January 25, 2020

3528 words 17 mins read

Paper Group ANR 1621

Learning Reinforced Attentional Representation for End-to-End Visual Tracking. A Transfer Learning Approach for Automated Segmentation of Prostate Whole Gland and Transition Zone in Diffusion Weighted MRI. Spatio-Temporal FAST 3D Convolutions for Human Action Recognition. Genetic Algorithms for Starshade Retargeting in Space-Based Telescopes. Gener …

Learning Reinforced Attentional Representation for End-to-End Visual Tracking


Title	Learning Reinforced Attentional Representation for End-to-End Visual Tracking
Authors	Peng Gao, Qiquan Zhang, Fei Wang, Liyi Xiao, Hamido Fujita, Yan Zhang
Abstract	Although numerous recent tracking approaches have made tremendous advances in the last decade, achieving high-performance visual tracking remains a challenge. In this paper, we propose an end-to-end network model to learn reinforced attentional representation for accurate target object discrimination and localization. We utilize a novel hierarchical attentional module with long short-term memory and multi-layer perceptrons to leverage both inter- and intra-frame attention to effectively facilitate visual pattern emphasis. Moreover, we incorporate a contextual attentional correlation filter into the backbone network to make our model trainable in an end-to-end fashion. Our proposed approach not only takes full advantage of informative geometries and semantics but also updates correlation filters online without fine-tuning the backbone network to enable the adaptation of variations in the target object’s appearance. Extensive experiments conducted on several popular benchmark datasets demonstrate that our proposed approach is effective and computationally efficient.
Tasks	Visual Tracking
Published	2019-08-27
URL	https://arxiv.org/abs/1908.10009v3
PDF	https://arxiv.org/pdf/1908.10009v3.pdf
PWC	https://paperswithcode.com/paper/learning-reinforced-attentional
Repo
Framework

A Transfer Learning Approach for Automated Segmentation of Prostate Whole Gland and Transition Zone in Diffusion Weighted MRI


Title	A Transfer Learning Approach for Automated Segmentation of Prostate Whole Gland and Transition Zone in Diffusion Weighted MRI
Authors	Saman Motamed, Isha Gujrathi, Dominik Deniffel, Anton Oentoro, Masoom A. Haider, Farzad Khalvati
Abstract	The segmentation of prostate whole gland and transition zone in Diffusion Weighted MRI (DWI) are the first step in designing computer-aided detection algorithms for prostate cancer. However, variations in MRI acquisition parameters and scanner manufacturing result in different appearances of prostate tissue in the images. Convolutional neural networks (CNNs) which have shown to be successful in various medical image analysis tasks including segmentation are typically sensitive to the variations in imaging parameters. This sensitivity leads to poor segmentation performance of CNNs trained on a source cohort and tested on a target cohort from a different scanner and hence, it limits the applicability of CNNs for cross-cohort training and testing. Contouring prostate whole gland and transition zone in DWI images are time-consuming and expensive. Thus, it is important to enable CNNs pretrained on images of source domain, to segment images of target domain with minimum requirement for manual segmentation of images from the target domain. In this work, we propose a transfer learning method based on a modified U-net architecture and loss function, for segmentation of prostate whole gland and transition zone in DWIs using a CNN pretrained on a source dataset and tested on the target dataset. We explore the effect of the size of subset of target dataset used for fine-tuning the pre-trained CNN on the overall segmentation accuracy. Our results show that with a fine-tuning data as few as 30 patients from the target domain, the proposed transfer learning-based algorithm can reach dice score coefficient of 0.80 for both prostate whole gland and transition zone segmentation. Using a fine-tuning data of 115 patients from the target domain, dice score coefficient of 0.85 and 0.84 are achieved for segmentation of whole gland and transition zone, respectively, in the target domain.
Tasks	Transfer Learning
Published	2019-09-20
URL	https://arxiv.org/abs/1909.09541v1
PDF	https://arxiv.org/pdf/1909.09541v1.pdf
PWC	https://paperswithcode.com/paper/a-transfer-learning-approach-for-automated
Repo
Framework

Spatio-Temporal FAST 3D Convolutions for Human Action Recognition


Title	Spatio-Temporal FAST 3D Convolutions for Human Action Recognition
Authors	Alexandros Stergiou, Ronald Poppe
Abstract	Effective processing of video input is essential for the recognition of temporally varying events such as human actions. Motivated by the often distinctive temporal characteristics of actions in either horizontal or vertical direction, we introduce a novel convolution block for CNN architectures with video input. Our proposed Fractioned Adjacent Spatial and Temporal (FAST) 3D convolutions are a natural decomposition of a regular 3D convolution. Each convolution block consist of three sequential convolution operations: a 2D spatial convolution followed by spatio-temporal convolutions in the horizontal and vertical direction, respectively. Additionally, we introduce a FAST variant that treats horizontal and vertical motion in parallel. Experiments on benchmark action recognition datasets UCF-101 and HMDB-51 with ResNet architectures demonstrate consistent increased performance of FAST 3D convolution blocks over traditional 3D convolutions. The lower validation loss indicates better generalization, especially for deeper networks. We also evaluate the performance of CNN architectures with similar memory requirements, based either on Two-stream networks or with 3D convolution blocks. DenseNet-121 with FAST 3D convolutions was shown to perform best, giving further evidence of the merits of the decoupled spatio-temporal convolutions.
Tasks	Temporal Action Localization
Published	2019-09-30
URL	https://arxiv.org/abs/1909.13474v2
PDF	https://arxiv.org/pdf/1909.13474v2.pdf
PWC	https://paperswithcode.com/paper/spatio-temporal-fast-3d-convolutions-for
Repo
Framework

Genetic Algorithms for Starshade Retargeting in Space-Based Telescopes


Title	Genetic Algorithms for Starshade Retargeting in Space-Based Telescopes
Authors	Ho Chit Siu, Victor Pankratius
Abstract	Future space-based telescopes will leverage starshades as components that can be independently positioned. Starshades will adjust the light coming in from exoplanet host stars and enhance the direct imaging of exoplanets and other phenomena. In this context, scheduling of space-based telescope observations is subject to a large number of dynamic constraints, including target observability, fuel, and target priorities. We present an application of genetic algorithm (GA) scheduling on this problem that not only takes physical constraints into account, but also considers direct human suggestions on schedules. By allowing direct suggestions on schedules, this type of heuristic can capture the scheduling preferences and expertise of stakeholders without the need to always formally codify such objectives. Additionally, this approach allows schedules to be constructed from existing ones when scenarios change; for example, this capability allows for optimization without the need to recompute schedules from scratch after changes such as new discoveries or new targets of opportunity. We developed a specific graph-traversal-based framework upon which to apply GA for telescope scheduling, and use it to demonstrate the convergence behavior of a particular implementation of GA. From this work, difficulties with regards to assigning values to observational targets are also noted, and recommendations are made for different scenarios.
Tasks
Published	2019-07-23
URL	https://arxiv.org/abs/1907.09789v1
PDF	https://arxiv.org/pdf/1907.09789v1.pdf
PWC	https://paperswithcode.com/paper/genetic-algorithms-for-starshade-retargeting
Repo
Framework

Generate What You Can’t See - a View-dependent Image Generation


Title	Generate What You Can’t See - a View-dependent Image Generation
Authors	Karol Piaskowski, Rafal Staszak, Dominik Belter
Abstract	In order to operate autonomously, a robot should explore the environment and build a model of each of the surrounding objects. A common approach is to carefully scan the whole workspace. This is time-consuming. It is also often impossible to reach all the viewpoints required to acquire full knowledge about the environment. Humans can perform shape completion of occluded objects by relying on past experience. Therefore, we propose a method that generates images of an object from various viewpoints using a single input RGB image. A deep neural network is trained to imagine the object appearance from many viewpoints. We present the whole pipeline, which takes a single RGB image as input and returns a sequence of RGB and depth images of the object. The method utilizes a CNN-based object detector to extract the object from the natural scene. Then, the proposed network generates a set of RGB and depth images. We show the results both on a synthetic dataset and on real images.
Tasks	Image Generation
Published	2019-03-15
URL	http://arxiv.org/abs/1903.06814v1
PDF	http://arxiv.org/pdf/1903.06814v1.pdf
PWC	https://paperswithcode.com/paper/generate-what-you-cant-see-a-view-dependent
Repo
Framework

Multi-Point Bandit Algorithms for Nonstationary Online Nonconvex Optimization


Title	Multi-Point Bandit Algorithms for Nonstationary Online Nonconvex Optimization
Authors	Abhishek Roy, Krishnakumar Balasubramanian, Saeed Ghadimi, Prasant Mohapatra
Abstract	Bandit algorithms have been predominantly analyzed in the convex setting with function-value based stationary regret as the performance measure. In this paper, motivated by online reinforcement learning problems, we propose and analyze bandit algorithms for both general and structured nonconvex problems with nonstationary (or dynamic) regret as the performance measure, in both stochastic and non-stochastic settings. First, for general nonconvex functions, we consider nonstationary versions of first-order and second-order stationary solutions as a regret measure, motivated by similar performance measures for offline nonconvex optimization. In the case of second-order stationary solution based regret, we propose and analyze online and bandit versions of the cubic regularized Newton’s method. The bandit version is based on estimating the Hessian matrices in the bandit setting, based on second-order Gaussian Stein’s identity. Our nonstationary regret bounds in terms of second-order stationary solutions have interesting consequences for avoiding saddle points in the bandit setting. Next, for weakly quasi convex functions and monotone weakly submodular functions we consider nonstationary regret measures in terms of function-values; such structured classes of nonconvex functions enable one to consider regret measure defined in terms of function values, similar to convex functions. For this case of function-value, and first-order stationary solution based regret measures, we provide regret bounds in both the low- and high-dimensional settings, for some scenarios.
Tasks
Published	2019-07-31
URL	https://arxiv.org/abs/1907.13616v2
PDF	https://arxiv.org/pdf/1907.13616v2.pdf
PWC	https://paperswithcode.com/paper/multi-point-bandit-algorithms-for
Repo
Framework

Client-Edge-Cloud Hierarchical Federated Learning


Title	Client-Edge-Cloud Hierarchical Federated Learning
Authors	Lumin Liu, Jun Zhang, S. H. Song, Khaled B. Letaief
Abstract	Federated Learning is a collaborative machine learning framework to train a deep learning model without accessing clients’ private data. Previous works assume one central parameter server either at the cloud or at the edge. The cloud server can access more data but with excessive communication overhead and long latency, while the edge server enjoys more efficient communications with the clients. To combine their advantages, we propose a client-edge-cloud hierarchical Federated Learning system, supported with a HierFAVG algorithm that allows multiple edge servers to perform partial model aggregation. In this way, the model can be trained faster and better communication-computation trade-offs can be achieved. Convergence analysis is provided for HierFAVG and the effects of key parameters are also investigated, which lead to qualitative design guidelines. Empirical experiments verify the analysis and demonstrate the benefits of this hierarchical architecture in different data distribution scenarios. Particularly, it is shown that by introducing the intermediate edge servers, the model training time and the energy consumption of the end devices can be simultaneously reduced compared to cloud-based Federated Learning.
Tasks
Published	2019-05-16
URL	https://arxiv.org/abs/1905.06641v2
PDF	https://arxiv.org/pdf/1905.06641v2.pdf
PWC	https://paperswithcode.com/paper/edge-assisted-hierarchical-federated-learning
Repo
Framework

Brain Tumor Segmentation and Survival Prediction


Title	Brain Tumor Segmentation and Survival Prediction
Authors	Rupal Agravat, Mehul S Raval
Abstract	The paper demonstrates the use of the fully convolutional neural network for glioma segmentation on the BraTS 2019 dataset. Three-layers deep encoder-decoder architecture is used along with dense connection at encoder part to propagate the information from coarse layer to deep layers. This architecture is used to train three tumor sub-components separately. Subcomponent training weights are initialized with whole tumor weights to get the localization of the tumor within the brain. At the end, three segmentation results were merged to get the entire tumor segmentation. Dice Similarity of training dataset with focal loss implementation for whole tumor, tumor core and enhancing tumor is 0.92, 0.90 and 0.79 respectively. Radiomic features along with segmentation results and age are used to predict the overall survival of patients using random forest regressor to classify survival of patients in long, medium and short survival classes. 55.4% of classification accuracy is reported for training dataset with the scans whose resection status is gross-total resection.
Tasks	Brain Tumor Segmentation
Published	2019-09-20
URL	https://arxiv.org/abs/1909.09399v1
PDF	https://arxiv.org/pdf/1909.09399v1.pdf
PWC	https://paperswithcode.com/paper/brain-tumor-segmentation-and-survival
Repo
Framework


Title	Learning to Answer Subjective, Specific Product-Related Queries using Customer Reviews by Adversarial Domain Adaptation
Authors	Manirupa Das, Zhen Wang, Evan Jaffe, Madhuja Chattopadhyay, Eric Fosler-Lussier, Rajiv Ramnath
Abstract	Online customer reviews on large-scale e-commerce websites, represent a rich and varied source of opinion data, often providing subjective qualitative assessments of product usage that can help potential customers to discover features that meet their personal needs and preferences. Thus they have the potential to automatically answer specific queries about products, and to address the problems of answer starvation and answer augmentation on associated consumer Q & A forums, by providing good answer alternatives. In this work, we explore several recently successful neural approaches to modeling sentence pairs, that could better learn the relationship between questions and ground truth answers, and thus help infer reviews that can best answer a question or augment a given answer. In particular, we hypothesize that our adversarial domain adaptation-based approach, due to its ability to additionally learn domain-invariant features from a large number of unlabeled, unpaired question-review samples, would perform better than our proposed baselines, at answering specific, subjective product-related queries using reviews. We validate this hypothesis using a small gold standard dataset of question-review pairs evaluated by human experts, significantly surpassing our chosen baselines. Moreover, our approach, using no labeled question-review sentence pair data for training, gives performance at par with another method utilizing labeled question-review samples for the same task.
Tasks	Domain Adaptation
Published	2019-10-18
URL	https://arxiv.org/abs/1910.08270v2
PDF	https://arxiv.org/pdf/1910.08270v2.pdf
PWC	https://paperswithcode.com/paper/learning-to-answer-subjective-specific
Repo
Framework

A GFML-based Robot Agent for Human and Machine Cooperative Learning on Game of Go


Title	A GFML-based Robot Agent for Human and Machine Cooperative Learning on Game of Go
Authors	Chang-Shing Lee, Mei-Hui Wang, Li-Chuang Chen, Yusuke Nojima, Tzong-Xiang Huang, Jinseok Woo, Naoyuki Kubota, Eri Sato-Shimokawara, Toru Yamaguchi
Abstract	This paper applies a genetic algorithm and fuzzy markup language to construct a human and smart machine cooperative learning system on game of Go. The genetic fuzzy markup language (GFML)-based Robot Agent can work on various kinds of robots, including Palro, Pepper, and TMUs robots. We use the parameters of FAIR open source Darkforest and OpenGo AI bots to construct the knowledge base of Open Go Darkforest (OGD) cloud platform for student learning on the Internet. In addition, we adopt the data from AlphaGo Master sixty online games as the training data to construct the knowledge base and rule base of the co-learning system. First, the Darkforest predicts the win rate based on various simulation numbers and matching rates for each game on OGD platform, then the win rate of OpenGo is as the final desired output. The experimental results show that the proposed approach can improve knowledge base and rule base of the prediction ability based on Darkforest and OpenGo AI bot with various simulation numbers.
Tasks	Game of Go
Published	2019-01-22
URL	http://arxiv.org/abs/1901.07191v1
PDF	http://arxiv.org/pdf/1901.07191v1.pdf
PWC	https://paperswithcode.com/paper/a-gfml-based-robot-agent-for-human-and
Repo
Framework

Unsupervised Paraphrasing by Simulated Annealing


Title	Unsupervised Paraphrasing by Simulated Annealing
Authors	Xianggen Liu, Lili Mou, Fandong Meng, Hao Zhou, Jie Zhou, Sen Song
Abstract	Unsupervised paraphrase generation is a promising and important research topic in natural language processing. We propose UPSA, a novel approach that accomplishes Unsupervised Paraphrasing by Simulated Annealing. We model paraphrase generation as an optimization problem and propose a sophisticated objective function, involving semantic similarity, expression diversity, and language fluency of paraphrases. Then, UPSA searches the sentence space towards this objective by performing a sequence of local editing. Our method is unsupervised and does not require parallel corpora for training, so it could be easily applied to different domains. We evaluate our approach on a variety of benchmark datasets, namely, Quora, Wikianswers, MSCOCO, and Twitter. Extensive results show that UPSA achieves the state-of-the-art performance compared with previous unsupervised methods in terms of both automatic and human evaluations. Further, our approach outperforms most existing domain-adapted supervised models, showing the generalizability of UPSA.
Tasks	Paraphrase Generation, Semantic Similarity, Semantic Textual Similarity
Published	2019-09-09
URL	https://arxiv.org/abs/1909.03588v2
PDF	https://arxiv.org/pdf/1909.03588v2.pdf
PWC	https://paperswithcode.com/paper/unsupervised-paraphrasing-by-simulated
Repo
Framework

Enhancing Stratospheric Weather Analyses and Forecasts by Deploying Sensors from a Weather Balloon


Title	Enhancing Stratospheric Weather Analyses and Forecasts by Deploying Sensors from a Weather Balloon
Authors	Kiwan Maeng, Iskender Kushan, Brandon Lucia, Ashish Kapoor
Abstract	The ability to analyze and forecast stratospheric weather conditions is fundamental to addressing climate change. However, our capacity to collect data in the stratosphere is limited by sparsely deployed weather balloons. We propose a framework to collect stratospheric data by releasing a contrail of tiny sensor devices as a weather balloon ascends. The key machine learning challenges are determining when and how to deploy a finite collection of sensors to produce a useful data set. We decide when to release sensors by modeling the deviation of a forecast from actual stratospheric conditions as a Gaussian process. We then implement a novel hardware system that is capable of optimally releasing sensors from a rising weather balloon. We show that this data engineering framework is effective through real weather balloon flights, as well as simulations.
Tasks
Published	2019-12-04
URL	https://arxiv.org/abs/1912.02276v1
PDF	https://arxiv.org/pdf/1912.02276v1.pdf
PWC	https://paperswithcode.com/paper/enhancing-stratospheric-weather-analyses-and
Repo
Framework

TBC-Net: A real-time detector for infrared small target detection using semantic constraint


Title	TBC-Net: A real-time detector for infrared small target detection using semantic constraint
Authors	Mingxin Zhao, Li Cheng, Xu Yang, Peng Feng, Liyuan Liu, Nanjian Wu
Abstract	Infrared small target detection is a key technique in infrared search and tracking (IRST) systems. Although deep learning has been widely used in the vision tasks of visible light images recently, it is rarely used in infrared small target detection due to the difficulty in learning small target features. In this paper, we propose a novel lightweight convolutional neural network TBC-Net for infrared small target detection. The TBCNet consists of a target extraction module (TEM) and a semantic constraint module (SCM), which are used to extract small targets from infrared images and to classify the extracted target images during the training, respectively. Meanwhile, we propose a joint loss function and a training method. The SCM imposes a semantic constraint on TEM by combining the high-level classification task and solve the problem of the difficulty to learn features caused by class imbalance problem. During the training, the targets are extracted from the input image and then be classified by SCM. During the inference, only the TEM is used to detect the small targets. We also propose a data synthesis method to generate training data. The experimental results show that compared with the traditional methods, TBC-Net can better reduce the false alarm caused by complicated background, the proposed network structure and joint loss have a significant improvement on small target feature learning. Besides, TBC-Net can achieve real-time detection on the NVIDIA Jetson AGX Xavier development board, which is suitable for applications such as field research with drones equipped with infrared sensors.
Tasks
Published	2019-12-27
URL	https://arxiv.org/abs/2001.05852v1
PDF	https://arxiv.org/pdf/2001.05852v1.pdf
PWC	https://paperswithcode.com/paper/tbc-net-a-real-time-detector-for-infrared
Repo
Framework

Prostate Segmentation from Ultrasound Images using Residual Fully Convolutional Network


Title	Prostate Segmentation from Ultrasound Images using Residual Fully Convolutional Network
Authors	M. S. Hossain, A. P. Paplinski, J. M. Betts
Abstract	Medical imaging based prostate cancer diagnosis procedure uses intra-operative transrectal ultrasound (TRUS) imaging to visualize the prostate shape and location to collect tissue samples. Correct tissue sampling from prostate requires accurate prostate segmentation in TRUS images. To achieve this, this study uses a novel residual connection based fully convolutional network. The advantage of this segmentation technique is that it requires no pre-processing of TRUS images to perform the segmentation. Thus, it offers a faster and straightforward prostate segmentation from TRUS images. Results show that the proposed technique can achieve around 86% Dice Similarity accuracy using only few TRUS datasets.
Tasks
Published	2019-03-21
URL	http://arxiv.org/abs/1903.08814v1
PDF	http://arxiv.org/pdf/1903.08814v1.pdf
PWC	https://paperswithcode.com/paper/prostate-segmentation-from-ultrasound-images
Repo
Framework

Gene Expression based Survival Prediction for Cancer Patients: A Topic Modeling Approach


Title	Gene Expression based Survival Prediction for Cancer Patients: A Topic Modeling Approach
Authors	Luke Kumar, Russell Greiner
Abstract	Cancer is one of the leading cause of death, worldwide. Many believe that genomic data will enable us to better predict the survival time of these patients, which will lead to better, more personalized treatment options and patient care. As standard survival prediction models have a hard time coping with the high-dimensionality of such gene expression (GE) data, many projects use some dimensionality reduction techniques to overcome this hurdle. We introduce a novel methodology, inspired by topic modeling from the natural language domain, to derive expressive features from the high-dimensional GE data. There, a document is represented as a mixture over a relatively small number of topics, where each topic corresponds to a distribution over the words; here, to accommodate the heterogeneity of a patient’s cancer, we represent each patient (~document) as a mixture over cancer-topics, where each cancer-topic is a mixture over GE values (~words). This required some extensions to the standard LDA model eg: to accommodate the “real-valued” expression values - leading to our novel “discretized” Latent Dirichlet Allocation (dLDA) procedure. We initially focus on the METABRIC dataset, which describes breast cancer patients using the r=49,576 GE values, from microarrays. Our results show that our approach provides survival estimates that are more accurate than standard models, in terms of the standard Concordance measure. We then validate this approach by running it on the Pan-kidney (KIPAN) dataset, over r=15,529 GE values - here using the mRNAseq modality - and find that it again achieves excellent results. In both cases, we also show that the resulting model is calibrated, using the recent “D-calibrated” measure. These successes, in two different cancer types and expression modalities, demonstrates the generality, and the effectiveness, of this approach.
Tasks	Dimensionality Reduction
Published	2019-03-25
URL	https://arxiv.org/abs/1903.10536v2
PDF	https://arxiv.org/pdf/1903.10536v2.pdf
PWC	https://paperswithcode.com/paper/gene-expression-based-survival-prediction-for
Repo
Framework