Paper Group ANR 578
Medical Image Retrieval using Deep Convolutional Neural Network. Multi-Task Learning for Contextual Bandits. Using Program Induction to Interpret Transition System Dynamics. Fine Grained Citation Span for References in Wikipedia. RUM: network Representation learning throUgh Multi-level structural information preservation. Analysis of supervised and …
Medical Image Retrieval using Deep Convolutional Neural Network
| Title | Medical Image Retrieval using Deep Convolutional Neural Network |
| Authors | Adnan Qayyum, Syed Muhammad Anwar, Muhammad Awais, Muhammad Majid |
| Abstract | With a widespread use of digital imaging data in hospitals, the size of medical image repositories is increasing rapidly. This causes difficulty in managing and querying these large databases leading to the need of content based medical image retrieval (CBMIR) systems. A major challenge in CBMIR systems is the semantic gap that exists between the low level visual information captured by imaging devices and high level semantic information perceived by human. The efficacy of such systems is more crucial in terms of feature representations that can characterize the high-level information completely. In this paper, we propose a framework of deep learning for CBMIR system by using deep Convolutional Neural Network (CNN) that is trained for classification of medical images. An intermodal dataset that contains twenty four classes and five modalities is used to train the network. The learned features and the classification results are used to retrieve medical images. For retrieval, best results are achieved when class based predictions are used. An average classification accuracy of 99.77% and a mean average precision of 0.69 is achieved for retrieval task. The proposed method is best suited to retrieve multimodal medical images for different body organs. |
| Tasks | Image Retrieval, Medical Image Retrieval |
| Published | 2017-03-24 |
| URL | http://arxiv.org/abs/1703.08472v1 |
| http://arxiv.org/pdf/1703.08472v1.pdf | |
| PWC | https://paperswithcode.com/paper/medical-image-retrieval-using-deep |
| Repo | |
| Framework | |
Multi-Task Learning for Contextual Bandits
| Title | Multi-Task Learning for Contextual Bandits |
| Authors | Aniket Anand Deshmukh, Urun Dogan, Clayton Scott |
| Abstract | Contextual bandits are a form of multi-armed bandit in which the agent has access to predictive side information (known as the context) for each arm at each time step, and have been used to model personalized news recommendation, ad placement, and other applications. In this work, we propose a multi-task learning framework for contextual bandit problems. Like multi-task learning in the batch setting, the goal is to leverage similarities in contexts for different arms so as to improve the agent’s ability to predict rewards from contexts. We propose an upper confidence bound-based multi-task learning algorithm for contextual bandits, establish a corresponding regret bound, and interpret this bound to quantify the advantages of learning in the presence of high task (arm) similarity. We also describe an effective scheme for estimating task similarity from data, and demonstrate our algorithm’s performance on several data sets. |
| Tasks | Multi-Armed Bandits, Multi-Task Learning |
| Published | 2017-05-24 |
| URL | http://arxiv.org/abs/1705.08618v1 |
| http://arxiv.org/pdf/1705.08618v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-task-learning-for-contextual-bandits |
| Repo | |
| Framework | |
Using Program Induction to Interpret Transition System Dynamics
| Title | Using Program Induction to Interpret Transition System Dynamics |
| Authors | Svetlin Penkov, Subramanian Ramamoorthy |
| Abstract | Explaining and reasoning about processes which underlie observed black-box phenomena enables the discovery of causal mechanisms, derivation of suitable abstract representations and the formulation of more robust predictions. We propose to learn high level functional programs in order to represent abstract models which capture the invariant structure in the observed data. We introduce the $\pi$-machine (program-induction machine) – an architecture able to induce interpretable LISP-like programs from observed data traces. We propose an optimisation procedure for program learning based on backpropagation, gradient descent and A* search. We apply the proposed method to two problems: system identification of dynamical systems and explaining the behaviour of a DQN agent. Our results show that the $\pi$-machine can efficiently induce interpretable programs from individual data traces. |
| Tasks | |
| Published | 2017-07-26 |
| URL | http://arxiv.org/abs/1708.00376v1 |
| http://arxiv.org/pdf/1708.00376v1.pdf | |
| PWC | https://paperswithcode.com/paper/using-program-induction-to-interpret |
| Repo | |
| Framework | |
Fine Grained Citation Span for References in Wikipedia
| Title | Fine Grained Citation Span for References in Wikipedia |
| Authors | Besnik Fetahu, Katja Markert, Avishek Anand |
| Abstract | \emph{Verifiability} is one of the core editing principles in Wikipedia, editors being encouraged to provide citations for the added content. For a Wikipedia article, determining the \emph{citation span} of a citation, i.e. what content is covered by a citation, is important as it helps decide for which content citations are still missing. We are the first to address the problem of determining the \emph{citation span} in Wikipedia articles. We approach this problem by classifying which textual fragments in an article are covered by a citation. We propose a sequence classification approach where for a paragraph and a citation, we determine the citation span at a fine-grained level. We provide a thorough experimental evaluation and compare our approach against baselines adopted from the scientific domain, where we show improvement for all evaluation metrics. |
| Tasks | |
| Published | 2017-07-23 |
| URL | http://arxiv.org/abs/1707.07278v1 |
| http://arxiv.org/pdf/1707.07278v1.pdf | |
| PWC | https://paperswithcode.com/paper/fine-grained-citation-span-for-references-in |
| Repo | |
| Framework | |
RUM: network Representation learning throUgh Multi-level structural information preservation
| Title | RUM: network Representation learning throUgh Multi-level structural information preservation |
| Authors | Yanlei Yu, Zhiwu Lu, Jiajun Liu, Guoping Zhao, Ji-Rong Wen, Kai Zheng |
| Abstract | We have witnessed the discovery of many techniques for network representation learning in recent years, ranging from encoding the context in random walks to embedding the lower order connections, to finding latent space representations with auto-encoders. However, existing techniques are looking mostly into the local structures in a network, while higher-level properties such as global community structures are often neglected. We propose a novel network representations learning model framework called RUM (network Representation learning throUgh Multi-level structural information preservation). In RUM, we incorporate three essential aspects of a node that capture a network’s characteristics in multiple levels: a node’s affiliated local triads, its neighborhood relationships, and its global community affiliations. Therefore the framework explicitly and comprehensively preserves the structural information of a network, extending the encoding process both to the local end of the structural information spectrum and to the global end. The framework is also flexible enough to take various community discovery algorithms as its preprocessor. Empirical results show that the representations learned by RUM have demonstrated substantial performance advantages in real-life tasks. |
| Tasks | Representation Learning |
| Published | 2017-10-08 |
| URL | http://arxiv.org/abs/1710.02836v1 |
| http://arxiv.org/pdf/1710.02836v1.pdf | |
| PWC | https://paperswithcode.com/paper/rum-network-representation-learning-through |
| Repo | |
| Framework | |
Analysis of supervised and semi-supervised GrowCut applied to segmentation of masses in mammography images
| Title | Analysis of supervised and semi-supervised GrowCut applied to segmentation of masses in mammography images |
| Authors | Filipe Rolim Cordeiro, Wellington Pinheiro dos Santos, Abel Guilhermino da Silva Filho |
| Abstract | Breast cancer is already one of the most common form of cancer worldwide. Mammography image analysis is still the most effective diagnostic method to promote the early detection of breast cancer. Accurately segmenting tumors in digital mammography images is important to improve diagnosis capabilities of health specialists and avoid misdiagnosis. In this work, we evaluate the feasibility of applying GrowCut to segment regions of tumor and we propose two GrowCut semi-supervised versions. All the analysis was performed by evaluating the application of segmentation techniques to a set of images obtained from the Mini-MIAS mammography image database. GrowCut segmentation was compared to Region Growing, Active Contours, Random Walks and Graph Cut techniques. Experiments showed that GrowCut, when compared to the other techniques, was able to acquire better results for the metrics analyzed. Moreover, the proposed semi-supervised versions of GrowCut was proved to have a clinically satisfactory quality of segmentation. |
| Tasks | |
| Published | 2017-12-20 |
| URL | http://arxiv.org/abs/1712.07312v1 |
| http://arxiv.org/pdf/1712.07312v1.pdf | |
| PWC | https://paperswithcode.com/paper/analysis-of-supervised-and-semi-supervised |
| Repo | |
| Framework | |
Predictive Analytics for Enhancing Travel Time Estimation in Navigation Apps of Apple, Google, and Microsoft
| Title | Predictive Analytics for Enhancing Travel Time Estimation in Navigation Apps of Apple, Google, and Microsoft |
| Authors | Pouria Amirian, Anahid Basiri, Jeremy Morley |
| Abstract | The explosive growth of the location-enabled devices coupled with the increasing use of Internet services has led to an increasing awareness of the importance and usage of geospatial information in many applications. The navigation apps (often called Maps), use a variety of available data sources to calculate and predict the travel time as well as several options for routing in public transportation, car or pedestrian modes. This paper evaluates the pedestrian mode of Maps apps in three major smartphone operating systems (Android, iOS and Windows Phone). In the paper, we will show that the Maps apps on iOS, Android and Windows Phone in pedestrian mode, predict travel time without learning from the individual’s movement profile. In addition, we will exemplify that those apps suffer from a specific data quality issue which relates to the absence of information about location and type of pedestrian crossings. Finally, we will illustrate learning from movement profile of individuals using various predictive analytics models to improve the accuracy of travel time estimation. |
| Tasks | |
| Published | 2017-05-23 |
| URL | http://arxiv.org/abs/1705.08509v1 |
| http://arxiv.org/pdf/1705.08509v1.pdf | |
| PWC | https://paperswithcode.com/paper/predictive-analytics-for-enhancing-travel |
| Repo | |
| Framework | |
Fingerprint Spoof Buster
| Title | Fingerprint Spoof Buster |
| Authors | Tarang Chugh, Kai Cao, Anil K. Jain |
| Abstract | The primary purpose of a fingerprint recognition system is to ensure a reliable and accurate user authentication, but the security of the recognition system itself can be jeopardized by spoof attacks. This study addresses the problem of developing accurate, generalizable, and efficient algorithms for detecting fingerprint spoof attacks. Specifically, we propose a deep convolutional neural network based approach utilizing local patches centered and aligned using fingerprint minutiae. Experimental results on three public-domain LivDet datasets (2011, 2013, and 2015) show that the proposed approach provides state-of-the-art accuracies in fingerprint spoof detection for intra-sensor, cross-material, cross-sensor, as well as cross-dataset testing scenarios. For example, in LivDet 2015, the proposed approach achieves 99.03% average accuracy over all sensors compared to 95.51% achieved by the LivDet 2015 competition winners. Additionally, two new fingerprint presentation attack datasets containing more than 20,000 images, using two different fingerprint readers, and over 12 different spoof fabrication materials are collected. We also present a graphical user interface, called Fingerprint Spoof Buster, that allows the operator to visually examine the local regions of the fingerprint highlighted as live or spoof, instead of relying on only a single score as output by the traditional approaches. |
| Tasks | |
| Published | 2017-12-12 |
| URL | http://arxiv.org/abs/1712.04489v1 |
| http://arxiv.org/pdf/1712.04489v1.pdf | |
| PWC | https://paperswithcode.com/paper/fingerprint-spoof-buster |
| Repo | |
| Framework | |
Hashed Binary Search Sampling for Convolutional Network Training with Large Overhead Image Patches
| Title | Hashed Binary Search Sampling for Convolutional Network Training with Large Overhead Image Patches |
| Authors | Dalton Lunga, Lexie Yang, Budhendra Bhaduri |
| Abstract | Very large overhead imagery associated with ground truth maps has the potential to generate billions of training image patches for machine learning algorithms. However, random sampling selection criteria often leads to redundant and noisy-image patches for model training. With minimal research efforts behind this challenge, the current status spells missed opportunities to develop supervised learning algorithms that generalize over wide geographical scenes. In addition, much of the computational cycles for large scale machine learning are poorly spent crunching through noisy and redundant image patches. We demonstrate a potential framework to address these challenges specifically, while evaluating a human settlement detection task. A novel binary search tree sampling scheme is fused with a kernel based hashing procedure that maps image patches into hash-buckets using binary codes generated from image content. The framework exploits inherent redundancy within billions of image patches to promote mostly high variance preserving samples for accelerating algorithmic training and increasing model generalization. |
| Tasks | |
| Published | 2017-07-18 |
| URL | http://arxiv.org/abs/1707.05685v1 |
| http://arxiv.org/pdf/1707.05685v1.pdf | |
| PWC | https://paperswithcode.com/paper/hashed-binary-search-sampling-for |
| Repo | |
| Framework | |
On Data-Dependent Random Features for Improved Generalization in Supervised Learning
| Title | On Data-Dependent Random Features for Improved Generalization in Supervised Learning |
| Authors | Shahin Shahrampour, Ahmad Beirami, Vahid Tarokh |
| Abstract | The randomized-feature approach has been successfully employed in large-scale kernel approximation and supervised learning. The distribution from which the random features are drawn impacts the number of features required to efficiently perform a learning task. Recently, it has been shown that employing data-dependent randomization improves the performance in terms of the required number of random features. In this paper, we are concerned with the randomized-feature approach in supervised learning for good generalizability. We propose the Energy-based Exploration of Random Features (EERF) algorithm based on a data-dependent score function that explores the set of possible features and exploits the promising regions. We prove that the proposed score function with high probability recovers the spectrum of the best fit within the model class. Our empirical results on several benchmark datasets further verify that our method requires smaller number of random features to achieve a certain generalization error compared to the state-of-the-art while introducing negligible pre-processing overhead. EERF can be implemented in a few lines of code and requires no additional tuning parameters. |
| Tasks | |
| Published | 2017-12-19 |
| URL | http://arxiv.org/abs/1712.07102v1 |
| http://arxiv.org/pdf/1712.07102v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-data-dependent-random-features-for |
| Repo | |
| Framework | |
A Parameterized Approach to Personalized Variable Length Summarization of Soccer Matches
| Title | A Parameterized Approach to Personalized Variable Length Summarization of Soccer Matches |
| Authors | Mohak Sukhwani, Ravi Kothari |
| Abstract | We present a parameterized approach to produce personalized variable length summaries of soccer matches. Our approach is based on temporally segmenting the soccer video into ‘plays’, associating a user-specifiable ‘utility’ for each type of play and using ‘bin-packing’ to select a subset of the plays that add up to the desired length while maximizing the overall utility (volume in bin-packing terms). Our approach systematically allows a user to override the default weights assigned to each type of play with individual preferences and thus see a highly personalized variable length summarization of soccer matches. We demonstrate our approach based on the output of an end-to-end pipeline that we are building to produce such summaries. Though aspects of the overall end-to-end pipeline are human assisted at present, the results clearly show that the proposed approach is capable of producing semantically meaningful and compelling summaries. Besides the obvious use of producing summaries of superior league matches for news broadcasts, we anticipate our work to promote greater awareness of the local matches and junior leagues by producing consumable summaries of them. |
| Tasks | |
| Published | 2017-06-28 |
| URL | http://arxiv.org/abs/1706.09193v1 |
| http://arxiv.org/pdf/1706.09193v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-parameterized-approach-to-personalized |
| Repo | |
| Framework | |
A Multi-view Context-aware Approach to Android Malware Detection and Malicious Code Localization
| Title | A Multi-view Context-aware Approach to Android Malware Detection and Malicious Code Localization |
| Authors | Annamalai Narayanan, Mahinthan Chandramohan, Lihui Chen, Yang Liu |
| Abstract | Existing Android malware detection approaches use a variety of features such as security sensitive APIs, system calls, control-flow structures and information flows in conjunction with Machine Learning classifiers to achieve accurate detection. Each of these feature sets provides a unique semantic perspective (or view) of apps’ behaviours with inherent strengths and limitations. Meaning, some views are more amenable to detect certain attacks but may not be suitable to characterise several other attacks. Most of the existing malware detection approaches use only one (or a selected few) of the aforementioned feature sets which prevent them from detecting a vast majority of attacks. Addressing this limitation, we propose MKLDroid, a unified framework that systematically integrates multiple views of apps for performing comprehensive malware detection and malicious code localisation. The rationale is that, while a malware app can disguise itself in some views, disguising in every view while maintaining malicious intent will be much harder. MKLDroid uses a graph kernel to capture structural and contextual information from apps’ dependency graphs and identify malice code patterns in each view. Subsequently, it employs Multiple Kernel Learning (MKL) to find a weighted combination of the views which yields the best detection accuracy. Besides multi-view learning, MKLDroid’s unique and salient trait is its ability to locate fine-grained malice code portions in dependency graphs (e.g., methods/classes). Through our large-scale experiments on several datasets (incl. wild apps), we demonstrate that MKLDroid outperforms three state-of-the-art techniques consistently, in terms of accuracy while maintaining comparable efficiency. In our malicious code localisation experiments on a dataset of repackaged malware, MKLDroid was able to identify all the malice classes with 94% average recall. |
| Tasks | Android Malware Detection, Malware Detection, MULTI-VIEW LEARNING |
| Published | 2017-04-06 |
| URL | http://arxiv.org/abs/1704.01759v2 |
| http://arxiv.org/pdf/1704.01759v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-multi-view-context-aware-approach-to |
| Repo | |
| Framework | |
Fast-Slow Recurrent Neural Networks
| Title | Fast-Slow Recurrent Neural Networks |
| Authors | Asier Mujika, Florian Meier, Angelika Steger |
| Abstract | Processing sequential data of variable length is a major challenge in a wide range of applications, such as speech recognition, language modeling, generative image modeling and machine translation. Here, we address this challenge by proposing a novel recurrent neural network (RNN) architecture, the Fast-Slow RNN (FS-RNN). The FS-RNN incorporates the strengths of both multiscale RNNs and deep transition RNNs as it processes sequential data on different timescales and learns complex transition functions from one time step to the next. We evaluate the FS-RNN on two character level language modeling data sets, Penn Treebank and Hutter Prize Wikipedia, where we improve state of the art results to $1.19$ and $1.25$ bits-per-character (BPC), respectively. In addition, an ensemble of two FS-RNNs achieves $1.20$ BPC on Hutter Prize Wikipedia outperforming the best known compression algorithm with respect to the BPC measure. We also present an empirical investigation of the learning and network dynamics of the FS-RNN, which explains the improved performance compared to other RNN architectures. Our approach is general as any kind of RNN cell is a possible building block for the FS-RNN architecture, and thus can be flexibly applied to different tasks. |
| Tasks | Language Modelling, Machine Translation, Speech Recognition |
| Published | 2017-05-24 |
| URL | http://arxiv.org/abs/1705.08639v2 |
| http://arxiv.org/pdf/1705.08639v2.pdf | |
| PWC | https://paperswithcode.com/paper/fast-slow-recurrent-neural-networks |
| Repo | |
| Framework | |
Geometry of Policy Improvement
| Title | Geometry of Policy Improvement |
| Authors | Guido Montufar, Johannes Rauh |
| Abstract | We investigate the geometry of optimal memoryless time independent decision making in relation to the amount of information that the acting agent has about the state of the system. We show that the expected long term reward, discounted or per time step, is maximized by policies that randomize among at most $k$ actions whenever at most $k$ world states are consistent with the agent’s observation. Moreover, we show that the expected reward per time step can be studied in terms of the expected discounted reward. Our main tool is a geometric version of the policy improvement lemma, which identifies a polyhedral cone of policy changes in which the state value function increases for all states. |
| Tasks | Decision Making |
| Published | 2017-04-06 |
| URL | http://arxiv.org/abs/1704.01785v1 |
| http://arxiv.org/pdf/1704.01785v1.pdf | |
| PWC | https://paperswithcode.com/paper/geometry-of-policy-improvement |
| Repo | |
| Framework | |
Multi-task Self-Supervised Visual Learning
| Title | Multi-task Self-Supervised Visual Learning |
| Authors | Carl Doersch, Andrew Zisserman |
| Abstract | We investigate methods for combining multiple self-supervised tasks–i.e., supervised tasks where data can be collected without manual labeling–in order to train a single visual representation. First, we provide an apples-to-apples comparison of four different self-supervised tasks using the very deep ResNet-101 architecture. We then combine tasks to jointly train a network. We also explore lasso regularization to encourage the network to factorize the information in its representation, and methods for “harmonizing” network inputs in order to learn a more unified representation. We evaluate all methods on ImageNet classification, PASCAL VOC detection, and NYU depth prediction. Our results show that deeper networks work better, and that combining tasks–even via a naive multi-head architecture–always improves performance. Our best joint network nearly matches the PASCAL performance of a model pre-trained on ImageNet classification, and matches the ImageNet network on NYU depth prediction. |
| Tasks | Depth Estimation |
| Published | 2017-08-25 |
| URL | http://arxiv.org/abs/1708.07860v1 |
| http://arxiv.org/pdf/1708.07860v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-task-self-supervised-visual-learning |
| Repo | |
| Framework | |
