Paper Group ANR 980
Breast Tumor Cellularity Assessment using Deep Neural Networks. A Two-Stage Approach to Multivariate Linear Regression with Sparsely Mismatched Data. Machine learning Calabi-Yau metrics. Inverse Graphics: Unsupervised Learning of 3D Shapes from Single Images. Learning Open Information Extraction of Implicit Relations from Reading Comprehension Data …
Breast Tumor Cellularity Assessment using Deep Neural Networks
| Title | Breast Tumor Cellularity Assessment using Deep Neural Networks |
| Authors | Alexander Rakhlin, Aleksei Tiulpin, Alexey A. Shvets, Alexandr A. Kalinin, Vladimir I. Iglovikov, Sergey Nikolenko |
| Abstract | Breast cancer is one of the main causes of death worldwide. Histopathological cellularity assessment of residual tumors in post-surgical tissues is used to analyze a tumor’s response to a therapy. Correct cellularity assessment increases the chances of getting an appropriate treatment and facilitates the patient’s survival. In current clinical practice, tumor cellularity is manually estimated by pathologists; this process is tedious and prone to errors or low agreement rates between assessors. In this work, we evaluated three strong novel Deep Learning-based approaches for automatic assessment of tumor cellularity from post-treated breast surgical specimens stained with hematoxylin and eosin. We validated the proposed methods on the BreastPathQ SPIE challenge dataset that consisted of 2395 image patches selected from whole slide images acquired from 64 patients. Compared to expert pathologist scoring, our best performing method yielded the Cohen’s kappa coefficient of 0.70 (vs. 0.42 previously known in literature) and the intra-class correlation coefficient of 0.89 (vs. 0.83). Our results suggest that Deep Learning-based methods have a significant potential to alleviate the burden on pathologists, enhance the diagnostic workflow, and, thereby, facilitate better clinical outcomes in breast cancer treatment. |
| Tasks | |
| Published | 2019-05-05 |
| URL | https://arxiv.org/abs/1905.01743v3 |
| https://arxiv.org/pdf/1905.01743v3.pdf | |
| PWC | https://paperswithcode.com/paper/breast-tumor-cellularity-assessment-using |
| Repo | |
| Framework | |
A Two-Stage Approach to Multivariate Linear Regression with Sparsely Mismatched Data
| Title | A Two-Stage Approach to Multivariate Linear Regression with Sparsely Mismatched Data |
| Authors | Martin Slawski, Emanuel Ben-David, Ping Li |
| Abstract | A tacit assumption in linear regression is that (response, predictor)-pairs correspond to identical observational units. A series of recent works have studied scenarios in which this assumption is violated under terms such as Unlabeled Sensing and Regression with Unknown Permutation’'. In this paper, we study the setup of multiple response variables and a notion of mismatches that generalizes permutations in order to allow for missing matches as well as for one-to-many matches. A two-stage method is proposed under the assumption that most pairs are correctly matched. In the first stage, the regression parameter is estimated by handling mismatches as contaminations, and subsequently the generalized permutation is estimated by a basic variant of matching. The approach is both computationally convenient and equipped with favorable statistical guarantees. Specifically, it is shown that the conditions for permutation recovery become considerably less stringent as the number of responses $m$ per observation increase. Particularly, for $m = \Omega(\log n)$, the required signal-to-noise ratio does no longer depend on the sample size $n$. Numerical results on synthetic and real data are presented to support the main findings of our analysis. |
| Tasks | |
| Published | 2019-07-16 |
| URL | https://arxiv.org/abs/1907.07148v1 |
| https://arxiv.org/pdf/1907.07148v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-two-stage-approach-to-multivariate-linear |
| Repo | |
| Framework | |
Machine learning Calabi-Yau metrics
| Title | Machine learning Calabi-Yau metrics |
| Authors | Anthony Ashmore, Yang-Hui He, Burt Ovrut |
| Abstract | We apply machine learning to the problem of finding numerical Calabi-Yau metrics. Building on Donaldson’s algorithm for calculating balanced metrics on K"ahler manifolds, we combine conventional curve fitting and machine-learning techniques to numerically approximate Ricci-flat metrics. We show that machine learning is able to predict the Calabi-Yau metric and quantities associated with it, such as its determinant, having seen only a small sample of training data. Using this in conjunction with a straightforward curve fitting routine, we demonstrate that it is possible to find highly accurate numerical metrics much more quickly than by using Donaldson’s algorithm alone, with our new machine-learning algorithm decreasing the time required by between one and two orders of magnitude. |
| Tasks | |
| Published | 2019-10-18 |
| URL | https://arxiv.org/abs/1910.08605v2 |
| https://arxiv.org/pdf/1910.08605v2.pdf | |
| PWC | https://paperswithcode.com/paper/machine-learning-calabi-yau-metrics |
| Repo | |
| Framework | |
Inverse Graphics: Unsupervised Learning of 3D Shapes from Single Images
| Title | Inverse Graphics: Unsupervised Learning of 3D Shapes from Single Images |
| Authors | Talip Ucar |
| Abstract | Using generative models for Inverse Graphics is an active area of research. However, most works focus on developing models for supervised and semi-supervised methods. In this paper, we study the problem of unsupervised learning of 3D geometry from single images. Our approach is to use a generative model that produces 2-D images as projections of a latent 3D voxel grid, which we train either as a variational auto-encoder or using adversarial methods. Our contributions are as follows: First, we show how to recover 3D shape and pose from general datasets such as MNIST, and MNIST Fashion in good quality. Second, we compare the shapes learned using adversarial and variational methods. Adversarial approach gives denser 3D shapes. Third, we explore the idea of modelling the pose of an object as uniform distribution to recover 3D shape from a single image. Our experiment with the CelebA dataset \cite{liu2015faceattributes} proves that we can recover complete 3D shape from a single image when the object is symmetric along one, or more axis whilst results obtained using ModelNet40 \cite{wu20153d} show the potential side-effects, in which the model learns 3D shapes such that it can render the same image from any viewpoint. Forth, we present a general end-to-end approach to learning 3D shapes from single images in a completely unsupervised fashion by modelling the factors of variation such as azimuth as independent latent variables. Our method makes no assumptions about the dataset, and can work with synthetic as well as real images (i.e. unsupervised in true sense). We present our results, by training the model using the $\mu$-VAE objective \cite{ucar2019bridging} and a dataset combining all images from MNIST, MNIST Fashion, CelebA and six categories of ModelNet40. The model is able to learn 3D shapes and the pose in qood quality and leverages information learned across all datasets. |
| Tasks | |
| Published | 2019-10-31 |
| URL | https://arxiv.org/abs/1911.07937v2 |
| https://arxiv.org/pdf/1911.07937v2.pdf | |
| PWC | https://paperswithcode.com/paper/inverse-graphics-unsupervised-learning-of-3d |
| Repo | |
| Framework | |
Learning Open Information Extraction of Implicit Relations from Reading Comprehension Datasets
| Title | Learning Open Information Extraction of Implicit Relations from Reading Comprehension Datasets |
| Authors | Jacob Beckerman, Theodore Christakis |
| Abstract | The relationship between two entities in a sentence is often implied by word order and common sense, rather than an explicit predicate. For example, it is evident that “Fed chair Powell indicates rate hike” implies (Powell, is a, Fed chair) and (Powell, works for, Fed). These tuples are just as significant as the explicit-predicate tuple (Powell, indicates, rate hike), but have much lower recall under traditional Open Information Extraction (OpenIE) systems. Implicit tuples are our term for this type of extraction where the relation is not present in the input sentence. There is very little OpenIE training data available relative to other NLP tasks and none focused on implicit relations. We develop an open source, parse-based tool for converting large reading comprehension datasets to OpenIE datasets and release a dataset 35x larger than previously available by sentence count. A baseline neural model trained on this data outperforms previous methods on the implicit extraction task. |
| Tasks | Common Sense Reasoning, Open Information Extraction, Reading Comprehension |
| Published | 2019-05-15 |
| URL | https://arxiv.org/abs/1905.07471v1 |
| https://arxiv.org/pdf/1905.07471v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-open-information-extraction-of |
| Repo | |
| Framework | |
BSL: An R Package for Efficient Parameter Estimation for Simulation-Based Models via Bayesian Synthetic Likelihood
| Title | BSL: An R Package for Efficient Parameter Estimation for Simulation-Based Models via Bayesian Synthetic Likelihood |
| Authors | Ziwen An, Leah F South, Christopher Drovandi |
| Abstract | Bayesian synthetic likelihood (BSL) is a popular method for estimating the parameter posterior distribution for complex statistical models and stochastic processes that possess a computationally intractable likelihood function. Instead of evaluating the likelihood, BSL approximates the likelihood of a judiciously chosen summary statistic of the data via model simulation and density estimation. Compared to alternative methods such as approximate Bayesian computation (ABC), BSL requires little tuning and requires less model simulations than ABC when the chosen summary statistic is high-dimensional. The original synthetic likelihood relies on a multivariate normal approximation of the intractable likelihood, where the mean and covariance are estimated by simulation. An extension of BSL considers replacing the sample covariance with a penalised covariance estimator to reduce the number of required model simulations. Further, a semi-parametric approach has been developed to relax the normality assumption. In this paper, we present an R package called BSL that amalgamates the aforementioned methods and more into a single, easy-to-use and coherent piece of software. The R package also includes several examples to illustrate how to use the package and demonstrate the utility of the methods. |
| Tasks | Density Estimation |
| Published | 2019-07-25 |
| URL | https://arxiv.org/abs/1907.10940v1 |
| https://arxiv.org/pdf/1907.10940v1.pdf | |
| PWC | https://paperswithcode.com/paper/bsl-an-r-package-for-efficient-parameter |
| Repo | |
| Framework | |
Content-aware Density Map for Crowd Counting and Density Estimation
| Title | Content-aware Density Map for Crowd Counting and Density Estimation |
| Authors | Mahdi Maktabdar Oghaz, Anish R Khadka, Vasileios Argyriou, Paolo Remagnino |
| Abstract | Precise knowledge about the size of a crowd, its density and flow can provide valuable information for safety and security applications, event planning, architectural design and to analyze consumer behavior. Creating a powerful machine learning model, to employ for such applications requires a large and highly accurate and reliable dataset. Unfortunately the existing crowd counting and density estimation benchmark datasets are not only limited in terms of their size, but also lack annotation, in general too time consuming to implement. This paper attempts to address this very issue through a content aware technique, uses combinations of Chan-Vese segmentation algorithm, two-dimensional Gaussian filter and brute-force nearest neighbor search. The results shows that by simply replacing the commonly used density map generators with the proposed method, higher level of accuracy can be achieved using the existing state of the art models. |
| Tasks | Crowd Counting, Density Estimation |
| Published | 2019-06-17 |
| URL | https://arxiv.org/abs/1906.07258v1 |
| https://arxiv.org/pdf/1906.07258v1.pdf | |
| PWC | https://paperswithcode.com/paper/content-aware-density-map-for-crowd-counting |
| Repo | |
| Framework | |
Detecting Ghostwriters in High Schools
| Title | Detecting Ghostwriters in High Schools |
| Authors | Magnus Stavngaard, August Sørensen, Stephan Lorenzen, Niklas Hjuler, Stephen Alstrup |
| Abstract | Students hiring ghostwriters to write their assignments is an increasing problem in educational institutions all over the world, with companies selling these services as a product. In this work, we develop automatic techniques with special focus on detecting such ghostwriting in high school assignments. This is done by training deep neural networks on an unprecedented large amount of data supplied by the Danish company MaCom, which covers 90% of Danish high schools. We achieve an accuracy of 0.875 and a AUC score of 0.947 on an evenly split data set. |
| Tasks | |
| Published | 2019-06-04 |
| URL | https://arxiv.org/abs/1906.01635v1 |
| https://arxiv.org/pdf/1906.01635v1.pdf | |
| PWC | https://paperswithcode.com/paper/detecting-ghostwriters-in-high-schools |
| Repo | |
| Framework | |
Discrepancy, Coresets, and Sketches in Machine Learning
| Title | Discrepancy, Coresets, and Sketches in Machine Learning |
| Authors | Zohar Karnin, Edo Liberty |
| Abstract | This paper defines the notion of class discrepancy for families of functions. It shows that low discrepancy classes admit small offline and streaming coresets. We provide general techniques for bounding the class discrepancy of machine learning problems. As corollaries of the general technique we bound the discrepancy (and therefore coreset complexity) of logistic regression, sigmoid activation loss, matrix covariance, kernel density and any analytic function of the dot product or the squared distance. Our results prove the existence of epsilon-approximation O(sqrt{d}/epsilon) sized coresets for the above problems. This resolves the long-standing open problem regarding the coreset complexity of Gaussian kernel density estimation. We provide two more related but independent results. First, an exponential improvement of the widely used merge-and-reduce trick which gives improved streaming sketches for any low discrepancy problem. Second, an extremely simple deterministic algorithm for finding low discrepancy sequences (and therefore coresets) for any positive semi-definite kernel. This paper establishes some explicit connections between class discrepancy, coreset complexity, learnability, and streaming algorithms. |
| Tasks | Density Estimation |
| Published | 2019-06-11 |
| URL | https://arxiv.org/abs/1906.04845v1 |
| https://arxiv.org/pdf/1906.04845v1.pdf | |
| PWC | https://paperswithcode.com/paper/discrepancy-coresets-and-sketches-in-machine |
| Repo | |
| Framework | |
A Simple Saliency Method That Passes the Sanity Checks
| Title | A Simple Saliency Method That Passes the Sanity Checks |
| Authors | Arushi Gupta, Sanjeev Arora |
| Abstract | There is great interest in “saliency methods” (also called “attribution methods”), which give “explanations” for a deep net’s decision, by assigning a “score” to each feature/pixel in the input. Their design usually involves credit-assignment via the gradient of the output with respect to input. Recently Adebayo et al. [arXiv:1810.03292] questioned the validity of many of these methods since they do not pass simple sanity checks which test whether the scores shift/vanish when layers of the trained net are randomized, or when the net is retrained using random labels for inputs. We propose a simple fix to existing saliency methods that helps them pass sanity checks, which we call “competition for pixels”. This involves computing saliency maps for all possible labels in the classification task, and using a simple competition among them to identify and remove less relevant pixels from the map. The simplest variant of this is “Competitive Gradient $\odot$ Input (CGI)": it is efficient, requires no additional training, and uses only the input and gradient. Some theoretical justification is provided for it (especially for ReLU networks) and its performance is empirically demonstrated. |
| Tasks | |
| Published | 2019-05-27 |
| URL | https://arxiv.org/abs/1905.12152v2 |
| https://arxiv.org/pdf/1905.12152v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-simple-saliency-method-that-passes-the |
| Repo | |
| Framework | |
RuDaCoP: The Dataset for Smartphone-based Intellectual Pedestrian Navigation
| Title | RuDaCoP: The Dataset for Smartphone-based Intellectual Pedestrian Navigation |
| Authors | Andrey Bayev, Ilya Gartseev, Ivan Chistyakov, Alexey Nikulin, Alexey Derevyankin, Mikhail Pikhletsky |
| Abstract | This paper presents the large and diverse dataset for development of smartphone-based pedestrian navigation algorithms. This dataset consists of about 1200 sets of inertial measurements from sensors of several smartphones. The measurements are collected while walking through different trajectories up to 10 minutes long. The data are accompanied by the high accuracy ground truth collected with two foot-mounted inertial measurement units and post-processed by the presented algorithms. The dataset suits both for training of intellectual pedestrian navigation algorithms based on learning techniques and for development of pedestrian navigation algorithms based on classical approaches. The dataset is accessible at http://gartseev.ru/projects/ipin2019. |
| Tasks | |
| Published | 2019-08-09 |
| URL | https://arxiv.org/abs/1908.03609v1 |
| https://arxiv.org/pdf/1908.03609v1.pdf | |
| PWC | https://paperswithcode.com/paper/rudacop-the-dataset-for-smartphone-based |
| Repo | |
| Framework | |
Strategizing against No-regret Learners
| Title | Strategizing against No-regret Learners |
| Authors | Yuan Deng, Jon Schneider, Balusubramanian Sivan |
| Abstract | How should a player who repeatedly plays a game against a no-regret learner strategize to maximize his utility? We study this question and show that under some mild assumptions, the player can always guarantee himself a utility of at least what he would get in a Stackelberg equilibrium of the game. When the no-regret learner has only two actions, we show that the player cannot get any higher utility than the Stackelberg equilibrium utility. But when the no-regret learner has more than two actions and plays a mean-based no-regret strategy, we show that the player can get strictly higher than the Stackelberg equilibrium utility. We provide a characterization of the optimal game-play for the player against a mean-based no-regret learner as a solution to a control problem. When the no-regret learner’s strategy also guarantees him a no-swap regret, we show that the player cannot get anything higher than a Stackelberg equilibrium utility. |
| Tasks | |
| Published | 2019-09-30 |
| URL | https://arxiv.org/abs/1909.13861v1 |
| https://arxiv.org/pdf/1909.13861v1.pdf | |
| PWC | https://paperswithcode.com/paper/strategizing-against-no-regret-learners |
| Repo | |
| Framework | |
Scalable Data Augmentation for Deep Learning
| Title | Scalable Data Augmentation for Deep Learning |
| Authors | Yuexi Wang, Nicholas G. Polson, Vadim O. Sokolov |
| Abstract | Scalable Data Augmentation (SDA) provides a framework for training deep learning models using auxiliary hidden layers. Scalable MCMC is available for network training and inference. SDA provides a number of computational advantages over traditional algorithms, such as avoiding backtracking, local modes and can perform optimization with stochastic gradient descent (SGD) in TensorFlow. Standard deep neural networks with logit, ReLU and SVM activation functions are straightforward to implement. To illustrate our architectures and methodology, we use P'{o}lya-Gamma logit data augmentation for a number of standard datasets. Finally, we conclude with directions for future research. |
| Tasks | Data Augmentation |
| Published | 2019-03-22 |
| URL | http://arxiv.org/abs/1903.09668v1 |
| http://arxiv.org/pdf/1903.09668v1.pdf | |
| PWC | https://paperswithcode.com/paper/scalable-data-augmentation-for-deep-learning |
| Repo | |
| Framework | |
Training Detection-Range-Frugal Cooperative Collision Avoidance Models for Quadcopters via Neuroevolution
| Title | Training Detection-Range-Frugal Cooperative Collision Avoidance Models for Quadcopters via Neuroevolution |
| Authors | Amir Behjat, Krushang Gabani, Souma Chowdhury |
| Abstract | Cooperative autonomous approaches to avoiding collisions among small Unmanned Aerial Vehicles (UAVs) is central to safe integration of UAVs within the civilian airspace. One potential online cooperative approach is the concept of reciprocal actions, where both UAVs take pre-trained mutually coherent actions that do not require active online coordination (thereby avoiding the computational burden and risk associated with it). This paper presents a learning based approach to train such reciprocal maneuvers. Neuroevolution, which uses evolutionary algorithms to simultaneously optimize the topology and weights of neural networks, is used as the learning method – which operates over a set of sample approach scenarios. Unlike most existing work (that minimize travel distance, energy or risk), the training process here focuses on the objective of minimizing the required detection range; this has important practical implications w.r.t. alleviating the dependency on sophisticated sensing and their reliability under various environments. A specialized design of experiments and line search is used to identify the minimum detection range for each sample scenarios. In order to allow an efficient training process, a classifier is used to discard actions (without simulating them) where the controller would fail. The model obtained via neuroevolution is observed to generalize well to (i.e., successful collision avoidance over) unseen approach scenarios. |
| Tasks | |
| Published | 2019-05-31 |
| URL | https://arxiv.org/abs/1906.00052v1 |
| https://arxiv.org/pdf/1906.00052v1.pdf | |
| PWC | https://paperswithcode.com/paper/190600052 |
| Repo | |
| Framework | |
DL-PDE: Deep-learning based data-driven discovery of partial differential equations from discrete and noisy data
| Title | DL-PDE: Deep-learning based data-driven discovery of partial differential equations from discrete and noisy data |
| Authors | Hao Xu, Haibin Chang, Dongxiao Zhang |
| Abstract | In recent years, data-driven methods have been utilized to learn dynamical systems and partial differential equations (PDE). However, major challenges remain to be resolved, including learning PDE under noisy data and limited discrete data. To overcome these challenges, in this work, a deep-learning based data-driven method, called DL-PDE, is developed to discover the governing PDEs of underlying physical processes. The DL-PDE method combines deep learning via neural networks and data-driven discovery of PDEs via sparse regressions, such as the least absolute shrinkage and selection operator (Lasso) and sequential threshold ridge regression (STRidge). In this method, derivatives are calculated by automatic differentiation from the deep neural network, and equation form and coefficients are obtained with sparse regressions. The DL-PDE is tested with physical processes, governed by groundwater flow equation, contaminant transport equation, Burgers equation and Korteweg-de Vries (KdV) equation, for proof-of-concept and applications in real-world engineering settings. The proposed DL-PDE achieves satisfactory results when data are discrete and noisy. |
| Tasks | |
| Published | 2019-08-13 |
| URL | https://arxiv.org/abs/1908.04463v1 |
| https://arxiv.org/pdf/1908.04463v1.pdf | |
| PWC | https://paperswithcode.com/paper/dl-pde-deep-learning-based-data-driven |
| Repo | |
| Framework | |
