January 28, 2020

3083 words 15 mins read

Paper Group ANR 990

Sinogram interpolation for sparse-view micro-CT with deep learning neural network. SAPSAM - Sparsely Annotated Pathological Sign Activation Maps - A novel approach to train Convolutional Neural Networks on lung CT scans using binary labels only. A Novel Approach for Partial Fingerprint Identification to Mitigate MasterPrint Generation. Conditional …

Sinogram interpolation for sparse-view micro-CT with deep learning neural network


Title	Sinogram interpolation for sparse-view micro-CT with deep learning neural network
Authors	Xu Dong, Swapnil Vekhande, Guohua Cao
Abstract	In sparse-view Computed Tomography (CT), only a small number of projection images are taken around the object, and sinogram interpolation method has a significant impact on final image quality. When the amount of sparsity (the amount of missing views in sinogram data) is not high, conventional interpolation methods have yielded good results. When the amount of sparsity is high, more advanced sinogram interpolation methods are needed. Recently, several deep learning (DL) based sinogram interpolation methods have been proposed. However, those DL-based methods have mostly tested so far on computer simulated sinogram data rather experimentally acquired sinogram data. In this study, we developed a sinogram interpolation method for sparse-view micro-CT based on the combination of U-Net and residual learning. We applied the method to sinogram data obtained from sparse-view micro-CT experiments, where the sparsity reached 90%. The interpolated sinogram by the DL neural network was fed to FBP algorithm for reconstruction. The result shows that both RMSE and SSIM of CT image are greatly improved. The experimental results demonstrate that this sinogram interpolation method produce significantly better results over standard linear interpolation methods when the sinogram data are extremely sparse.
Tasks	Computed Tomography (CT)
Published	2019-02-09
URL	http://arxiv.org/abs/1902.03362v2
PDF	http://arxiv.org/pdf/1902.03362v2.pdf
PWC	https://paperswithcode.com/paper/sinogram-interpolation-for-sparse-view-micro
Repo
Framework

SAPSAM - Sparsely Annotated Pathological Sign Activation Maps - A novel approach to train Convolutional Neural Networks on lung CT scans using binary labels only


Title	SAPSAM - Sparsely Annotated Pathological Sign Activation Maps - A novel approach to train Convolutional Neural Networks on lung CT scans using binary labels only
Authors	Mario Zusag, Sujal Desai, Marcello Di Paolo, Thomas Semple, Anand Shah, Elsa Angelini
Abstract	Chronic Pulmonary Aspergillosis (CPA) is a complex lung disease caused by infection with Aspergillus. Computed tomography (CT) images are frequently requested in patients with suspected and established disease, but the radiological signs on CT are difficult to quantify making accurate follow-up challenging. We propose a novel method to train Convolutional Neural Networks using only regional labels on the presence of pathological signs, to not only detect CPA, but also spatially localize pathological signs. We use average intensity projections within different ranges of Hounsfield-unit (HU) values, transforming input 3D CT scans into 2D RGB-like images. CNN architectures are trained for hierarchical tasks, leading to precise activation maps of pathological patterns. Results on a cohort of 352 subjects demonstrate high classification accuracy, localization precision and predictive power of 2 year survival. Such tool opens the way to CPA patient stratification and quantitative follow-up of CPA pathological signs, for patients under drug therapy.
Tasks	Computed Tomography (CT)
Published	2019-02-06
URL	http://arxiv.org/abs/1902.02629v1
PDF	http://arxiv.org/pdf/1902.02629v1.pdf
PWC	https://paperswithcode.com/paper/sapsam-sparsely-annotated-pathological-sign
Repo
Framework

A Novel Approach for Partial Fingerprint Identification to Mitigate MasterPrint Generation


Title	A Novel Approach for Partial Fingerprint Identification to Mitigate MasterPrint Generation
Authors	Mahesh Joshi, Bodhisatwa Mazumdar, Somnath Dey
Abstract	Partial fingerprint recognition is a method to recognize an individual when the sensor size has a small form factor in accepting a full fingerprint. It is also used in forensic research to identify the partial fingerprints collected from the crime scenes. But the distinguishing features in the partial fingerprint are relatively low due to small fingerprint captured by the sensor. Hence, the uniqueness of a partial fingerprint cannot be guaranteed, leading to a possibility that a single partial fingerprint may identify multiple subjects. A MasterPrint is a partial fingerprint that identifies at least 4% different individuals from the enrolled template database. A fingerprint identification system with such a flaw can play a significant role in convicting an innocent in a criminal case. We propose a partial fingerprint identification approach that aims to mitigate MasterPrint generation. The proposed method, when applied to partial fingerprint dataset cropped from standard FVC 2002 DB1(A) dataset showed significant improvement in reducing the count of MasterPrints. The experimental result demonstrates improved results on other parameters, such as True match Rate (TMR) and Equal Error Rate (EER), generally used to evaluate the performance of a fingerprint biometric system.
Tasks
Published	2019-11-08
URL	https://arxiv.org/abs/1911.03052v1
PDF	https://arxiv.org/pdf/1911.03052v1.pdf
PWC	https://paperswithcode.com/paper/a-novel-approach-for-partial-fingerprint
Repo
Framework

Conditional Super Learner


Title	Conditional Super Learner
Authors	Gilmer Valdes, Yannet Interian, Efstathios D. Gennatas Mark J. Van der Laan
Abstract	In this article we consider the Conditional Super Learner (CSL), an algorithm which selects the best model candidate from a library conditional on the covariates. The CSL expands the idea of using cross-validation to select the best model and merges it with meta learning. Here we propose a specific algorithm that finds a local minimum to the problem posed, proof that it converges at a rate faster than Op(n^-1/4) and offers extensive empirical evidence that it is an excellent candidate to substitute stacking or for the analysis of Hierarchical problems.
Tasks	Meta-Learning
Published	2019-12-13
URL	https://arxiv.org/abs/1912.06675v1
PDF	https://arxiv.org/pdf/1912.06675v1.pdf
PWC	https://paperswithcode.com/paper/conditional-super-learner
Repo
Framework

Multiple-objective Reinforcement Learning for Inverse Design and Identification


Title	Multiple-objective Reinforcement Learning for Inverse Design and Identification
Authors	Haoran Wei, Mariefel Olarte, Garrett B. Goh
Abstract	The aim of the inverse chemical design is to develop new molecules with given optimized molecular properties or objectives. Recently, generative deep learning (DL) networks are considered as the state-of-the-art in inverse chemical design and have achieved early success in generating molecular structures with desired properties in the pharmaceutical and material chemistry fields. However, satisfying a large number (larger than 10 objectives) of molecular objectives is a limitation of current generative models. To improve the model’s ability to handle a large number of molecule design objectives, we developed a Reinforcement Learning (RL) based generative framework to optimize chemical molecule generation. Our use of Curriculum Learning (CL) to fine-tune the pre-trained generative network allowed the model to satisfy up to 21 objectives and increase the generative network’s robustness. The experiments show that the proposed multiple-objective RL-based generative model can correctly identify unknown molecules with an 83 to 100 percent success rate, compared to the baseline approach of 0 percent. Additionally, this proposed generative model is not limited to just chemistry research challenges; we anticipate that problems that utilize RL with multiple-objectives will benefit from this framework.
Tasks
Published	2019-10-09
URL	https://arxiv.org/abs/1910.03741v1
PDF	https://arxiv.org/pdf/1910.03741v1.pdf
PWC	https://paperswithcode.com/paper/multiple-objective-reinforcement-learning-for
Repo
Framework

Review-based Question Generation with Adaptive Instance Transfer and Augmentation


Title	Review-based Question Generation with Adaptive Instance Transfer and Augmentation
Authors	Qian Yu, Lidong Bing, Qiong Zhang, Wai Lam, Luo Si
Abstract	Online reviews provide rich information about products and service, while it remains inefficient for potential consumers to exploit the reviews for fulfilling their specific information need. We propose to explore question generation as a new way of exploiting review information. One major challenge of this task is the lack of review-question pairs for training a neural generation model. We propose an iterative learning framework for handling this challenge via adaptive transfer and augmentation of the training instances with the help of the available user-posed question-answer data. To capture the aspect characteristics in reviews, the augmentation and generation procedures incorporate related features extracted via unsupervised learning. Experiments on data from 10 categories of a popular E-commerce site demonstrate the effectiveness of the framework, as well as the usefulness of the new task.
Tasks	Question Generation
Published	2019-11-05
URL	https://arxiv.org/abs/1911.01556v1
PDF	https://arxiv.org/pdf/1911.01556v1.pdf
PWC	https://paperswithcode.com/paper/review-based-question-generation-with
Repo
Framework

Volume Preserving Image Segmentation with Entropic Regularization Optimal Transport and Its Applications in Deep Learning


Title	Volume Preserving Image Segmentation with Entropic Regularization Optimal Transport and Its Applications in Deep Learning
Authors	Haifeng Li, Jun Liu, Li Cui, Haiyang Huang, Xue-cheng Tai
Abstract	Image segmentation with a volume constraint is an important prior for many real applications. In this work, we present a novel volume preserving image segmentation algorithm, which is based on the framework of entropic regularized optimal transport theory. The classical Total Variation (TV) regularizer and volume preserving are integrated into a regularized optimal transport model, and the volume and classification constraints can be regarded as two measures preserving constraints in the optimal transport problem. By studying the dual problem, we develop a simple and efficient dual algorithm for our model. Moreover, to be different from many variational based image segmentation algorithms, the proposed algorithm can be directly unrolled to a new Volume Preserving and TV regularized softmax (VPTV-softmax) layer for semantic segmentation in the popular Deep Convolution Neural Network (DCNN). The experiment results show that our proposed model is very competitive and can improve the performance of many semantic segmentation nets such as the popular U-net.
Tasks	Semantic Segmentation
Published	2019-09-22
URL	https://arxiv.org/abs/1909.09931v2
PDF	https://arxiv.org/pdf/1909.09931v2.pdf
PWC	https://paperswithcode.com/paper/190909931
Repo
Framework

Automated Left Ventricle Dimension Measurement in 2D Cardiac Ultrasound via an Anatomically Meaningful CNN Approach


Title	Automated Left Ventricle Dimension Measurement in 2D Cardiac Ultrasound via an Anatomically Meaningful CNN Approach
Authors	Andrew Gilbert, Marit Holden, Line Eikvil, Svein Arne Aase, Eigil Samset, Kristin McLeod
Abstract	Two-dimensional echocardiography (2DE) measurements of left ventricle (LV) dimensions are highly significant markers of several cardiovascular diseases. These measurements are often used in clinical care despite suffering from large variability between observers. This variability is due to the challenging nature of accurately finding the correct temporal and spatial location of measurement endpoints in ultrasound images. These images often contain fuzzy boundaries and varying reflection patterns between frames. In this work, we present a convolutional neural network (CNN) based approach to automate 2DE LV measurements. Treating the problem as a landmark detection problem, we propose a modified U-Net CNN architecture to generate heatmaps of likely coordinate locations. To improve the network performance we use anatomically meaningful heatmaps as labels and train with a multi-component loss function. Our network achieves 13.4%, 6%, and 10.8% mean percent error on intraventricular septum (IVS), LV internal dimension (LVID), and LV posterior wall (LVPW) measurements respectively. The design outperforms other networks and matches or approaches intra-analyser expert error.
Tasks
Published	2019-11-06
URL	https://arxiv.org/abs/1911.02448v1
PDF	https://arxiv.org/pdf/1911.02448v1.pdf
PWC	https://paperswithcode.com/paper/automated-left-ventricle-dimension
Repo
Framework

U-Net Based Multi-instance Video Object Segmentation


Title	U-Net Based Multi-instance Video Object Segmentation
Authors	Heguang Liu, Jingle Jiang
Abstract	Multi-instance video object segmentation is to segment specific instances throughout a video sequence in pixel level, given only an annotated first frame. In this paper, we implement an effective fully convolutional networks with U-Net similar structure built on top of OSVOS fine-tuned layer. We use instance isolation to transform this multi-instance segmentation problem into binary labeling problem, and use weighted cross entropy loss and dice coefficient loss as our loss function. Our best model achieves F mean of 0.467 and J mean of 0.424 on DAVIS dataset, which is a comparable performance with the State-of-the-Art approach. But case analysis shows this model can achieve a smoother contour and better instance coverage, meaning it better for recall focused segmentation scenario. We also did experiments on other convolutional neural networks, including Seg-Net, Mask R-CNN, and provide insightful comparison and discussion.
Tasks	Instance Segmentation, Semantic Segmentation, Video Object Segmentation, Video Semantic Segmentation
Published	2019-05-19
URL	https://arxiv.org/abs/1905.07826v1
PDF	https://arxiv.org/pdf/1905.07826v1.pdf
PWC	https://paperswithcode.com/paper/u-net-based-multi-instance-video-object
Repo
Framework

On Linear Learning with Manycore Processors


Title	On Linear Learning with Manycore Processors
Authors	Eliza Wszola, Celestine Mendler-Dünner, Martin Jaggi, Markus Püschel
Abstract	A new generation of manycore processors is on the rise that offers dozens and more cores on a chip and, in a sense, fuses host processor and accelerator. In this paper we target the efficient training of generalized linear models on these machines. We propose a novel approach for achieving parallelism which we call Heterogeneous Tasks on Homogeneous Cores (HTHC). It divides the problem into multiple fundamentally different tasks, which themselves are parallelized. For evaluation, we design a detailed, architecture-cognizant implementation of our scheme on a recent 72-core Knights Landing processor that is adaptive to the cache, memory, and core structure. Our library efficiently supports dense and sparse datasets as well as 4-bit quantized data for further possible gains in performance. We show benchmarks for Lasso and SVM with different data sets against straightforward parallel implementations and prior software. In particular, for Lasso on dense data, we improve the state-of-the-art by an order of magnitude.
Tasks
Published	2019-05-02
URL	https://arxiv.org/abs/1905.00626v6
PDF	https://arxiv.org/pdf/1905.00626v6.pdf
PWC	https://paperswithcode.com/paper/on-linear-learning-with-manycore-processors
Repo
Framework

Attentive Knowledge Graph Embedding for Personalized Recommendation


Title	Attentive Knowledge Graph Embedding for Personalized Recommendation
Authors	Xiao Sha, Zhu Sun, Jie Zhang
Abstract	Knowledge graphs (KGs) have proven to be effective for high-quality recommendation. Most efforts, however, explore KGs by either extracting separate paths connecting user-item pairs, or iteratively propagating user preference over the entire KGs, thus failing to efficiently exploit KGs for enhanced recommendation. In this paper, we design a novel attentive knowledge graph embedding (AKGE) framework for recommendation, which sufficiently exploits both semantics and topology of KGs in an interaction-specific manner. Specifically, AKGE first automatically extracts high-order subgraphs that link user-item pairs with rich semantics, and then encodes the subgraphs by the proposed attentive graph neural network to learn accurate user preference. Extensive experiments on three real-world datasets demonstrate that AKGE consistently outperforms state-of-the-art methods. It additionally provides potential explanations for the recommendation results.
Tasks	Graph Embedding, Knowledge Graph Embedding, Knowledge Graphs
Published	2019-10-18
URL	https://arxiv.org/abs/1910.08288v3
PDF	https://arxiv.org/pdf/1910.08288v3.pdf
PWC	https://paperswithcode.com/paper/attentive-knowledge-graph-embedding-for
Repo
Framework

Informative GANs via Structured Regularization of Optimal Transport


Title	Informative GANs via Structured Regularization of Optimal Transport
Authors	Pierre Bréchet, Tao Wu, Thomas Möllenhoff, Daniel Cremers
Abstract	We tackle the challenge of disentangled representation learning in generative adversarial networks (GANs) from the perspective of regularized optimal transport (OT). Specifically, a smoothed OT loss gives rise to an implicit transportation plan between the latent space and the data space. Based on this theoretical observation, we exploit a structured regularization on the transportation plan to encourage a prescribed latent subspace to be informative. This yields the formulation of a novel informative OT-based GAN. By convex duality, we obtain the equivalent view that this leads to perturbed ground costs favoring sparsity in the informative latent dimensions. Practically, we devise a stable training algorithm for the proposed informative GAN. Our experiments support the hypothesis that such regularizations effectively yield the discovery of disentangled and interpretable latent representations. Our work showcases potential power of a regularized OT framework in the context of generative modeling through its access to the transport plan. Further challenges are addressed in this line.
Tasks	Representation Learning
Published	2019-12-04
URL	https://arxiv.org/abs/1912.02160v1
PDF	https://arxiv.org/pdf/1912.02160v1.pdf
PWC	https://paperswithcode.com/paper/informative-gans-via-structured
Repo
Framework

SISC: End-to-end Interpretable Discovery Radiomics-Driven Lung Cancer Prediction via Stacked Interpretable Sequencing Cells


Title	SISC: End-to-end Interpretable Discovery Radiomics-Driven Lung Cancer Prediction via Stacked Interpretable Sequencing Cells
Authors	Vignesh Sankar, Devinder Kumar, David A. Clausi, Graham W. Taylor, Alexander Wong
Abstract	Objective: Lung cancer is the leading cause of cancer-related death worldwide. Computer-aided diagnosis (CAD) systems have shown significant promise in recent years for facilitating the effective detection and classification of abnormal lung nodules in computed tomography (CT) scans. While hand-engineered radiomic features have been traditionally used for lung cancer prediction, there have been significant recent successes achieving state-of-the-art results in the area of discovery radiomics. Here, radiomic sequencers comprising of highly discriminative radiomic features are discovered directly from archival medical data. However, the interpretation of predictions made using such radiomic sequencers remains a challenge. Method: A novel end-to-end interpretable discovery radiomics-driven lung cancer prediction pipeline has been designed, build, and tested. The radiomic sequencer being discovered possesses a deep architecture comprised of stacked interpretable sequencing cells (SISC). Results: The SISC architecture is shown to outperform previous approaches while providing more insight in to its decision making process. Conclusion: The SISC radiomic sequencer is able to achieve state-of-the-art results in lung cancer prediction, and also offers prediction interpretability in the form of critical response maps. Significance: The critical response maps are useful for not only validating the predictions of the proposed SISC radiomic sequencer, but also provide improved radiologist-machine collaboration for effective diagnosis.
Tasks	Computed Tomography (CT), Decision Making
Published	2019-01-15
URL	http://arxiv.org/abs/1901.04641v1
PDF	http://arxiv.org/pdf/1901.04641v1.pdf
PWC	https://paperswithcode.com/paper/sisc-end-to-end-interpretable-discovery
Repo
Framework

Composition and decomposition of GANs


Title	Composition and decomposition of GANs
Authors	Yeu-Chern Harn, Zhenghao Chen, Vladimir Jojic
Abstract	In this work, we propose a composition/decomposition framework for adversarially training generative models on composed data - data where each sample can be thought of as being constructed from a fixed number of components. In our framework, samples are generated by sampling components from component generators and feeding these components to a composition function which combines them into a “composed sample”. This compositional training approach improves the modularity, extensibility and interpretability of Generative Adversarial Networks (GANs) - providing a principled way to incrementally construct complex models out of simpler component models, and allowing for explicit “division of responsibility” between these components. Using this framework, we define a family of learning tasks and evaluate their feasibility on two datasets in two different data modalities (image and text). Lastly, we derive sufficient conditions such that these compositional generative models are identifiable. Our work provides a principled approach to building on pre-trained generative models or for exploiting the compositional nature of data distributions to train extensible and interpretable models.
Tasks
Published	2019-01-23
URL	http://arxiv.org/abs/1901.07667v1
PDF	http://arxiv.org/pdf/1901.07667v1.pdf
PWC	https://paperswithcode.com/paper/composition-and-decomposition-of-gans
Repo
Framework

Reference Setup for Quantitative Comparison of Segmentation Techniques for Short Glass Fiber CT Data


Title	Reference Setup for Quantitative Comparison of Segmentation Techniques for Short Glass Fiber CT Data
Authors	Tomasz Konopczyński, Jitendra Rathore, Thorben Kröger, Lei Zheng, Christoph S. Garbe, Simone Carmignato, Jürgen Hesser
Abstract	Comparing different algorithms for segmenting glass fibers in industrial computed tomography (CT) scans is difficult due to the absence of a standard reference dataset. In this work, we introduce a set of annotated scans of short-fiber reinforced polymers (SFRP) as well as synthetically created CT volume data together with the evaluation metrics. We suggest both the metrics and this data set as a reference for studying the performance of different algorithms. The real scans were acquired by a Nikon MCT225 X-ray CT system. The simulated scans were created by the use of an in-house computational model and third-party commercial software. For both types of data, corresponding ground truth annotations have been prepared, including hand annotations for the real scans and STL models for the synthetic scans. Additionally, a Hessian-based Frangi vesselness filter for fiber segmentation has been implemented and open-sourced to serve as a reference for comparisons.
Tasks	Computed Tomography (CT)
Published	2019-01-04
URL	http://arxiv.org/abs/1901.01210v1
PDF	http://arxiv.org/pdf/1901.01210v1.pdf
PWC	https://paperswithcode.com/paper/reference-setup-for-quantitative-comparison
Repo
Framework