April 2, 2020

3092 words 15 mins read

Paper Group ANR 313

Machine Learning based prediction of noncentrosymmetric crystal materials. Cytology Image Analysis Techniques Towards Automation: Systematically Revisited. Strip Pooling: Rethinking Spatial Pooling for Scene Parsing. Exploring Partial Intrinsic and Extrinsic Symmetry in 3D Medical Imaging. DeepFit: 3D Surface Fitting via Neural Network Weighted Lea …

Machine Learning based prediction of noncentrosymmetric crystal materials


Title	Machine Learning based prediction of noncentrosymmetric crystal materials
Authors	Yuqi Song, Joseph Lindsay, Yong Zhao, Alireza Nasiri, Steph-Yves Loius, Jie Ling, Ming Hu, Jianjun Hu
Abstract	Noncentrosymmetric materials play a critical role in many important applications such as laser technology, communication systems,quantum computing, cybersecurity, and etc. However, the experimental discovery of new noncentrosymmetric materials is extremely difficult. Here we present a machine learning model that could predict whether the composition of a potential crystalline structure would be centrosymmetric or not. By evaluating a diverse set of composition features calculated using matminer featurizer package coupled with different machine learning algorithms, we find that Random Forest Classifiers give the best performance for noncentrosymmetric material prediction, reaching an accuracy of 84.8% when evaluated with 10 fold cross-validation on the dataset with 82,506 samples extracted from Materials Project. A random forest model trained with materials with only 3 elements gives even higher accuracy of 86.9%. We apply our ML model to screen potential noncentrosymmetric materials from 2,000,000 hypothetical materials generated by our inverse design engine and report the top 20 candidate noncentrosymmetric materials with 2 to 4 elements and top 20 borate candidates
Tasks
Published	2020-02-26
URL	https://arxiv.org/abs/2002.11295v1
PDF	https://arxiv.org/pdf/2002.11295v1.pdf
PWC	https://paperswithcode.com/paper/machine-learning-based-prediction-of-1
Repo
Framework

Cytology Image Analysis Techniques Towards Automation: Systematically Revisited


Title	Cytology Image Analysis Techniques Towards Automation: Systematically Revisited
Authors	Shyamali Mitra, Nibaran Das, Soumyajyoti Dey, Sukanta Chakrabarty, Mita Nasipuri, Mrinal Kanti Naskar
Abstract	Cytology is the branch of pathology which deals with the microscopic examination of cells for diagnosis of carcinoma or inflammatory conditions. Automation in cytology started in the early 1950s with the aim to reduce manual efforts in diagnosis of cancer. The inflush of intelligent technological units with high computational power and improved specimen collection techniques helped to achieve its technological heights. In the present survey, we focus on such image processing techniques which put steps forward towards the automation of cytology. We take a short tour to 17 types of cytology and explore various segmentation and/or classification techniques which evolved during last three decades boosting the concept of automation in cytology. It is observed, that most of the works are aligned towards three types of cytology: Cervical, Breast and Lung, which are discussed elaborately in this paper. The user-end systems developed during that period are summarized to comprehend the overall growth in the respective domains. To be precise, we discuss the diversity of the state-of-the-art methodologies, their challenges to provide prolific and competent future research directions inbringing the cytology-based commercial systems into the mainstream.
Tasks
Published	2020-03-17
URL	https://arxiv.org/abs/2003.07529v1
PDF	https://arxiv.org/pdf/2003.07529v1.pdf
PWC	https://paperswithcode.com/paper/cytology-image-analysis-techniques-towards
Repo
Framework

Strip Pooling: Rethinking Spatial Pooling for Scene Parsing


Title	Strip Pooling: Rethinking Spatial Pooling for Scene Parsing
Authors	Qibin Hou, Li Zhang, Ming-Ming Cheng, Jiashi Feng
Abstract	Spatial pooling has been proven highly effective in capturing long-range contextual information for pixel-wise prediction tasks, such as scene parsing. In this paper, beyond conventional spatial pooling that usually has a regular shape of NxN, we rethink the formulation of spatial pooling by introducing a new pooling strategy, called strip pooling, which considers a long but narrow kernel, i.e., 1xN or Nx1. Based on strip pooling, we further investigate spatial pooling architecture design by 1) introducing a new strip pooling module that enables backbone networks to efficiently model long-range dependencies, 2) presenting a novel building block with diverse spatial pooling as a core, and 3) systematically comparing the performance of the proposed strip pooling and conventional spatial pooling techniques. Both novel pooling-based designs are lightweight and can serve as an efficient plug-and-play module in existing scene parsing networks. Extensive experiments on popular benchmarks (e.g., ADE20K and Cityscapes) demonstrate that our simple approach establishes new state-of-the-art results. Code is made available at https://github.com/Andrew-Qibin/SPNet.
Tasks	Scene Parsing
Published	2020-03-30
URL	https://arxiv.org/abs/2003.13328v1
PDF	https://arxiv.org/pdf/2003.13328v1.pdf
PWC	https://paperswithcode.com/paper/2003-13328
Repo
Framework

Exploring Partial Intrinsic and Extrinsic Symmetry in 3D Medical Imaging


Title	Exploring Partial Intrinsic and Extrinsic Symmetry in 3D Medical Imaging
Authors	Javad Fotouhi, Giacomo Taylor, Mathias Unberath, Alex Johnson, Sing Chun Lee, Greg Osgood, Mehran Armand, Nassir Navab
Abstract	We present a novel methodology to detect imperfect bilateral symmetry in CT of human anatomy. In this paper, the structurally symmetric nature of the pelvic bone is explored and is used to provide interventional image augmentation for treatment of unilateral fractures in patients with traumatic injuries. The mathematical basis of our solution is on the incorporation of attributes and characteristics that satisfy the properties of intrinsic and extrinsic symmetry and are robust to outliers. In the first step, feature points that satisfy intrinsic symmetry are automatically detected in the M"obius space defined on the CT data. These features are then pruned via a two-stage RANSAC to attain correspondences that satisfy also the extrinsic symmetry. Then, a disparity function based on Tukey’s biweight robust estimator is introduced and minimized to identify a symmetry plane parametrization that yields maximum contralateral similarity. Finally, a novel regularization term is introduced to enhance similarity between bone density histograms across the partial symmetry plane, relying on the important biological observation that, even if injured, the dislocated bone segments remain within the body. Our extensive evaluations on various cases of common fracture types demonstrate the validity of the novel concepts and the robustness and accuracy of the proposed method.
Tasks	Image Augmentation
Published	2020-03-04
URL	https://arxiv.org/abs/2003.02294v1
PDF	https://arxiv.org/pdf/2003.02294v1.pdf
PWC	https://paperswithcode.com/paper/exploring-partial-intrinsic-and-extrinsic
Repo
Framework

DeepFit: 3D Surface Fitting via Neural Network Weighted Least Squares


Title	DeepFit: 3D Surface Fitting via Neural Network Weighted Least Squares
Authors	Yizhak Ben-Shabat, Stephen Gould
Abstract	We propose a surface fitting method for unstructured 3D point clouds. This method, called DeepFit, incorporates a neural network to learn point-wise weights for weighted least squares polynomial surface fitting. The learned weights act as a soft selection for the neighborhood of surface points thus avoiding the scale selection required of previous methods. To train the network we propose a novel surface consistency loss that improves point weight estimation. The method enables extracting normal vectors and other geometrical properties, such as principal curvatures, the latter were not presented as ground truth during training. We achieve state-of-the-art results on a benchmark normal and curvature estimation dataset, demonstrate robustness to noise, outliers and density variations, and show its application on noise removal.
Tasks
Published	2020-03-23
URL	https://arxiv.org/abs/2003.10826v1
PDF	https://arxiv.org/pdf/2003.10826v1.pdf
PWC	https://paperswithcode.com/paper/deepfit-3d-surface-fitting-via-neural-network
Repo
Framework

Over-parameterized Adversarial Training: An Analysis Overcoming the Curse of Dimensionality


Title	Over-parameterized Adversarial Training: An Analysis Overcoming the Curse of Dimensionality
Authors	Yi Zhang, Orestis Plevrakis, Simon S. Du, Xingguo Li, Zhao Song, Sanjeev Arora
Abstract	Adversarial training is a popular method to give neural nets robustness against adversarial perturbations. In practice adversarial training leads to low robust training loss. However, a rigorous explanation for why this happens under natural conditions is still missing. Recently a convergence theory for standard (non-adversarial) supervised training was developed by various groups for {\em very overparametrized} nets. It is unclear how to extend these results to adversarial training because of the min-max objective. Recently, a first step towards this direction was made by Gao et al. using tools from online learning, but they require the width of the net to be \emph{exponential} in input dimension $d$, and with an unnatural activation function. Our work proves convergence to low robust training loss for \emph{polynomial} width instead of exponential, under natural assumptions and with the ReLU activation. Key element of our proof is showing that ReLU networks near initialization can approximate the step function, which may be of independent interest.
Tasks
Published	2020-02-16
URL	https://arxiv.org/abs/2002.06668v2
PDF	https://arxiv.org/pdf/2002.06668v2.pdf
PWC	https://paperswithcode.com/paper/over-parameterized-adversarial-training-an
Repo
Framework

TempLe: Learning Template of Transitions for Sample Efficient Multi-task RL


Title	TempLe: Learning Template of Transitions for Sample Efficient Multi-task RL
Authors	Yanchao Sun, Xiangyu Yin, Furong Huang
Abstract	Transferring knowledge among various environments is important to efficiently learn multiple tasks online. Most existing methods directly use the previously learned models or previously learned optimal policies to learn new tasks. However, these methods may be inefficient when the underlying models or optimal policies are substantially different across tasks. In this paper, we propose Template Learning (TempLe), the first PAC-MDP method for multi-task reinforcement learning that could be applied to tasks with varying state/action space. TempLe generates transition dynamics templates, abstractions of the transition dynamics across tasks, to gain sample efficiency by extracting similarities between tasks even when their underlying models or optimal policies have limited commonalities. We present two algorithms for an “online” and a “finite-model” setting respectively. We prove that our proposed TempLe algorithms achieve much lower sample complexity than single-task learners or state-of-the-art multi-task methods. We show via systematically designed experiments that our TempLe method universally outperforms the state-of-the-art multi-task methods (PAC-MDP or not) in various settings and regimes.
Tasks
Published	2020-02-16
URL	https://arxiv.org/abs/2002.06659v1
PDF	https://arxiv.org/pdf/2002.06659v1.pdf
PWC	https://paperswithcode.com/paper/temple-learning-template-of-transitions-for
Repo
Framework

Exploring Adversarial Attack in Spiking Neural Networks with Spike-Compatible Gradient


Title	Exploring Adversarial Attack in Spiking Neural Networks with Spike-Compatible Gradient
Authors	Ling Liang, Xing Hu, Lei Deng, Yujie Wu, Guoqi Li, Yufei Ding, Peng Li, Yuan Xie
Abstract	Recently, backpropagation through time inspired learning algorithms are widely introduced into SNNs to improve the performance, which brings the possibility to attack the models accurately given Spatio-temporal gradient maps. We propose two approaches to address the challenges of gradient input incompatibility and gradient vanishing. Specifically, we design a gradient to spike converter to convert continuous gradients to ternary ones compatible with spike inputs. Then, we design a gradient trigger to construct ternary gradients that can randomly flip the spike inputs with a controllable turnover rate, when meeting all zero gradients. Putting these methods together, we build an adversarial attack methodology for SNNs trained by supervised algorithms. Moreover, we analyze the influence of the training loss function and the firing threshold of the penultimate layer, which indicates a “trap” region under the cross-entropy loss that can be escaped by threshold tuning. Extensive experiments are conducted to validate the effectiveness of our solution. Besides the quantitative analysis of the influence factors, we evidence that SNNs are more robust against adversarial attack than ANNs. This work can help reveal what happens in SNN attack and might stimulate more research on the security of SNN models and neuromorphic devices.
Tasks	Adversarial Attack
Published	2020-01-01
URL	https://arxiv.org/abs/2001.01587v1
PDF	https://arxiv.org/pdf/2001.01587v1.pdf
PWC	https://paperswithcode.com/paper/exploring-adversarial-attack-in-spiking
Repo
Framework

Data-driven models and computational tools for neurolinguistics: a language technology perspective


Title	Data-driven models and computational tools for neurolinguistics: a language technology perspective
Authors	Ekaterina Artemova, Amir Bakarov, Aleksey Artemov, Evgeny Burnaev, Maxim Sharaev
Abstract	In this paper, our focus is the connection and influence of language technologies on the research in neurolinguistics. We present a review of brain imaging-based neurolinguistic studies with a focus on the natural language representations, such as word embeddings and pre-trained language models. Mutual enrichment of neurolinguistics and language technologies leads to development of brain-aware natural language representations. The importance of this research area is emphasized by medical applications.
Tasks	Word Embeddings
Published	2020-03-23
URL	https://arxiv.org/abs/2003.10540v1
PDF	https://arxiv.org/pdf/2003.10540v1.pdf
PWC	https://paperswithcode.com/paper/data-driven-models-and-computational-tools
Repo
Framework

Leveraging Foreign Language Labeled Data for Aspect-Based Opinion Mining


Title	Leveraging Foreign Language Labeled Data for Aspect-Based Opinion Mining
Authors	Nguyen Thi Thanh Thuy, Ngo Xuan Bach, Tu Minh Phuong
Abstract	Aspect-based opinion mining is the task of identifying sentiment at the aspect level in opinionated text, which consists of two subtasks: aspect category extraction and sentiment polarity classification. While aspect category extraction aims to detect and categorize opinion targets such as product features, sentiment polarity classification assigns a sentiment label, i.e. positive, negative, or neutral, to each identified aspect. Supervised learning methods have been shown to deliver better accuracy for this task but they require labeled data, which is costly to obtain, especially for resource-poor languages like Vietnamese. To address this problem, we present a supervised aspect-based opinion mining method that utilizes labeled data from a foreign language (English in this case), which is translated to Vietnamese by an automated translation tool (Google Translate). Because aspects and opinions in different languages may be expressed by different words, we propose using word embeddings, in addition to other features, to reduce the vocabulary difference between the original and translated texts, thus improving the effectiveness of aspect category extraction and sentiment polarity classification processes. We also introduce an annotated corpus of aspect categories and sentiment polarities extracted from restaurant reviews in Vietnamese, and conduct a series of experiments on the corpus. Experimental results demonstrate the effectiveness of the proposed approach.
Tasks	Opinion Mining, Word Embeddings
Published	2020-03-15
URL	https://arxiv.org/abs/2003.06858v1
PDF	https://arxiv.org/pdf/2003.06858v1.pdf
PWC	https://paperswithcode.com/paper/leveraging-foreign-language-labeled-data-for
Repo
Framework

Bertrand-DR: Improving Text-to-SQL using a Discriminative Re-ranker


Title	Bertrand-DR: Improving Text-to-SQL using a Discriminative Re-ranker
Authors	Amol Kelkar, Rohan Relan, Vaishali Bhardwaj, Saurabh Vaichal, Peter Relan
Abstract	To access data stored in relational databases, users need to understand the database schema and write a query using a query language such as SQL. To simplify this task, text-to-SQL models attempt to translate a user’s natural language question to corresponding SQL query. Recently, several generative text-to-SQL models have been developed. We propose a novel discriminative re-ranker to improve the performance of generative text-to-SQL models by extracting the best SQL query from the beam output predicted by the text-to-SQL generator, resulting in improved performance in the cases where the best query was in the candidate list, but not at the top of the list. We build the re-ranker as a schema agnostic BERT fine-tuned classifier. We analyze relative strengths of the text-to-SQL and re-ranker models across different query hardness levels, and suggest how to combine the two models for optimal performance. We demonstrate the effectiveness of the re-ranker by applying it to two state-of-the-art text-to-SQL models, and achieve top 4 score on the Spider leaderboard at the time of writing this article.
Tasks	Text-To-Sql
Published	2020-02-03
URL	https://arxiv.org/abs/2002.00557v1
PDF	https://arxiv.org/pdf/2002.00557v1.pdf
PWC	https://paperswithcode.com/paper/bertrand-dr-improving-text-to-sql-using-a
Repo
Framework

When deep denoising meets iterative phase retrieval


Title	When deep denoising meets iterative phase retrieval
Authors	Yaotian Wang, Xiaohang Sun, Jason W. Fleischer
Abstract	Recovering a signal from its Fourier intensity underlies many important applications, including lensless imaging and imaging through scattering media. Conventional algorithms for retrieving the phase suffer when noise is present but display global convergence when given clean data. Neural networks have been used to improve algorithm robustness, but efforts to date are sensitive to initial conditions and give inconsistent performance. Here, we combine iterative methods from phase retrieval with image statistics from deep denoisers, via regularization-by-denoising. The resulting methods inherit the advantages of each approach and outperform other noise-robust phase retrieval algorithms. Our work paves the way for hybrid imaging methods that integrate machine-learned constraints in conventional algorithms.
Tasks	Denoising
Published	2020-03-03
URL	https://arxiv.org/abs/2003.01792v1
PDF	https://arxiv.org/pdf/2003.01792v1.pdf
PWC	https://paperswithcode.com/paper/when-deep-denoising-meets-iterative-phase
Repo
Framework

Incorporating Expert Prior Knowledge into Experimental Design via Posterior Sampling


Title	Incorporating Expert Prior Knowledge into Experimental Design via Posterior Sampling
Authors	Cheng Li, Sunil Gupta, Santu Rana, Vu Nguyen, Antonio Robles-Kelly, Svetha Venkatesh
Abstract	Scientific experiments are usually expensive due to complex experimental preparation and processing. Experimental design is therefore involved with the task of finding the optimal experimental input that results in the desirable output by using as few experiments as possible. Experimenters can often acquire the knowledge about the location of the global optimum. However, they do not know how to exploit this knowledge to accelerate experimental design. In this paper, we adopt the technique of Bayesian optimization for experimental design since Bayesian optimization has established itself as an efficient tool for optimizing expensive black-box functions. Again, it is unknown how to incorporate the expert prior knowledge about the global optimum into Bayesian optimization process. To address it, we represent the expert knowledge about the global optimum via placing a prior distribution on it and we then derive its posterior distribution. An efficient Bayesian optimization approach has been proposed via posterior sampling on the posterior distribution of the global optimum. We theoretically analyze the convergence of the proposed algorithm and discuss the robustness of incorporating expert prior. We evaluate the efficiency of our algorithm by optimizing synthetic functions and tuning hyperparameters of classifiers along with a real-world experiment on the synthesis of short polymer fiber. The results clearly demonstrate the advantages of our proposed method.
Tasks
Published	2020-02-26
URL	https://arxiv.org/abs/2002.11256v1
PDF	https://arxiv.org/pdf/2002.11256v1.pdf
PWC	https://paperswithcode.com/paper/incorporating-expert-prior-knowledge-into
Repo
Framework

u-net CNN based fourier ptychography


Title	u-net CNN based fourier ptychography
Authors	Yican Chen, Zhi Luo, Xia Wu, Huidong Yang, Bo Huang
Abstract	Fourier ptychography is a recently explored imaging method for overcoming the diffraction limit of conventional cameras with applications in microscopy and yielding high-resolution images. In order to splice together low-resolution images taken under different illumination angles of coherent light source, an iterative phase retrieval algorithm is adopted. However, the reconstruction procedure is slow and needs a good many of overlap in the Fourier domain for the continuous recorded low-resolution images and is also worse under system aberrations such as noise or random update sequence. In this paper, we propose a new retrieval algorithm that is based on convolutional neural networks. Once well trained, our model can perform high-quality reconstruction rapidly by using the graphics processing unit. The experiments demonstrate that our model achieves better reconstruction results and is more robust under system aberrations.
Tasks
Published	2020-03-16
URL	https://arxiv.org/abs/2003.07460v1
PDF	https://arxiv.org/pdf/2003.07460v1.pdf
PWC	https://paperswithcode.com/paper/u-net-cnn-based-fourier-ptychography
Repo
Framework

Towards Byzantine-resilient Learning in Decentralized Systems


Title	Towards Byzantine-resilient Learning in Decentralized Systems
Authors	Shangwei Guo, Tianwei Zhang, Xiaofei Xie, Lei Ma, Tao Xiang, Yang Liu
Abstract	With the proliferation of IoT and edge computing, decentralized learning is becoming more promising. When designing a distributed learning system, one major challenge to consider is Byzantine Fault Tolerance (BFT). Past works have researched Byzantine-resilient solutions for centralized distributed learning. However, there are currently no satisfactory solutions with strong efficiency and security in decentralized systems. In this paper, we propose a novel algorithm, Mozi, to achieve BFT in decentralized learning systems. Specifically, Mozi provides a uniform Byzantine-resilient aggregation rule for benign nodes to select the useful parameter updates and filter out the malicious ones in each training iteration. It guarantees that each benign node in a decentralized system can train a correct model under very strong Byzantine attacks with an arbitrary number of faulty nodes. We perform the theoretical analysis to prove the uniform convergence of our proposed algorithm. Experimental evaluations demonstrate the high security and efficiency of Mozi compared to all existing solutions.
Tasks
Published	2020-02-20
URL	https://arxiv.org/abs/2002.08569v1
PDF	https://arxiv.org/pdf/2002.08569v1.pdf
PWC	https://paperswithcode.com/paper/towards-byzantine-resilient-learning-in
Repo
Framework