Paper Group ANR 316
Accelerating the Super-Resolution Convolutional Neural Network. Deep Convolutional Neural Networks for Microscopy-Based Point of Care Diagnostics. Inverted Bilingual Topic Models for Lexicon Extraction from Non-parallel Data. Deep Learning a Grasp Function for Grasping under Gripper Pose Uncertainty. Recent Advances in Transient Imaging: A Computer …
Accelerating the Super-Resolution Convolutional Neural Network
| Title | Accelerating the Super-Resolution Convolutional Neural Network |
| Authors | Chao Dong, Chen Change Loy, Xiaoou Tang |
| Abstract | As a successful deep model applied in image super-resolution (SR), the Super-Resolution Convolutional Neural Network (SRCNN) has demonstrated superior performance to the previous hand-crafted models either in speed and restoration quality. However, the high computational cost still hinders it from practical usage that demands real-time performance (24 fps). In this paper, we aim at accelerating the current SRCNN, and propose a compact hourglass-shape CNN structure for faster and better SR. We re-design the SRCNN structure mainly in three aspects. First, we introduce a deconvolution layer at the end of the network, then the mapping is learned directly from the original low-resolution image (without interpolation) to the high-resolution one. Second, we reformulate the mapping layer by shrinking the input feature dimension before mapping and expanding back afterwards. Third, we adopt smaller filter sizes but more mapping layers. The proposed model achieves a speed up of more than 40 times with even superior restoration quality. Further, we present the parameter settings that can achieve real-time performance on a generic CPU while still maintaining good performance. A corresponding transfer strategy is also proposed for fast training and testing across different upscaling factors. |
| Tasks | Image Super-Resolution, Super-Resolution |
| Published | 2016-08-01 |
| URL | http://arxiv.org/abs/1608.00367v1 |
| http://arxiv.org/pdf/1608.00367v1.pdf | |
| PWC | https://paperswithcode.com/paper/accelerating-the-super-resolution |
| Repo | |
| Framework | |
Deep Convolutional Neural Networks for Microscopy-Based Point of Care Diagnostics
| Title | Deep Convolutional Neural Networks for Microscopy-Based Point of Care Diagnostics |
| Authors | John A. Quinn, Rose Nakasi, Pius K. B. Mugagga, Patrick Byanyima, William Lubega, Alfred Andama |
| Abstract | Point of care diagnostics using microscopy and computer vision methods have been applied to a number of practical problems, and are particularly relevant to low-income, high disease burden areas. However, this is subject to the limitations in sensitivity and specificity of the computer vision methods used. In general, deep learning has recently revolutionised the field of computer vision, in some cases surpassing human performance for other object recognition tasks. In this paper, we evaluate the performance of deep convolutional neural networks on three different microscopy tasks: diagnosis of malaria in thick blood smears, tuberculosis in sputum samples, and intestinal parasite eggs in stool samples. In all cases accuracy is very high and substantially better than an alternative approach more representative of traditional medical imaging techniques. |
| Tasks | Object Recognition |
| Published | 2016-08-09 |
| URL | http://arxiv.org/abs/1608.02989v1 |
| http://arxiv.org/pdf/1608.02989v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-convolutional-neural-networks-for-5 |
| Repo | |
| Framework | |
Inverted Bilingual Topic Models for Lexicon Extraction from Non-parallel Data
| Title | Inverted Bilingual Topic Models for Lexicon Extraction from Non-parallel Data |
| Authors | Tengfei Ma, Tetsuya Nasukawa |
| Abstract | Topic models have been successfully applied in lexicon extraction. However, most previous methods are limited to document-aligned data. In this paper, we try to address two challenges of applying topic models to lexicon extraction in non-parallel data: 1) hard to model the word relationship and 2) noisy seed dictionary. To solve these two challenges, we propose two new bilingual topic models to better capture the semantic information of each word while discriminating the multiple translations in a noisy seed dictionary. We extend the scope of topic models by inverting the roles of “word” and “document”. In addition, to solve the problem of noise in seed dictionary, we incorporate the probability of translation selection in our models. Moreover, we also propose an effective measure to evaluate the similarity of words in different languages and select the optimal translation pairs. Experimental results using real world data demonstrate the utility and efficacy of the proposed models. |
| Tasks | Topic Models |
| Published | 2016-12-21 |
| URL | http://arxiv.org/abs/1612.07215v2 |
| http://arxiv.org/pdf/1612.07215v2.pdf | |
| PWC | https://paperswithcode.com/paper/inverted-bilingual-topic-models-for-lexicon |
| Repo | |
| Framework | |
Deep Learning a Grasp Function for Grasping under Gripper Pose Uncertainty
| Title | Deep Learning a Grasp Function for Grasping under Gripper Pose Uncertainty |
| Authors | Edward Johns, Stefan Leutenegger, Andrew J. Davison |
| Abstract | This paper presents a new method for parallel-jaw grasping of isolated objects from depth images, under large gripper pose uncertainty. Whilst most approaches aim to predict the single best grasp pose from an image, our method first predicts a score for every possible grasp pose, which we denote the grasp function. With this, it is possible to achieve grasping robust to the gripper’s pose uncertainty, by smoothing the grasp function with the pose uncertainty function. Therefore, if the single best pose is adjacent to a region of poor grasp quality, that pose will no longer be chosen, and instead a pose will be chosen which is surrounded by a region of high grasp quality. To learn this function, we train a Convolutional Neural Network which takes as input a single depth image of an object, and outputs a score for each grasp pose across the image. Training data for this is generated by use of physics simulation and depth image simulation with 3D object meshes, to enable acquisition of sufficient data without requiring exhaustive real-world experiments. We evaluate with both synthetic and real experiments, and show that the learned grasp score is more robust to gripper pose uncertainty than when this uncertainty is not accounted for. |
| Tasks | |
| Published | 2016-08-07 |
| URL | http://arxiv.org/abs/1608.02239v1 |
| http://arxiv.org/pdf/1608.02239v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-a-grasp-function-for-grasping |
| Repo | |
| Framework | |
Recent Advances in Transient Imaging: A Computer Graphics and Vision Perspective
| Title | Recent Advances in Transient Imaging: A Computer Graphics and Vision Perspective |
| Authors | Adrian Jarabo, Belen Masia, Julio Marco, Diego Gutierrez |
| Abstract | Transient imaging has recently made a huge impact in the computer graphics and computer vision fields. By capturing, reconstructing, or simulating light transport at extreme temporal resolutions, researchers have proposed novel techniques to show movies of light in motion, see around corners, detect objects in highly-scattering media, or infer material properties from a distance, to name a few. The key idea is to leverage the wealth of information in the temporal domain at the pico or nanosecond resolution, information usually lost during the capture-time temporal integration. This paper presents recent advances in this field of transient imaging from a graphics and vision perspective, including capture techniques, analysis, applications and simulation. |
| Tasks | |
| Published | 2016-11-03 |
| URL | http://arxiv.org/abs/1611.00939v1 |
| http://arxiv.org/pdf/1611.00939v1.pdf | |
| PWC | https://paperswithcode.com/paper/recent-advances-in-transient-imaging-a |
| Repo | |
| Framework | |
Imaging around corners with single-pixel detector by computational ghost imaging
| Title | Imaging around corners with single-pixel detector by computational ghost imaging |
| Authors | Bin Bai, Jianbin Liu, Yu Zhou, Songlin Zhang, Yuchen He, Zhuo Xu |
| Abstract | We have designed a single-pixel camera with imaging around corners based on computational ghost imaging. It can obtain the image of an object when the camera cannot look at the object directly. Our imaging system explores the fact that a bucket detector in a ghost imaging setup has no spatial resolution capability. A series of experiments have been designed to confirm our predictions. This camera has potential applications for imaging around corner or other similar environments where the object cannot be observed directly. |
| Tasks | |
| Published | 2016-12-08 |
| URL | http://arxiv.org/abs/1612.07120v1 |
| http://arxiv.org/pdf/1612.07120v1.pdf | |
| PWC | https://paperswithcode.com/paper/imaging-around-corners-with-single-pixel |
| Repo | |
| Framework | |
A Multiple Kernel Learning Approach for Human Behavioral Task Classification using STN-LFP Signal
| Title | A Multiple Kernel Learning Approach for Human Behavioral Task Classification using STN-LFP Signal |
| Authors | Hosein M. Golshan, Adam O. Hebb, Sara J. Hanrahan, Joshua Nedrud, Mohammad H. Mahoor |
| Abstract | Deep Brain Stimulation (DBS) has gained increasing attention as an effective method to mitigate Parkinsons disease (PD) disorders. Existing DBS systems are open-loop such that the system parameters are not adjusted automatically based on patients behavior. Classification of human behavior is an important step in the design of the next generation of DBS systems that are closed-loop. This paper presents a classification approach to recognize such behavioral tasks using the subthalamic nucleus (STN) Local Field Potential (LFP) signals. In our approach, we use the time-frequency representation (spectrogram) of the raw LFP signals recorded from left and right STNs as the feature vectors. Then these features are combined together via Support Vector Machines (SVM) with Multiple Kernel Learning (MKL) formulation. The MKL-based classification method is utilized to classify different tasks: button press, mouth movement, speech, and arm movement. Our experiments show that the lp-norm MKL significantly outperforms single kernel SVM-based classifiers in classifying behavioral tasks of five subjects even using signals acquired with a low sampling rate of 10 Hz. This leads to a lower computational cost. |
| Tasks | |
| Published | 2016-07-27 |
| URL | http://arxiv.org/abs/1607.07987v1 |
| http://arxiv.org/pdf/1607.07987v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-multiple-kernel-learning-approach-for-human |
| Repo | |
| Framework | |
NodIO, a JavaScript framework for volunteer-based evolutionary algorithms : first results
| Title | NodIO, a JavaScript framework for volunteer-based evolutionary algorithms : first results |
| Authors | Juan-J. Merelo, Mario García-Valdez, Pedro A. Castillo, Pablo García-Sánchez, P. de las Cuevas, Nuria Rico |
| Abstract | JavaScript is an interpreted language mainly known for its inclusion in web browsers, making them a container for rich Internet based applications. This has inspired its use, for a long time, as a tool for evolutionary algorithms, mainly so in browser-based volunteer computing environments. Several libraries have also been published so far and are in use. However, the last years have seen a resurgence of interest in the language, becoming one of the most popular and thus spawning the improvement of its implementations, which are now the foundation of many new client-server applications. We present such an application for running distributed volunteer-based evolutionary algorithm experiments, and we make a series of measurements to establish the speed of JavaScript in evolutionary algorithms that can serve as a baseline for comparison with other distributed computing experiments. These experiments use different integer and floating point problems, and prove that the speed of JavaScript is actually competitive with other languages commonly used by the evolutionary algorithm practitioner. |
| Tasks | |
| Published | 2016-01-07 |
| URL | http://arxiv.org/abs/1601.01607v1 |
| http://arxiv.org/pdf/1601.01607v1.pdf | |
| PWC | https://paperswithcode.com/paper/nodio-a-javascript-framework-for-volunteer |
| Repo | |
| Framework | |
LSTM-Based System-Call Language Modeling and Robust Ensemble Method for Designing Host-Based Intrusion Detection Systems
| Title | LSTM-Based System-Call Language Modeling and Robust Ensemble Method for Designing Host-Based Intrusion Detection Systems |
| Authors | Gyuwan Kim, Hayoon Yi, Jangho Lee, Yunheung Paek, Sungroh Yoon |
| Abstract | In computer security, designing a robust intrusion detection system is one of the most fundamental and important problems. In this paper, we propose a system-call language-modeling approach for designing anomaly-based host intrusion detection systems. To remedy the issue of high false-alarm rates commonly arising in conventional methods, we employ a novel ensemble method that blends multiple thresholding classifiers into a single one, making it possible to accumulate ‘highly normal’ sequences. The proposed system-call language model has various advantages leveraged by the fact that it can learn the semantic meaning and interactions of each system call that existing methods cannot effectively consider. Through diverse experiments on public benchmark datasets, we demonstrate the validity and effectiveness of the proposed method. Moreover, we show that our model possesses high portability, which is one of the key aspects of realizing successful intrusion detection systems. |
| Tasks | Intrusion Detection, Language Modelling |
| Published | 2016-11-06 |
| URL | http://arxiv.org/abs/1611.01726v1 |
| http://arxiv.org/pdf/1611.01726v1.pdf | |
| PWC | https://paperswithcode.com/paper/lstm-based-system-call-language-modeling-and |
| Repo | |
| Framework | |
Attribute Learning for Network Intrusion Detection
| Title | Attribute Learning for Network Intrusion Detection |
| Authors | Jorge Luis Rivero Pérez, Bernardete Ribeiro |
| Abstract | Network intrusion detection is one of the most visible uses for Big Data analytics. One of the main problems in this application is the constant rise of new attacks. This scenario, characterized by the fact that not enough labeled examples are available for the new classes of attacks is hardly addressed by traditional machine learning approaches. New findings on the capabilities of Zero-Shot learning (ZSL) approach makes it an interesting solution for this problem because it has the ability to classify instances of unseen classes. ZSL has inherently two stages: the attribute learning and the inference stage. In this paper we propose a new algorithm for the attribute learning stage of ZSL. The idea is to learn new values for the attributes based on decision trees (DT). Our results show that based on the rules extracted from the DT a better distribution for the attribute values can be found. We also propose an experimental setup for the evaluation of ZSL on network intrusion detection (NID). |
| Tasks | Intrusion Detection, Network Intrusion Detection, Zero-Shot Learning |
| Published | 2016-07-28 |
| URL | http://arxiv.org/abs/1607.08634v1 |
| http://arxiv.org/pdf/1607.08634v1.pdf | |
| PWC | https://paperswithcode.com/paper/attribute-learning-for-network-intrusion |
| Repo | |
| Framework | |
Fourier Analysis and q-Gaussian Functions: Analytical and Numerical Results
| Title | Fourier Analysis and q-Gaussian Functions: Analytical and Numerical Results |
| Authors | Paulo Sérgio Silva Rodrigues, Gilson Antonio Giraldi |
| Abstract | It is a consensus in signal processing that the Gaussian kernel and its partial derivatives enable the development of robust algorithms for feature detection. Fourier analysis and convolution theory have central role in such development. In this paper we collect theoretical elements to follow this avenue but using the q-Gaussian kernel that is a nonextensive generalization of the Gaussian one. Firstly, we review some theoretical elements behind the one-dimensional q-Gaussian and its Fourier transform. Then, we consider the two-dimensional q-Gaussian and we highlight the issues behind its analytical Fourier transform computation. We analyze the q-Gaussian kernel in the space and Fourier domains using the concepts of space window, cut-off frequency, and the Heisenberg inequality. |
| Tasks | |
| Published | 2016-05-02 |
| URL | http://arxiv.org/abs/1605.00452v1 |
| http://arxiv.org/pdf/1605.00452v1.pdf | |
| PWC | https://paperswithcode.com/paper/fourier-analysis-and-q-gaussian-functions |
| Repo | |
| Framework | |
Joint Event Detection and Entity Resolution: a Virtuous Cycle
| Title | Joint Event Detection and Entity Resolution: a Virtuous Cycle |
| Authors | Matthias Galle, Jean-Michel Renders, Guillaume Jacquet |
| Abstract | Clustering web documents has numerous applications, such as aggregating news articles into meaningful events, detecting trends and hot topics on the Web, preserving diversity in search results, etc. At the same time, the importance of named entities and, in particular, the ability to recognize them and to solve the associated co-reference resolution problem are widely recognized as key enabling factors when mining, aggregating and comparing content on the Web. Instead of considering these two problems separately, we propose in this paper a method that tackles jointly the problem of clustering news articles into events and cross-document co-reference resolution of named entities. The co-occurrence of named entities in the same clusters is used as an additional signal to decide whether two referents should be merged into one entity. These refined entities can in turn be used as enhanced features to re-cluster the documents and then be refined again, entering into a virtuous cycle that improves simultaneously the performances of both tasks. We implemented a prototype system and report results using the TDT5 collection of news articles, demonstrating the potential of our approach. |
| Tasks | Entity Resolution |
| Published | 2016-07-18 |
| URL | http://arxiv.org/abs/1607.05142v1 |
| http://arxiv.org/pdf/1607.05142v1.pdf | |
| PWC | https://paperswithcode.com/paper/joint-event-detection-and-entity-resolution-a |
| Repo | |
| Framework | |
Towards Better Analysis of Deep Convolutional Neural Networks
| Title | Towards Better Analysis of Deep Convolutional Neural Networks |
| Authors | Mengchen Liu, Jiaxin Shi, Zhen Li, Chongxuan Li, Jun Zhu, Shixia Liu |
| Abstract | Deep convolutional neural networks (CNNs) have achieved breakthrough performance in many pattern recognition tasks such as image classification. However, the development of high-quality deep models typically relies on a substantial amount of trial-and-error, as there is still no clear understanding of when and why a deep model works. In this paper, we present a visual analytics approach for better understanding, diagnosing, and refining deep CNNs. We formulate a deep CNN as a directed acyclic graph. Based on this formulation, a hybrid visualization is developed to disclose the multiple facets of each neuron and the interactions between them. In particular, we introduce a hierarchical rectangle packing algorithm and a matrix reordering algorithm to show the derived features of a neuron cluster. We also propose a biclustering-based edge bundling method to reduce visual clutter caused by a large number of connections between neurons. We evaluated our method on a set of CNNs and the results are generally favorable. |
| Tasks | Image Classification |
| Published | 2016-04-24 |
| URL | http://arxiv.org/abs/1604.07043v3 |
| http://arxiv.org/pdf/1604.07043v3.pdf | |
| PWC | https://paperswithcode.com/paper/towards-better-analysis-of-deep-convolutional |
| Repo | |
| Framework | |
Robust Downbeat Tracking Using an Ensemble of Convolutional Networks
| Title | Robust Downbeat Tracking Using an Ensemble of Convolutional Networks |
| Authors | S. Durand, J. P. Bello, B. David, G. Richard |
| Abstract | In this paper, we present a novel state of the art system for automatic downbeat tracking from music signals. The audio signal is first segmented in frames which are synchronized at the tatum level of the music. We then extract different kind of features based on harmony, melody, rhythm and bass content to feed convolutional neural networks that are adapted to take advantage of each feature characteristics. This ensemble of neural networks is combined to obtain one downbeat likelihood per tatum. The downbeat sequence is finally decoded with a flexible and efficient temporal model which takes advantage of the metrical continuity of a song. We then perform an evaluation of our system on a large base of 9 datasets, compare its performance to 4 other published algorithms and obtain a significant increase of 16.8 percent points compared to the second best system, for altogether a moderate cost in test and training. The influence of each step of the method is studied to show its strengths and shortcomings. |
| Tasks | |
| Published | 2016-05-26 |
| URL | http://arxiv.org/abs/1605.08396v1 |
| http://arxiv.org/pdf/1605.08396v1.pdf | |
| PWC | https://paperswithcode.com/paper/robust-downbeat-tracking-using-an-ensemble-of |
| Repo | |
| Framework | |
Coarse2Fine: Two-Layer Fusion For Image Retrieval
| Title | Coarse2Fine: Two-Layer Fusion For Image Retrieval |
| Authors | Gaipeng Kong, Le Dong, Wenpu Dong, Liang Zheng, Qi Tian |
| Abstract | This paper addresses the problem of large-scale image retrieval. We propose a two-layer fusion method which takes advantage of global and local cues and ranks database images from coarse to fine (C2F). Departing from the previous methods fusing multiple image descriptors simultaneously, C2F is featured by a layered procedure composed by filtering and refining. In particular, C2F consists of three components. 1) Distractor filtering. With holistic representations, noise images are filtered out from the database, so the number of candidate images to be used for comparison with the query can be greatly reduced. 2) Adaptive weighting. For a certain query, the similarity of candidate images can be estimated by holistic similarity scores in complementary to the local ones. 3) Candidate refining. Accurate retrieval is conducted via local features, combining the pre-computed adaptive weights. Experiments are presented on two benchmarks, \emph{i.e.,} Holidays and Ukbench datasets. We show that our method outperforms recent fusion methods in terms of storage consumption and computation complexity, and that the accuracy is competitive to the state-of-the-arts. |
| Tasks | Image Retrieval |
| Published | 2016-07-04 |
| URL | http://arxiv.org/abs/1607.00719v1 |
| http://arxiv.org/pdf/1607.00719v1.pdf | |
| PWC | https://paperswithcode.com/paper/coarse2fine-two-layer-fusion-for-image |
| Repo | |
| Framework | |
