Paper Group ANR 902
Neural Variational Hybrid Collaborative Filtering. Dynamic learning rate using Mutual Information. Algorithmic Linearly Constrained Gaussian Processes. A Fuzzy Community-Based Recommender System Using PageRank. Can Image Enhancement be Beneficial to Find Smoke Images in Laparoscopic Surgery?. Versatile Auxiliary Regressor with Generative Adversaria …
Neural Variational Hybrid Collaborative Filtering
Title | Neural Variational Hybrid Collaborative Filtering |
Authors | Teng Xiao, Shangsong Liang, Hong Shen, Zaiqiao Meng |
Abstract | Collaborative Filtering (CF) is one of the most used methods for Recommender System. Because of the Bayesian nature and nonlinearity, deep generative models, e.g. Variational Autoencoder (VAE), have been applied into CF task, and have achieved great performance. However, most VAE-based methods suffer from matrix sparsity and consider the prior of users’ latent factors to be the same, which leads to poor latent representations of users and items. Additionally, most existing methods model latent factors of users only and but not items, which makes them not be able to recommend items to a new user. To tackle these problems, we propose a Neural Variational Hybrid Collaborative Filtering, NVHCF. Specifically, we consider both the generative processes of users and items, and the prior of latent factors of users and items to be side informationspecific, which enables our model to alleviate matrix sparsity and learn better latent representations of users and items. For inference purpose, we derived a Stochastic Gradient Variational Bayes (SGVB) algorithm to analytically approximate the intractable distributions of latent factors of users and items. Experiments conducted on two large datasets have showed our methods significantly outperform the state-of-the-art CF methods, including the VAE-based methods. |
Tasks | Recommendation Systems |
Published | 2018-10-12 |
URL | http://arxiv.org/abs/1810.05376v6 |
http://arxiv.org/pdf/1810.05376v6.pdf | |
PWC | https://paperswithcode.com/paper/neural-variational-hybrid-collaborative |
Repo | |
Framework | |
Dynamic learning rate using Mutual Information
Title | Dynamic learning rate using Mutual Information |
Authors | Shrihari Vasudevan |
Abstract | This paper demonstrates dynamic hyper-parameter setting, for deep neural network training, using Mutual Information (MI). The specific hyper-parameter studied in this paper is the learning rate. MI between the output layer and true outcomes is used to dynamically set the learning rate of the network through the training cycle; the idea is also extended to layer-wise setting of learning rate. Two approaches are demonstrated - tracking relative change in mutual information and, additionally tracking its value relative to a reference measure. The paper does not attempt to recommend a specific learning rate policy. Experiments demonstrate that mutual information may be effectively used to dynamically set learning rate and achieve competitive to better outcomes in competitive to better time. |
Tasks | |
Published | 2018-05-18 |
URL | http://arxiv.org/abs/1805.07249v2 |
http://arxiv.org/pdf/1805.07249v2.pdf | |
PWC | https://paperswithcode.com/paper/dynamic-learning-rate-using-mutual |
Repo | |
Framework | |
Algorithmic Linearly Constrained Gaussian Processes
Title | Algorithmic Linearly Constrained Gaussian Processes |
Authors | Markus Lange-Hegermann |
Abstract | We algorithmically construct multi-output Gaussian process priors which satisfy linear differential equations. Our approach attempts to parametrize all solutions of the equations using Gr"obner bases. If successful, a push forward Gaussian process along the paramerization is the desired prior. We consider several examples from physics, geomathematics and control, among them the full inhomogeneous system of Maxwell’s equations. By bringing together stochastic learning and computer algebra in a novel way, we combine noisy observations with precise algebraic computations. |
Tasks | Gaussian Processes |
Published | 2018-01-28 |
URL | http://arxiv.org/abs/1801.09197v3 |
http://arxiv.org/pdf/1801.09197v3.pdf | |
PWC | https://paperswithcode.com/paper/algorithmic-linearly-constrained-gaussian |
Repo | |
Framework | |
A Fuzzy Community-Based Recommender System Using PageRank
Title | A Fuzzy Community-Based Recommender System Using PageRank |
Authors | Maliheh Goliforoushani, Radin Hamidi Rad, Maryam Amir Haeri |
Abstract | Recommendation systems are widely used by different user service providers specially those who have interactions with the large community of users. This paper introduces a recommender system based on community detection. The recommendation is provided using the local and global similarities between users. The local information is obtained from communities, and the global ones are based on the ratings. Here, a new fuzzy community detection using the personalized PageRank metaphor is introduced. The fuzzy membership values of the users to the communities are utilized to define a similarity measure. The method is evaluated by using two well-known datasets: MovieLens and FilmTrust. The results show that our method outperforms recent recommender systems. |
Tasks | Community Detection, Recommendation Systems |
Published | 2018-12-18 |
URL | http://arxiv.org/abs/1812.09380v1 |
http://arxiv.org/pdf/1812.09380v1.pdf | |
PWC | https://paperswithcode.com/paper/a-fuzzy-community-based-recommender-system |
Repo | |
Framework | |
Can Image Enhancement be Beneficial to Find Smoke Images in Laparoscopic Surgery?
Title | Can Image Enhancement be Beneficial to Find Smoke Images in Laparoscopic Surgery? |
Authors | Congcong Wang, Vivek Sharma, Yu Fan, Faouzi Alaya Cheikh, Azeddine Beghdadi, Ole Jacob Elle, Rainer Stiefelhagen |
Abstract | Laparoscopic surgery has a limited field of view. Laser ablation in a laproscopic surgery causes smoke, which inevitably influences the surgeon’s visibility. Therefore, it is of vital importance to remove the smoke, such that a clear visualization is possible. In order to employ a desmoking technique, one needs to know beforehand if the image contains smoke or not, to this date, there exists no accurate method that could classify the smoke/non-smoke images completely. In this work, we propose a new enhancement method which enhances the informative details in the RGB images for discrimination of smoke/non-smoke images. Our proposed method utilizes weighted least squares optimization framework~(WLS). For feature extraction, we use statistical features based on bivariate histogram distribution of gradient magnitude~(GM) and Laplacian of Gaussian~(LoG). We then train a SVM classifier with binary smoke/non-smoke classification task. We demonstrate the effectiveness of our method on Cholec80 dataset. Experiments using our proposed enhancement method show promising results with improvements of 4% in accuracy and 4% in F1-Score over the baseline performance of RGB images. In addition, our approach improves over the saturation histogram based classification methodologies Saturation Analysis~(SAN) and Saturation Peak Analysis~(SPA) by 1/5% and 1/6% in accuracy/F1-Score metrics. |
Tasks | Image Enhancement |
Published | 2018-12-27 |
URL | http://arxiv.org/abs/1812.10784v1 |
http://arxiv.org/pdf/1812.10784v1.pdf | |
PWC | https://paperswithcode.com/paper/can-image-enhancement-be-beneficial-to-find |
Repo | |
Framework | |
Versatile Auxiliary Regressor with Generative Adversarial network (VAR+GAN)
Title | Versatile Auxiliary Regressor with Generative Adversarial network (VAR+GAN) |
Authors | Shabab Bazrafkan, Peter Corcoran |
Abstract | Being able to generate constrained samples is one of the most appealing applications of the deep generators. Conditional generators are one of the successful implementations of such models wherein the created samples are constrained to a specific class. In this work, the application of these networks is extended to regression problems wherein the conditional generator is restrained to any continuous aspect of the data. A new loss function is presented for the regression network and also implementations for generating faces with any particular set of landmarks is provided. |
Tasks | Face Generation |
Published | 2018-05-28 |
URL | http://arxiv.org/abs/1805.10864v1 |
http://arxiv.org/pdf/1805.10864v1.pdf | |
PWC | https://paperswithcode.com/paper/versatile-auxiliary-regressor-with-generative |
Repo | |
Framework | |
An adaptive self-organizing fuzzy logic controller in a serious game for motor impairment rehabilitation
Title | An adaptive self-organizing fuzzy logic controller in a serious game for motor impairment rehabilitation |
Authors | Shabnam Sadeghi Esfahlani, Silvia Cirstea, Alireza Sanaei, George Wilson |
Abstract | Rehabilitation robotics combined with video game technology provides a means of assisting in the rehabilitation of patients with neuromuscular disorders by performing various facilitation movements. The current work presents ReHabGame, a serious game using a fusion of implemented technologies that can be easily used by patients and therapists to assess and enhance sensorimotor performance and also increase the activities in the daily lives of patients. The game allows a player to control avatar movements through a Kinect Xbox, Myo armband and rudder foot pedal, and involves a series of reach-grasp-collect tasks whose difficulty levels are learnt by a fuzzy interface. The orientation, angular velocity, head and spine tilts and other data generated by the player are monitored and saved, whilst the task completion is calculated by solving an inverse kinematics algorithm which orientates the upper limb joints of the avatar. The different values in upper body quantities of movement provide fuzzy input from which crisp output is determined and used to generate an appropriate subsequent rehabilitation game level. The system can thus provide personalised, autonomously-learnt rehabilitation programmes for patients with neuromuscular disorders with superior predictions to guide the development of improved clinical protocols compared to traditional theraputic activities. |
Tasks | |
Published | 2018-04-27 |
URL | http://arxiv.org/abs/1804.10392v1 |
http://arxiv.org/pdf/1804.10392v1.pdf | |
PWC | https://paperswithcode.com/paper/an-adaptive-self-organizing-fuzzy-logic |
Repo | |
Framework | |
Virtual Battery Parameter Identification using Transfer Learning based Stacked Autoencoder
Title | Virtual Battery Parameter Identification using Transfer Learning based Stacked Autoencoder |
Authors | Indrasis Chakraborty, Sai Pushpak Nandanoori, Soumya Kundu |
Abstract | Recent studies have shown that the aggregated dynamic flexibility of an ensemble of thermostatic loads can be modeled in the form of a virtual battery. The existing methods for computing the virtual battery parameters require the knowledge of the first-principle models and parameter values of the loads in the ensemble. In real-world applications, however, it is likely that the only available information are end-use measurements such as power consumption, room temperature, device on/off status, etc., while very little about the individual load models and parameters are known. We propose a transfer learning based deep network framework for calculating virtual battery state of a given ensemble of flexible thermostatic loads, from the available end-use measurements. This proposed framework extracts first order virtual battery model parameters for the given ensemble. We illustrate the effectiveness of this novel framework on different ensembles of ACs and WHs. |
Tasks | Transfer Learning |
Published | 2018-10-10 |
URL | http://arxiv.org/abs/1810.04642v1 |
http://arxiv.org/pdf/1810.04642v1.pdf | |
PWC | https://paperswithcode.com/paper/virtual-battery-parameter-identification |
Repo | |
Framework | |
Towards Deep Representation Learning with Genetic Programming
Title | Towards Deep Representation Learning with Genetic Programming |
Authors | Lino Rodriguez-Coayahuitl, Alicia Morales-Reyes, Hugo Jair Escalante |
Abstract | Genetic Programming (GP) is an evolutionary algorithm commonly used for machine learning tasks. In this paper we present a method that allows GP to transform the representation of a large-scale machine learning dataset into a more compact representation, by means of processing features from the original representation at individual level. We develop as a proof of concept of this method an autoencoder. We tested a preliminary version of our approach in a variety of well-known machine learning image datasets. We speculate that this method, used in an iterative manner, can produce results competitive with state-of-art deep neural networks. |
Tasks | Representation Learning |
Published | 2018-02-20 |
URL | http://arxiv.org/abs/1802.07133v1 |
http://arxiv.org/pdf/1802.07133v1.pdf | |
PWC | https://paperswithcode.com/paper/towards-deep-representation-learning-with |
Repo | |
Framework | |
Improving the results of string kernels in sentiment analysis and Arabic dialect identification by adapting them to your test set
Title | Improving the results of string kernels in sentiment analysis and Arabic dialect identification by adapting them to your test set |
Authors | Radu Tudor Ionescu, Andrei M. Butnaru |
Abstract | Recently, string kernels have obtained state-of-the-art results in various text classification tasks such as Arabic dialect identification or native language identification. In this paper, we apply two simple yet effective transductive learning approaches to further improve the results of string kernels. The first approach is based on interpreting the pairwise string kernel similarities between samples in the training set and samples in the test set as features. Our second approach is a simple self-training method based on two learning iterations. In the first iteration, a classifier is trained on the training set and tested on the test set, as usual. In the second iteration, a number of test samples (to which the classifier associated higher confidence scores) are added to the training set for another round of training. However, the ground-truth labels of the added test samples are not necessary. Instead, we use the labels predicted by the classifier in the first training iteration. By adapting string kernels to the test set, we report significantly better accuracy rates in English polarity classification and Arabic dialect identification. |
Tasks | Language Identification, Native Language Identification, Sentiment Analysis, Text Classification |
Published | 2018-08-25 |
URL | http://arxiv.org/abs/1808.08409v2 |
http://arxiv.org/pdf/1808.08409v2.pdf | |
PWC | https://paperswithcode.com/paper/improving-the-results-of-string-kernels-in |
Repo | |
Framework | |
Adversarial Image Registration with Application for MR and TRUS Image Fusion
Title | Adversarial Image Registration with Application for MR and TRUS Image Fusion |
Authors | Pingkun Yan, Sheng Xu, Ardeshir R. Rastinehad, Brad J. Wood |
Abstract | Robust and accurate alignment of multimodal medical images is a very challenging task, which however is very useful for many clinical applications. For example, magnetic resonance (MR) and transrectal ultrasound (TRUS) image registration is a critical component in MR-TRUS fusion guided prostate interventions. However, due to the huge difference between the image appearances and the large variation in image correspondence, MR-TRUS image registration is a very challenging problem. In this paper, an adversarial image registration (AIR) framework is proposed. By training two deep neural networks simultaneously, one being a generator and the other being a discriminator, we can obtain not only a network for image registration, but also a metric network which can help evaluate the quality of image registration. The developed AIR-net is then evaluated using clinical datasets acquired through image-fusion guided prostate biopsy procedures and promising results are demonstrated. |
Tasks | Image Registration |
Published | 2018-04-30 |
URL | http://arxiv.org/abs/1804.11024v2 |
http://arxiv.org/pdf/1804.11024v2.pdf | |
PWC | https://paperswithcode.com/paper/adversarial-image-registration-with |
Repo | |
Framework | |
A matrix-free approach to parallel and memory-efficient deformable image registration
Title | A matrix-free approach to parallel and memory-efficient deformable image registration |
Authors | Lars König, Jan Rühaak, Alexander Derksen, Jan Lellmann |
Abstract | We present a novel computational approach to fast and memory-efficient deformable image registration. In the variational registration model, the computation of the objective function derivatives is the computationally most expensive operation, both in terms of runtime and memory requirements. In order to target this bottleneck, we analyze the matrix structure of gradient and Hessian computations for the case of the normalized gradient fields distance measure and curvature regularization. Based on this analysis, we derive equivalent matrix-free closed-form expressions for derivative computations, eliminating the need for storing intermediate results and the costs of sparse matrix arithmetic. This has further benefits: (1) matrix computations can be fully parallelized, (2) memory complexity for derivative computation is reduced from linear to constant, and (3) overall computation times are substantially reduced. In comparison with an optimized matrix-based reference implementation, the CPU implementation achieves speedup factors between 3.1 and 9.7, and we are able to handle substantially higher resolutions. Using a GPU implementation, we achieve an additional speedup factor of up to 9.2. Furthermore, we evaluated the approach on real-world medical datasets. On ten publicly available lung CT images from the DIR-Lab 4DCT dataset, we achieve the best mean landmark error of 0.93 mm compared to other submissions on the DIR-Lab website, with an average runtime of only 9.23 s. Complete non-rigid registration of full-size 3D thorax-abdomen CT volumes from oncological follow-up is achieved in 12.6 s. The experimental results show that the proposed matrix-free algorithm enables the use of variational registration models also in applications which were previously impractical due to memory or runtime restrictions. |
Tasks | Image Registration |
Published | 2018-04-27 |
URL | http://arxiv.org/abs/1804.10541v1 |
http://arxiv.org/pdf/1804.10541v1.pdf | |
PWC | https://paperswithcode.com/paper/a-matrix-free-approach-to-parallel-and-memory |
Repo | |
Framework | |
Coverless information hiding based on Generative Model
Title | Coverless information hiding based on Generative Model |
Authors | Xintao Duan, Haoxian Song |
Abstract | A new coverless image information hiding method based on generative model is proposed, we feed the secret image to the generative model database, and generate a meaning-normal and independent image different from the secret image, then, the generated image is transmitted to the receiver and is fed to the generative model database to generate another image visually the same as the secret image. So we only need to transmit the meaning-normal image which is not related to the secret image, and we can achieve the same effect as the transmission of the secret image. This is the first time to propose the coverless image information hiding method based on generative model, compared with the traditional image steganography, the transmitted image does not embed any information of the secret image in this method, therefore, can effectively resist steganalysis tools. Experimental results show that our method has high capacity, safety and reliability. |
Tasks | Image Steganography |
Published | 2018-02-10 |
URL | http://arxiv.org/abs/1802.03528v1 |
http://arxiv.org/pdf/1802.03528v1.pdf | |
PWC | https://paperswithcode.com/paper/coverless-information-hiding-based-on-1 |
Repo | |
Framework | |
Approximate k-NN Graph Construction: a Generic Online Approach
Title | Approximate k-NN Graph Construction: a Generic Online Approach |
Authors | Wan-Lei Zhao |
Abstract | Nearest neighbor search and k-nearest neighbor graph construction are two fundamental issues arise from many disciplines such as information retrieval, data-mining and machine learning. Despite continuous efforts have been taken in the last several decades, these two issues remain challenging. They become more and more imminent given the big data emerge in various fields in recent years. In this paper, a simple but effective solution both for k-nearest neighbor search and k-nearest neighbor graph construction is presented. These two issues are addressed jointly in our solution. On one hand, the k-nearest neighbor graph construction is treated as a search task. Each sample along with its k-nearest neighbors are joined into the k-nearest neighbor graph by performing the nearest neighbor search sequentially on the graph under construction. On the other hand, the built k-nearest neighbor graph is used to support k-nearest neighbor search. Since the graph is built online, the dynamic update on the graph, which is not desirable from most of the existing solutions, is supported. This solution is feasible for various distance measures. Its effectiveness both as k-nearest neighbor construction and k-nearest neighbor search approaches is verified across various datasets in different scales, various dimensions and under different metrics. |
Tasks | graph construction, Information Retrieval |
Published | 2018-04-09 |
URL | https://arxiv.org/abs/1804.03032v4 |
https://arxiv.org/pdf/1804.03032v4.pdf | |
PWC | https://paperswithcode.com/paper/k-nn-graph-construction-a-generic-online |
Repo | |
Framework | |
Learnable Exposure Fusion for Dynamic Scenes
Title | Learnable Exposure Fusion for Dynamic Scenes |
Authors | Fahd Bouzaraa, Ibrahim Halfaoui, Onay Urfalioglu |
Abstract | In this paper, we focus on Exposure Fusion (EF) [ExposFusi2] for dynamic scenes. The task is to fuse multiple images obtained by exposure bracketing to create an image which comprises a high level of details. Typically, such images are not possible to obtain directly from a camera due to hardware limitations, e.g., a limited dynamic range of the sensor. A major problem of such tasks is that the images may not be spatially aligned due to scene motion or camera motion. It is known that the required alignment by image registration problems is ill-posed. In this case, the images to be aligned vary in their intensity range, which makes the problem even more difficult. To address the mentioned problems, we propose an end-to-end \emph{Convolutional Neural Network} (CNN) based approach to learn to estimate exposure fusion from $2$ and $3$ Low Dynamic Range (LDR) images depicting different scene contents. To the best of our knowledge, no efficient and robust CNN-based end-to-end approach can be found in the literature for this kind of problem. The idea is to create a dataset with perfectly aligned LDR images to obtain ground-truth exposure fusion images. At the same time, we obtain additional LDR images with some motion, having the same exposure fusion ground-truth as the perfectly aligned LDR images. This way, we can train an end-to-end CNN having misaligned LDR input images, but with a proper ground truth exposure fusion image. We propose a specific CNN-architecture to solve this problem. In various experiments, we show that the proposed approach yields excellent results. |
Tasks | Image Registration |
Published | 2018-04-04 |
URL | http://arxiv.org/abs/1804.01611v1 |
http://arxiv.org/pdf/1804.01611v1.pdf | |
PWC | https://paperswithcode.com/paper/learnable-exposure-fusion-for-dynamic-scenes |
Repo | |
Framework | |