Paper Group ANR 301
Live Target Detection with Deep Learning Neural Network and Unmanned Aerial Vehicle on Android Mobile Device. Scalar Quantization as Sparse Least Square Optimization. Constructing Ontology-Based Cancer Treatment Decision Support System with Case-Based Reasoning. WHInter: A Working set algorithm for High-dimensional sparse second order Interaction m …
Live Target Detection with Deep Learning Neural Network and Unmanned Aerial Vehicle on Android Mobile Device
| Title | Live Target Detection with Deep Learning Neural Network and Unmanned Aerial Vehicle on Android Mobile Device |
| Authors | Ali Canberk Anar, Erkan Bostanci, Mehmet Serdar Guzel |
| Abstract | This paper describes the stages faced during the development of an Android program which obtains and decodes live images from DJI Phantom 3 Professional Drone and implements certain features of the TensorFlow Android Camera Demo application. Test runs were made and outputs of the application were noted. A lake was classified as seashore, breakwater and pier with the proximities of 24.44%, 21.16% and 12.96% respectfully. The joystick of the UAV controller and laptop keyboard was classified with the proximities of 19.10% and 13.96% respectfully. The laptop monitor was classified as screen, monitor and television with the proximities of 18.77%, 14.76% and 14.00% respectfully. The computer used during the development of this study was classified as notebook and laptop with the proximities of 20.04% and 11.68% respectfully. A tractor parked at a parking lot was classified with the proximity of 12.88%. A group of cars in the same parking lot were classified as sports car, racer and convertible with the proximities of 31.75%, 18.64% and 13.45% respectfully at an inference time of 851ms. |
| Tasks | |
| Published | 2018-03-19 |
| URL | http://arxiv.org/abs/1803.07015v2 |
| http://arxiv.org/pdf/1803.07015v2.pdf | |
| PWC | https://paperswithcode.com/paper/live-target-detection-with-deep-learning |
| Repo | |
| Framework | |
Scalar Quantization as Sparse Least Square Optimization
| Title | Scalar Quantization as Sparse Least Square Optimization |
| Authors | Chen Wang, Xiaomei Yang, Shaomin Fei, Kai Zhou, Xiaofeng Gong, Miao Du, Ruisen Luo |
| Abstract | Quantization can be used to form new vectors/matrices with shared values close to the original. In recent years, the popularity of scalar quantization for value-sharing applications has been soaring as it has been found huge utilities in reducing the complexity of neural networks. Existing clustering-based quantization techniques, while being well-developed, have multiple drawbacks including the dependency of the random seed, empty or out-of-the-range clusters, and high time complexity for a large number of clusters. To overcome these problems, in this paper, the problem of scalar quantization is examined from a new perspective, namely sparse least square optimization. Specifically, inspired by the property of sparse least square regression, several quantization algorithms based on $l_1$ least square are proposed. In addition, similar schemes with $l_1 + l_2$ and $l_0$ regularization are proposed. Furthermore, to compute quantization results with a given amount of values/clusters, this paper designed an iterative method and a clustering-based method, and both of them are built on sparse least square. The paper shows that the latter method is mathematically equivalent to an improved version of k-means clustering-based quantization algorithm, although the two algorithms originated from different intuitions. The algorithms proposed were tested with three types of data and their computational performances, including information loss, time consumption, and the distribution of the values of the sparse vectors, were compared and analyzed. The paper offers a new perspective to probe the area of quantization, and the algorithms proposed can outperform existing methods especially under some bit-width reduction scenarios, when the required post-quantization resolution (number of values) is not significantly lower than the original number. |
| Tasks | Quantization |
| Published | 2018-03-01 |
| URL | https://arxiv.org/abs/1803.00204v4 |
| https://arxiv.org/pdf/1803.00204v4.pdf | |
| PWC | https://paperswithcode.com/paper/vector-quantization-as-sparse-least-square |
| Repo | |
| Framework | |
Constructing Ontology-Based Cancer Treatment Decision Support System with Case-Based Reasoning
| Title | Constructing Ontology-Based Cancer Treatment Decision Support System with Case-Based Reasoning |
| Authors | Ying Shen, Joël Colloc, Armelle Jacquet-Andrieu, Ziyi Guo, Yong Liu |
| Abstract | Decision support is a probabilistic and quantitative method designed for modeling problems in situations with ambiguity. Computer technology can be employed to provide clinical decision support and treatment recommendations. The problem of natural language applications is that they lack formality and the interpretation is not consistent. Conversely, ontologies can capture the intended meaning and specify modeling primitives. Disease Ontology (DO) that pertains to cancer’s clinical stages and their corresponding information components is utilized to improve the reasoning ability of a decision support system (DSS). The proposed DSS uses Case-Based Reasoning (CBR) to consider disease manifestations and provides physicians with treatment solutions from similar previous cases for reference. The proposed DSS supports natural language processing (NLP) queries. The DSS obtained 84.63% accuracy in disease classification with the help of the ontology. |
| Tasks | |
| Published | 2018-12-05 |
| URL | http://arxiv.org/abs/1812.01891v1 |
| http://arxiv.org/pdf/1812.01891v1.pdf | |
| PWC | https://paperswithcode.com/paper/constructing-ontology-based-cancer-treatment |
| Repo | |
| Framework | |
WHInter: A Working set algorithm for High-dimensional sparse second order Interaction models
| Title | WHInter: A Working set algorithm for High-dimensional sparse second order Interaction models |
| Authors | Marine Le Morvan, Jean-Philippe Vert |
| Abstract | Learning sparse linear models with two-way interactions is desirable in many application domains such as genomics. l1-regularised linear models are popular to estimate sparse models, yet standard implementations fail to address specifically the quadratic explosion of candidate two-way interactions in high dimensions, and typically do not scale to genetic data with hundreds of thousands of features. Here we present WHInter, a working set algorithm to solve large l1-regularised problems with two-way interactions for binary design matrices. The novelty of WHInter stems from a new bound to efficiently identify working sets while avoiding to scan all features, and on fast computations inspired from solutions to the maximum inner product search problem. We apply WHInter to simulated and real genetic data and show that it is more scalable and two orders of magnitude faster than the state of the art. |
| Tasks | |
| Published | 2018-02-16 |
| URL | http://arxiv.org/abs/1802.05980v1 |
| http://arxiv.org/pdf/1802.05980v1.pdf | |
| PWC | https://paperswithcode.com/paper/whinter-a-working-set-algorithm-for-high |
| Repo | |
| Framework | |
A Supervised Learning Approach For Heading Detection
| Title | A Supervised Learning Approach For Heading Detection |
| Authors | Sahib Singh Budhiraja, Vijay Mago |
| Abstract | As the Portable Document Format (PDF) file format increases in popularity, research in analysing its structure for text extraction and analysis is necessary. Detecting headings can be a crucial component of classifying and extracting meaningful data. This research involves training a supervised learning model to detect headings with features carefully selected through recursive feature elimination. The best performing classifier had an accuracy of 96.95%, sensitivity of 0.986 and a specificity of 0.953. This research into heading detection contributes to the field of PDF based text extraction and can be applied to the automation of large scale PDF text analysis in a variety of professional and policy based contexts. |
| Tasks | |
| Published | 2018-08-31 |
| URL | http://arxiv.org/abs/1809.01477v1 |
| http://arxiv.org/pdf/1809.01477v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-supervised-learning-approach-for-heading |
| Repo | |
| Framework | |
Reconciling Feature-Reuse and Overfitting in DenseNet with Specialized Dropout
| Title | Reconciling Feature-Reuse and Overfitting in DenseNet with Specialized Dropout |
| Authors | Kun Wan, Boyuan Feng, Lingwei Xie, Yufei Ding |
| Abstract | Recently convolutional neural networks (CNNs) achieve great accuracy in visual recognition tasks. DenseNet becomes one of the most popular CNN models due to its effectiveness in feature-reuse. However, like other CNN models, DenseNets also face overfitting problem if not severer. Existing dropout method can be applied but not as effective due to the introduced nonlinear connections. In particular, the property of feature-reuse in DenseNet will be impeded, and the dropout effect will be weakened by the spatial correlation inside feature maps. To address these problems, we craft the design of a specialized dropout method from three aspects, dropout location, dropout granularity, and dropout probability. The insights attained here could potentially be applied as a general approach for boosting the accuracy of other CNN models with similar nonlinear connections. Experimental results show that DenseNets with our specialized dropout method yield better accuracy compared to vanilla DenseNet and state-of-the-art CNN models, and such accuracy boost increases with the model depth. |
| Tasks | |
| Published | 2018-09-28 |
| URL | http://arxiv.org/abs/1810.00091v1 |
| http://arxiv.org/pdf/1810.00091v1.pdf | |
| PWC | https://paperswithcode.com/paper/reconciling-feature-reuse-and-overfitting-in |
| Repo | |
| Framework | |
What Catches the Eye? Visualizing and Understanding Deep Saliency Models
| Title | What Catches the Eye? Visualizing and Understanding Deep Saliency Models |
| Authors | Sen He, Ali Borji, Yang Mi, Nicolas Pugeault |
| Abstract | Deep convolutional neural networks have demonstrated high performances for fixation prediction in recent years. How they achieve this, however, is less explored and they remain to be black box models. Here, we attempt to shed light on the internal structure of deep saliency models and study what features they extract for fixation prediction. Specifically, we use a simple yet powerful architecture, consisting of only one CNN and a single resolution input, combined with a new loss function for pixel-wise fixation prediction during free viewing of natural scenes. We show that our simple method is on par or better than state-of-the-art complicated saliency models. Furthermore, we propose a method, related to saliency model evaluation metrics, to visualize deep models for fixation prediction. Our method reveals the inner representations of deep models for fixation prediction and provides evidence that saliency, as experienced by humans, is likely to involve high-level semantic knowledge in addition to low-level perceptual cues. Our results can be useful to measure the gap between current saliency models and the human inter-observer model and to build new models to close this gap. |
| Tasks | |
| Published | 2018-03-15 |
| URL | http://arxiv.org/abs/1803.05753v3 |
| http://arxiv.org/pdf/1803.05753v3.pdf | |
| PWC | https://paperswithcode.com/paper/what-catches-the-eye-visualizing-and |
| Repo | |
| Framework | |
GU IRLAB at SemEval-2018 Task 7: Tree-LSTMs for Scientific Relation Classification
| Title | GU IRLAB at SemEval-2018 Task 7: Tree-LSTMs for Scientific Relation Classification |
| Authors | Sean MacAvaney, Luca Soldaini, Arman Cohan, Nazli Goharian |
| Abstract | SemEval 2018 Task 7 focuses on relation ex- traction and classification in scientific literature. In this work, we present our tree-based LSTM network for this shared task. Our approach placed 9th (of 28) for subtask 1.1 (relation classification), and 5th (of 20) for subtask 1.2 (relation classification with noisy entities). We also provide an ablation study of features included as input to the network. |
| Tasks | Relation Classification |
| Published | 2018-04-15 |
| URL | http://arxiv.org/abs/1804.05408v1 |
| http://arxiv.org/pdf/1804.05408v1.pdf | |
| PWC | https://paperswithcode.com/paper/gu-irlab-at-semeval-2018-task-7-tree-lstms |
| Repo | |
| Framework | |
Interpretable Optimal Stopping
| Title | Interpretable Optimal Stopping |
| Authors | Dragos Florin Ciocan, Velibor V. Mišić |
| Abstract | Optimal stopping is the problem of deciding when to stop a stochastic system to obtain the greatest reward, arising in numerous application areas such as finance, healthcare and marketing. State-of-the-art methods for high-dimensional optimal stopping involve approximating the value function or the continuation value, and then using that approximation within a greedy policy. Although such policies can perform very well, they are generally not guaranteed to be interpretable; that is, a decision maker may not be able to easily see the link between the current system state and the policy’s action. In this paper, we propose a new approach to optimal stopping, wherein the policy is represented as a binary tree, in the spirit of naturally interpretable tree models commonly used in machine learning. We show that the class of tree policies is rich enough to approximate the optimal policy. We formulate the problem of learning such policies from observed trajectories of the stochastic system as a sample average approximation (SAA) problem. We prove that the SAA problem converges under mild conditions as the sample size increases, but that computationally even immediate simplifications of the SAA problem are theoretically intractable. We thus propose a tractable heuristic for approximately solving the SAA problem, by greedily constructing the tree from the top down. We demonstrate the value of our approach by applying it to the canonical problem of option pricing, using both synthetic instances and instances using real S&P-500 data. Our method obtains policies that (1) outperform state-of-the-art non-interpretable methods, based on simulation-regression and martingale duality, and (2) possess a remarkably simple and intuitive structure. |
| Tasks | |
| Published | 2018-12-18 |
| URL | https://arxiv.org/abs/1812.07211v2 |
| https://arxiv.org/pdf/1812.07211v2.pdf | |
| PWC | https://paperswithcode.com/paper/interpretable-optimal-stopping |
| Repo | |
| Framework | |
Towards integrating spatial localization in convolutional neural networks for brain image segmentation
| Title | Towards integrating spatial localization in convolutional neural networks for brain image segmentation |
| Authors | Pierre-Antoine Ganaye, Michaël Sdika, Hugues Benoit-Cattin |
| Abstract | Semantic segmentation is an established while rapidly evolving field in medical imaging. In this paper we focus on the segmentation of brain Magnetic Resonance Images (MRI) into cerebral structures using convolutional neural networks (CNN). CNNs achieve good performance by finding effective high dimensional image features describing the patch content only. In this work, we propose different ways to introduce spatial constraints into the network to further reduce prediction inconsistencies. A patch based CNN architecture was trained, making use of multiple scales to gather contextual information. Spatial constraints were introduced within the CNN through a distance to landmarks feature or through the integration of a probability atlas. We demonstrate experimentally that using spatial information helps to reduce segmentation inconsistencies. |
| Tasks | Brain Image Segmentation, Semantic Segmentation |
| Published | 2018-04-12 |
| URL | http://arxiv.org/abs/1804.04563v1 |
| http://arxiv.org/pdf/1804.04563v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-integrating-spatial-localization-in |
| Repo | |
| Framework | |
Optimal Strategies for Matching and Retrieval Problems by Comparing Covariates
| Title | Optimal Strategies for Matching and Retrieval Problems by Comparing Covariates |
| Authors | Yandong Wen, Mahmoud Al Ismail, Bhiksha Raj, Rita Singh |
| Abstract | In many retrieval problems, where we must retrieve one or more entries from a gallery in response to a probe, it is common practice to learn to do by directly comparing the probe and gallery entries to one another. In many situations the gallery and probe have common covariates – external variables that are common to both. In principle it is possible to perform the retrieval based merely on these covariates. The process, however, becomes gated by our ability to recognize the covariates for the probe and gallery entries correctly. In this paper we analyze optimal strategies for retrieval based only on matching covariates, when the recognition of the covariates is itself inaccurate. We investigate multiple problems: recovering one item from a gallery of $N$ entries, matching pairs of instances, and retrieval from large collections. We verify our analytical formulae through experiments to verify their correctness in practical settings. |
| Tasks | |
| Published | 2018-07-12 |
| URL | http://arxiv.org/abs/1807.04834v2 |
| http://arxiv.org/pdf/1807.04834v2.pdf | |
| PWC | https://paperswithcode.com/paper/optimal-strategies-for-matching-and-retrieval |
| Repo | |
| Framework | |
Person Identification from Partial Gait Cycle Using Fully Convolutional Neural Network
| Title | Person Identification from Partial Gait Cycle Using Fully Convolutional Neural Network |
| Authors | Maryam Babaee, Linwei Li, Gerhard Rigoll |
| Abstract | Gait as a biometric property for person identification plays a key role in video surveillance and security applications. In gait recognition, normally, gait feature such as Gait Energy Image (GEI) is extracted from one full gait cycle. However in many circumstances, such a full gait cycle might not be available due to occlusion. Thus, the GEI is not complete giving rise to a degrading in gait-based person identification rate. In this paper, we address this issue by proposing a novel method to identify individuals from gait feature when a few (or even single) frame(s) is available. To do so, we propose a deep learning-based approach to transform incomplete GEI to the corresponding complete GEI obtained from a full gait cycle. More precisely, this transformation is done gradually by training several auto encoders independently and then combining these as a uniform model. Experimental results on two public gait datasets, namely OULP and Casia-B demonstrate the validity of the proposed method in dealing with very incomplete gait cycles. |
| Tasks | Gait Recognition, Person Identification |
| Published | 2018-04-23 |
| URL | http://arxiv.org/abs/1804.08506v1 |
| http://arxiv.org/pdf/1804.08506v1.pdf | |
| PWC | https://paperswithcode.com/paper/person-identification-from-partial-gait-cycle |
| Repo | |
| Framework | |
Deep Learning Phase Segregation
| Title | Deep Learning Phase Segregation |
| Authors | Amir Barati Farimani, Joseph Gomes, Rishi Sharma, Franklin L. Lee, Vijay S. Pande |
| Abstract | Phase segregation, the process by which the components of a binary mixture spontaneously separate, is a key process in the evolution and design of many chemical, mechanical, and biological systems. In this work, we present a data-driven approach for the learning, modeling, and prediction of phase segregation. A direct mapping between an initially dispersed, immiscible binary fluid and the equilibrium concentration field is learned by conditional generative convolutional neural networks. Concentration field predictions by the deep learning model conserve phase fraction, correctly predict phase transition, and reproduce area, perimeter, and total free energy distributions up to 98% accuracy. |
| Tasks | |
| Published | 2018-03-23 |
| URL | http://arxiv.org/abs/1803.08993v1 |
| http://arxiv.org/pdf/1803.08993v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-phase-segregation |
| Repo | |
| Framework | |
MobiBits: Multimodal Mobile Biometric Database
| Title | MobiBits: Multimodal Mobile Biometric Database |
| Authors | Ewelina Bartuzi, Katarzyna Roszczewska, Mateusz Trokielewicz, Radosław Białobrzeski |
| Abstract | This paper presents a novel database comprising representations of five different biometric characteristics, collected in a mobile, unconstrained or semi-constrained setting with three different mobile devices, including characteristics previously unavailable in existing datasets, namely hand images, thermal hand images, and thermal face images, all acquired with a mobile, off-the-shelf device. In addition to this collection of data we perform an extensive set of experiments providing insight on benchmark recognition performance that can be achieved with these data, carried out with existing commercial and academic biometric solutions. This is the first known to us mobile biometric database introducing samples of biometric traits such as thermal hand images and thermal face images. We hope that this contribution will make a valuable addition to the already existing databases and enable new experiments and studies in the field of mobile authentication. The MobiBits database is made publicly available to the research community at no cost for non-commercial purposes. |
| Tasks | |
| Published | 2018-08-31 |
| URL | http://arxiv.org/abs/1808.10710v1 |
| http://arxiv.org/pdf/1808.10710v1.pdf | |
| PWC | https://paperswithcode.com/paper/mobibits-multimodal-mobile-biometric-database |
| Repo | |
| Framework | |
Fully-deformable 3D image registration in two seconds
| Title | Fully-deformable 3D image registration in two seconds |
| Authors | Daniel Budelmann, Lars König, Nils Papenberg, Jan Lellmann |
| Abstract | We present a highly parallel method for accurate and efficient variational deformable 3D image registration on a consumer-grade graphics processing unit (GPU). We build on recent matrix-free variational approaches and specialize the concepts to the massively-parallel manycore architecture provided by the GPU. Compared to a parallel and optimized CPU implementation, this allows us to achieve an average speedup of 32.53 on 986 real-world CT thorax-abdomen follow-up scans. At a resolution of approximately $256^3$ voxels, the average runtime is 1.99 seconds for the full registration. On the publicly available DIR-lab benchmark, our method ranks third with respect to average landmark error at an average runtime of 0.32 seconds. |
| Tasks | Image Registration |
| Published | 2018-12-17 |
| URL | http://arxiv.org/abs/1812.06765v1 |
| http://arxiv.org/pdf/1812.06765v1.pdf | |
| PWC | https://paperswithcode.com/paper/fully-deformable-3d-image-registration-in-two |
| Repo | |
| Framework | |
