Paper Group ANR 1534
Tracking-Assisted Segmentation of Biological Cells. Multi-stage Pretraining for Abstractive Summarization. Link Prediction in Multiplex Networks based on Interlayer Similarity. Adversarial Attack and Defense on Point Sets. Summary Level Training of Sentence Rewriting for Abstractive Summarization. A Bayesian Deep Learning Framework for End-To-End P …
Tracking-Assisted Segmentation of Biological Cells
| Title | Tracking-Assisted Segmentation of Biological Cells |
| Authors | Deepak K. Gupta, Nathan de Bruijn, Andreas Panteli, Efstratios Gavves |
| Abstract | U-Net and its variants have been demonstrated to work sufficiently well in biological cell tracking and segmentation. However, these methods still suffer in the presence of complex processes such as collision of cells, mitosis and apoptosis. In this paper, we augment U-Net with Siamese matching-based tracking and propose to track individual nuclei over time. By modelling the behavioural pattern of the cells, we achieve improved segmentation and tracking performances through a re-segmentation procedure. Our preliminary investigations on the Fluo-N2DH-SIM+ and Fluo-N2DH-GOWT1 datasets demonstrate that absolute improvements of up to 3.8 % and 3.4% can be obtained in segmentation and tracking accuracy, respectively. |
| Tasks | |
| Published | 2019-10-19 |
| URL | https://arxiv.org/abs/1910.08735v1 |
| https://arxiv.org/pdf/1910.08735v1.pdf | |
| PWC | https://paperswithcode.com/paper/tracking-assisted-segmentation-of-biological |
| Repo | |
| Framework | |
Multi-stage Pretraining for Abstractive Summarization
| Title | Multi-stage Pretraining for Abstractive Summarization |
| Authors | Sebastian Goodman, Zhenzhong Lan, Radu Soricut |
| Abstract | Neural models for abstractive summarization tend to achieve the best performance in the presence of highly specialized, summarization specific modeling add-ons such as pointer-generator, coverage-modeling, and inferencetime heuristics. We show here that pretraining can complement such modeling advancements to yield improved results in both short-form and long-form abstractive summarization using two key concepts: full-network initialization and multi-stage pretraining. Our method allows the model to transitively benefit from multiple pretraining tasks, from generic language tasks to a specialized summarization task to an even more specialized one such as bullet-based summarization. Using this approach, we demonstrate improvements of 1.05 ROUGE-L points on the Gigaword benchmark and 1.78 ROUGE-L points on the CNN/DailyMail benchmark, compared to a randomly-initialized baseline. |
| Tasks | Abstractive Text Summarization |
| Published | 2019-09-23 |
| URL | https://arxiv.org/abs/1909.10599v1 |
| https://arxiv.org/pdf/1909.10599v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-stage-pretraining-for-abstractive |
| Repo | |
| Framework | |
Link Prediction in Multiplex Networks based on Interlayer Similarity
| Title | Link Prediction in Multiplex Networks based on Interlayer Similarity |
| Authors | Shaghayegh Najari, Mostafa Salehi, Vahid Ranjbar, Mahdi Jalili |
| Abstract | Some networked systems can be better modelled by multilayer structure where the individual nodes develop relationships in multiple layers. Multilayer networks with similar nodes across layers are also known as multiplex networks. This manuscript proposes a novel framework for predicting forthcoming or missing links in multiplex networks. The link prediction problem in multiplex networks is how to predict links in one of the layers, taking into account the structural information of other layers. The proposed link prediction framework is based on interlayer similarity and proximity-based features extracted from the layer for which the link prediction is considered. To this end, commonly used proximity-based features such as Adamic-Adar and Jaccard Coefficient are considered. These features that have been originally proposed to predict missing links in monolayer networks, do not require learning, and thus are simple to compute. The proposed method introduces a systematic approach to take into account interlayer similarity for the link prediction purpose. Experimental results on both synthetic and real multiplex networks reveal the effectiveness of the proposed method and show its superior performance than state-of-the-art algorithms proposed for the link prediction problem in multiplex networks. |
| Tasks | Link Prediction |
| Published | 2019-04-23 |
| URL | http://arxiv.org/abs/1904.10169v2 |
| http://arxiv.org/pdf/1904.10169v2.pdf | |
| PWC | https://paperswithcode.com/paper/link-prediction-in-multiplex-networks-based |
| Repo | |
| Framework | |
Adversarial Attack and Defense on Point Sets
| Title | Adversarial Attack and Defense on Point Sets |
| Authors | Jiancheng Yang, Qiang Zhang, Rongyao Fang, Bingbing Ni, Jinxian Liu, Qi Tian |
| Abstract | Emergence of the utility of 3D point cloud data in critical vision tasks (e.g., ADAS) urges researchers to pay more attention to the robustness of 3D representations and deep networks. To this end, we develop an attack and defense scheme, dedicated to 3D point cloud data, for preventing 3D point clouds from manipulated as well as pursuing noise-tolerable 3D representation. A set of novel 3D point cloud attack operations are proposed via pointwise gradient perturbation and adversarial point attachment / detachment. We then develop a flexible perturbation-measurement scheme for 3D point cloud data to detect potential attack data or noisy sensing data. Extensive experimental results on common point cloud benchmarks demonstrate the validity of the proposed 3D attack and defense framework. |
| Tasks | Adversarial Attack |
| Published | 2019-02-28 |
| URL | http://arxiv.org/abs/1902.10899v1 |
| http://arxiv.org/pdf/1902.10899v1.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-attack-and-defense-on-point-sets |
| Repo | |
| Framework | |
Summary Level Training of Sentence Rewriting for Abstractive Summarization
| Title | Summary Level Training of Sentence Rewriting for Abstractive Summarization |
| Authors | Sanghwan Bae, Taeuk Kim, Jihoon Kim, Sang-goo Lee |
| Abstract | As an attempt to combine extractive and abstractive summarization, Sentence Rewriting models adopt the strategy of extracting salient sentences from a document first and then paraphrasing the selected ones to generate a summary. However, the existing models in this framework mostly rely on sentence-level rewards or suboptimal labels, causing a mismatch between a training objective and evaluation metric. In this paper, we present a novel training signal that directly maximizes summary-level ROUGE scores through reinforcement learning. In addition, we incorporate BERT into our model, making good use of its ability on natural language understanding. In extensive experiments, we show that a combination of our proposed model and training procedure obtains new state-of-the-art performance on both CNN/Daily Mail and New York Times datasets. We also demonstrate that it generalizes better on DUC-2002 test set. |
| Tasks | Abstractive Text Summarization |
| Published | 2019-09-19 |
| URL | https://arxiv.org/abs/1909.08752v3 |
| https://arxiv.org/pdf/1909.08752v3.pdf | |
| PWC | https://paperswithcode.com/paper/summary-level-training-of-sentence-rewriting |
| Repo | |
| Framework | |
A Bayesian Deep Learning Framework for End-To-End Prediction of Emotion from Heartbeat
| Title | A Bayesian Deep Learning Framework for End-To-End Prediction of Emotion from Heartbeat |
| Authors | Ross Harper, Joshua Southern |
| Abstract | Automatic prediction of emotion promises to revolutionise human-computer interaction. Recent trends involve fusion of multiple modalities - audio, visual, and physiological - to classify emotional state. However, practical considerations ‘in the wild’ limit collection of this physiological data to commoditised heartbeat sensors. Furthermore, real-world applications often require some measure of uncertainty over model output. We present here an end-to-end deep learning model for classifying emotional valence from unimodal heartbeat data. We further propose a Bayesian framework for modelling uncertainty over valence predictions, and describe a procedure for tuning output according to varying demands on confidence. We benchmarked our framework against two established datasets within the field and achieved peak classification accuracy of 90%. These results lay the foundation for applications of affective computing in real-world domains such as healthcare, where a high premium is placed on non-invasive collection of data, and predictive certainty. |
| Tasks | |
| Published | 2019-02-08 |
| URL | http://arxiv.org/abs/1902.03043v1 |
| http://arxiv.org/pdf/1902.03043v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-bayesian-deep-learning-framework-for-end-to |
| Repo | |
| Framework | |
A Stable Combinatorial Particle Swarm Optimization for Scalable Feature Selection in Gene Expression Data
| Title | A Stable Combinatorial Particle Swarm Optimization for Scalable Feature Selection in Gene Expression Data |
| Authors | Hassen Dhrif, Luis G. Sanchez Giraldo, Miroslav Kubat, Stefan Wuchty |
| Abstract | Evolutionary computation (EC) algorithms, such as discrete and multi-objective versions of particle swarm optimization (PSO), have been applied to solve the Feature selection (FS) problem, tackling the combinatorial explosion of search spaces that are peppered with local minima. Furthermore, high-dimensional FS problems such as finding a small set of biomarkers to make a diagnostic call add an additional challenge as such methods ability to pick out the most important features must remain unchanged in decision spaces of increasing dimensions and presence of irrelevant features. We developed a combinatorial PSO algorithm, called COMB-PSO, that scales up to high-dimensional gene expression data while still selecting the smallest subsets of genes that allow reliable classification of samples. In particular, COMB-PSO enhances the encoding, speed of convergence, control of divergence and diversity of the conventional PSO algorithm, balancing exploration and exploitation of the search space. Applying our approach on real gene expression data of different cancers, COMB-PSO finds gene sets of smallest size that allow a reliable classification of the underlying disease classes. |
| Tasks | Feature Selection |
| Published | 2019-01-24 |
| URL | http://arxiv.org/abs/1901.08619v1 |
| http://arxiv.org/pdf/1901.08619v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-stable-combinatorial-particle-swarm |
| Repo | |
| Framework | |
A Domain Adaptive Density Clustering Algorithm for Data with Varying Density Distribution
| Title | A Domain Adaptive Density Clustering Algorithm for Data with Varying Density Distribution |
| Authors | Jianguo Chen, Philip S. Yu |
| Abstract | As one type of efficient unsupervised learning methods, clustering algorithms have been widely used in data mining and knowledge discovery with noticeable advantages. However, clustering algorithms based on density peak have limited clustering effect on data with varying density distribution (VDD), equilibrium distribution (ED), and multiple domain-density maximums (MDDM), leading to the problems of sparse cluster loss and cluster fragmentation. To address these problems, we propose a Domain-Adaptive Density Clustering (DADC) algorithm, which consists of three steps: domain-adaptive density measurement, cluster center self-identification, and cluster self-ensemble. For data with VDD features, clusters in sparse regions are often neglected by using uniform density peak thresholds, which results in the loss of sparse clusters. We define a domain-adaptive density measurement method based on K-Nearest Neighbors (KNN) to adaptively detect the density peaks of different density regions. We treat each data point and its KNN neighborhood as a subgroup to better reflect its density distribution in a domain view. In addition, for data with ED or MDDM features, a large number of density peaks with similar values can be identified, which results in cluster fragmentation. We propose a cluster center self-identification and cluster self-ensemble method to automatically extract the initial cluster centers and merge the fragmented clusters. Experimental results demonstrate that compared with other comparative algorithms, the proposed DADC algorithm can obtain more reasonable clustering results on data with VDD, ED and MDDM features. Benefitting from a few parameter requirements and non-iterative nature, DADC achieves low computational complexity and is suitable for large-scale data clustering. |
| Tasks | |
| Published | 2019-11-23 |
| URL | https://arxiv.org/abs/1911.10293v1 |
| https://arxiv.org/pdf/1911.10293v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-domain-adaptive-density-clustering |
| Repo | |
| Framework | |
WSOD with PSNet and Box Regression
| Title | WSOD with PSNet and Box Regression |
| Authors | Sheng Yi, Xi Li, Huimin Ma |
| Abstract | Weakly supervised object detection(WSOD) task uses only image-level annotations to train object detection task. WSOD does not require time-consuming instance-level annotations, so the study of this task has attracted more and more attention. Previous weakly supervised object detection methods iteratively update detectors and pseudo-labels, or use feature-based mask-out methods. Most of these methods do not generate complete and accurate proposals, often only the most discriminative parts of the object, or too many background areas. To solve this problem, we added the box regression module to the weakly supervised object detection network and proposed a proposal scoring network (PSNet) to supervise it. The box regression module modifies proposal to improve the IoU of proposal and ground truth. PSNet scores the proposal output from the box regression network and utilize the score to improve the box regression module. In addition, we take advantage of the PRS algorithm for generating a more accurate pseudo label to train the box regression module. Using these methods, we train the detector on the PASCAL VOC 2007 and 2012 and obtain significantly improved results. |
| Tasks | Object Detection, Weakly Supervised Object Detection |
| Published | 2019-11-26 |
| URL | https://arxiv.org/abs/1911.11512v1 |
| https://arxiv.org/pdf/1911.11512v1.pdf | |
| PWC | https://paperswithcode.com/paper/wsod-with-psnet-and-box-regression |
| Repo | |
| Framework | |
A novel machine learning based framework for detection of Autism Spectrum Disorder (ASD)
| Title | A novel machine learning based framework for detection of Autism Spectrum Disorder (ASD) |
| Authors | Hamza Sharif, Rizwan Ahmed Khan |
| Abstract | Computer vision and machine learning are the linchpin of field of automation. The medicine industry has adopted numerous methods to discover the root causes of many diseases in order to automate detection process. But, the biomarkers of Autism Spectrum Disorder (ASD) are still unknown, let alone automating its detection. Studies from the neuroscience domain highlighted the fact that corpus callosum and intracranial brain volume holds significant information for detection of ASD. Such results and studies are not tested and verified by scientists working in the domain of computer vision / machine learning. Thus, in this study we have proposed a machine learning based framework for automatic detection of ASD using features extracted from corpus callosum and intracranial brain volume from ABIDE dataset. Corpus callosum and intracranial brain volume data is obtained from T1-weighted MRI scans. Our proposed framework first calculates weights of features extracted from Corpus callosum and intracranial brain volume data. This step ensures to utilize discriminative capabilities of only those features that will help in robust recognition of ASD. Then, conventional machine learning algorithm (conventional refers to algorithms other than deep learning) is applied on features that are most significant in terms of discriminative capabilities for recognition of ASD. Finally, for benchmarking and to verify potential of deep learning on analyzing neuroimaging data i.e. T1-weighted MRI scans, we have done experiment with state of the art deep learning architecture i.e. VGG16 . We have used transfer learning approach to use already trained VGG16 model for detection of ASD. This is done to help readers understand benefits and bottlenecks of using deep learning approach for analyzing neuroimaging data which is difficult to record in large enough quantity for deep learning. |
| Tasks | Transfer Learning |
| Published | 2019-03-27 |
| URL | https://arxiv.org/abs/1903.11323v3 |
| https://arxiv.org/pdf/1903.11323v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-novel-framework-for-automatic-detection-of |
| Repo | |
| Framework | |
Gaze Estimation for Assisted Living Environments
| Title | Gaze Estimation for Assisted Living Environments |
| Authors | Philipe A. Dias, Damiano Malafronte, Henry Medeiros, Francesca Odone |
| Abstract | Effective assisted living environments must be able to perform inferences on how their occupants interact with one another as well as with surrounding objects. To accomplish this goal using a vision-based automated approach, multiple tasks such as pose estimation, object segmentation and gaze estimation must be addressed. Gaze direction in particular provides some of the strongest indications of how a person interacts with the environment. In this paper, we propose a simple neural network regressor that estimates the gaze direction of individuals in a multi-camera assisted living scenario, relying only on the relative positions of facial keypoints collected from a single pose estimation model. To handle cases of keypoint occlusion, our model exploits a novel confidence gated unit in its input layer. In addition to the gaze direction, our model also outputs an estimation of its own prediction uncertainty. Experimental results on a public benchmark demonstrate that our approach performs on pair with a complex, dataset-specific baseline, while its uncertainty predictions are highly correlated to the actual angular error of corresponding estimations. Finally, experiments on images from a real assisted living environment demonstrate the higher suitability of our model for its final application. |
| Tasks | Gaze Estimation, Pose Estimation, Semantic Segmentation |
| Published | 2019-09-19 |
| URL | https://arxiv.org/abs/1909.09225v1 |
| https://arxiv.org/pdf/1909.09225v1.pdf | |
| PWC | https://paperswithcode.com/paper/gaze-estimation-for-assisted-living |
| Repo | |
| Framework | |
An algorithm for the selection of route dependent orientation information
| Title | An algorithm for the selection of route dependent orientation information |
| Authors | Heinrich Löwen, Angela Schwering |
| Abstract | Landmarks are important features of spatial cognition. Landmarks are naturally included in human route descriptions and in the past algorithms were developed to select the most salient landmarks at decision points and automatically incorporate them in route instructions. Moreover, it was shown that human route descriptions contain a significant amount of orientation information and that these orientation information support the acquisition of survey knowledge. Thus, there is a need to extend the landmarks selection in order to automatically select orientation information. In this work we present an algorithm for the computational selection of route dependent orientation information, which extends previous algorithms and includes a salience evaluation of orientation information for any location along the route. We implemented the algorithm and demonstrate the functionality on the basis of OpenStreetMap data. |
| Tasks | |
| Published | 2019-06-28 |
| URL | https://arxiv.org/abs/1907.05289v1 |
| https://arxiv.org/pdf/1907.05289v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-algorithm-for-the-selection-of-route |
| Repo | |
| Framework | |
Novel Approach for Solving a Variant of Equal Flow Problem
| Title | Novel Approach for Solving a Variant of Equal Flow Problem |
| Authors | Sasikanth Goteti, Swapnil Kumar |
| Abstract | In this article we consider a certain sub class of Integer Equal Flow problem, which are known NP hard [8]. Currently there exist no direct solutions for the same. It is a common problem in various inventory management systems. Here we discuss a local minima solution which uses projection of the convex spaces to resolve the equal flows and turn the problem into a known linear integer programming or constraint satisfaction problem which have reasonable known solutions and can be effectively solved using simplex or other standard optimization strategies. |
| Tasks | |
| Published | 2019-12-09 |
| URL | https://arxiv.org/abs/1912.04034v2 |
| https://arxiv.org/pdf/1912.04034v2.pdf | |
| PWC | https://paperswithcode.com/paper/novel-approach-for-solving-a-variant-of-equal |
| Repo | |
| Framework | |
EyeNet: A Multi-Task Network for Off-Axis Eye Gaze Estimation and User Understanding
| Title | EyeNet: A Multi-Task Network for Off-Axis Eye Gaze Estimation and User Understanding |
| Authors | Zhengyang Wu, Srivignesh Rajendran, Tarrence van As, Joelle Zimmermann, Vijay Badrinarayanan, Andrew Rabinovich |
| Abstract | Eye gaze estimation and simultaneous semantic understanding of a user through eye images is a crucial component in Virtual and Mixed Reality; enabling energy efficient rendering, multi-focal displays and effective interaction with 3D content. In head-mounted VR/MR devices the eyes are imaged off-axis to avoid blocking the user’s gaze, this view-point makes drawing eye related inferences very challenging. In this work, we present EyeNet, the first single deep neural network which solves multiple heterogeneous tasks related to eye gaze estimation and semantic user understanding for an off-axis camera setting. The tasks include eye segmentation, blink detection, emotive expression classification, IR LED glints detection, pupil and cornea center estimation. To train EyeNet end-to-end we employ both hand labelled supervision and model based supervision. We benchmark all tasks on MagicEyes, a large and new dataset of 587 subjects with varying morphology, gender, skin-color, make-up and imaging conditions. |
| Tasks | Gaze Estimation |
| Published | 2019-08-24 |
| URL | https://arxiv.org/abs/1908.09060v1 |
| https://arxiv.org/pdf/1908.09060v1.pdf | |
| PWC | https://paperswithcode.com/paper/eyenet-a-multi-task-network-for-off-axis-eye |
| Repo | |
| Framework | |
A bisector line field approach to interpolation of orientation fields
| Title | A bisector line field approach to interpolation of orientation fields |
| Authors | Nicolas Boizot, Ludovic Sacchelli |
| Abstract | We propose an approach to the problem of global reconstruction of an orientation field. The method is based on a geometric model called “bisector line fields”, which maps a pair of vector fields to an orientation field, effectively generalizing the notion of doubling phase vector fields. Endowed with a well chosen energy minimization problem, we provide a polynomial interpolation of a target orientation field while bypassing the doubling phase step. The procedure is then illustrated with examples from fingerprint analysis. |
| Tasks | |
| Published | 2019-07-26 |
| URL | https://arxiv.org/abs/1907.11449v2 |
| https://arxiv.org/pdf/1907.11449v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-bisector-line-field-approach-to |
| Repo | |
| Framework | |
