-adaptive-huber-loss |
| Repo | |
| Framework | |
“Draw My Topics”: Find Desired Topics fast from large scale of Corpus
| Title | “Draw My Topics”: Find Desired Topics fast from large scale of Corpus |
| Authors | Jason Dou, Ni Sun, Xiaojun Zou |
| Abstract | We develop the “Draw My Topics” toolkit, which provides a fast way to incorporate social scientists’ interest into standard topic modelling. Instead of using raw corpus with primitive processing as input, an algorithm based on Vector Space Model and Conditional Entropy are used to connect social scientists’ willingness and unsupervised topic models’ output. Space for users’ adjustment on specific corpus of their interest is also accommodated. We demonstrate the toolkit’s use on the Diachronic People’s Daily Corpus in Chinese. |
| Tasks | Topic Models |
| Published | 2016-02-03 |
| URL | http://arxiv.org/abs/1602.01428v1 |
| http://arxiv.org/pdf/1602.01428v1.pdf | |
| PWC | https://paperswithcode.com/paper/draw-my-topics-find-desired-topics-fast-from |
| Repo | |
| Framework | |
Variance-Reduced Proximal Stochastic Gradient Descent for Non-convex Composite optimization
| Title | Variance-Reduced Proximal Stochastic Gradient Descent for Non-convex Composite optimization |
| Authors | Xiyu Yu, Dacheng Tao |
| Abstract | Here we study non-convex composite optimization: first, a finite-sum of smooth but non-convex functions, and second, a general function that admits a simple proximal mapping. Most research on stochastic methods for composite optimization assumes convexity or strong convexity of each function. In this paper, we extend this problem into the non-convex setting using variance reduction techniques, such as prox-SVRG and prox-SAGA. We prove that, with a constant step size, both prox-SVRG and prox-SAGA are suitable for non-convex composite optimization, and help the problem converge to a stationary point within $O(1/\epsilon)$ iterations. That is similar to the convergence rate seen with the state-of-the-art RSAG method and faster than stochastic gradient descent. Our analysis is also extended into the min-batch setting, which linearly accelerates the convergence. To the best of our knowledge, this is the first analysis of convergence rate of variance-reduced proximal stochastic gradient for non-convex composite optimization. |
| Tasks | |
| Published | 2016-06-02 |
| URL | http://arxiv.org/abs/1606.00602v2 |
| http://arxiv.org/pdf/1606.00602v2.pdf | |
| PWC | https://paperswithcode.com/paper/variance-reduced-proximal-stochastic-gradient |
| Repo | |
| Framework | |
Denoising and compression in wavelet domain via projection onto approximation coefficients
| Title | Denoising and compression in wavelet domain via projection onto approximation coefficients |
| Authors | Mario Mastriani |
| Abstract | We describe a new filtering approach in the wavelet domain for image denoising and compression, based on the projections of details subbands coefficients (resultants of the splitting procedure, typical in wavelet domain) onto the approximation subband coefficients (much less noisy). The new algorithm is called Projection Onto Approximation Coefficients (POAC). As a result of this approach, only the approximation subband coefficients and three scalars are stored and/or transmitted to the channel. Besides, with the elimination of the details subbands coefficients, we obtain a bigger compression rate. Experimental results demonstrate that our approach compares favorably to more typical methods of denoising and compression in wavelet domain. |
| Tasks | Denoising, Image Denoising |
| Published | 2016-07-31 |
| URL | http://arxiv.org/abs/1608.00265v1 |
| http://arxiv.org/pdf/1608.00265v1.pdf | |
| PWC | https://paperswithcode.com/paper/denoising-and-compression-in-wavelet-domain |
| Repo | |
| Framework | |
