Paper Group ANR 1641
MIDV-2019: Challenges of the modern mobile-based document OCR. Concept and Experimental Demonstration of Optical IM/DD End-to-End System Optimization using a Generative Model. Fair Algorithms for Clustering. Evaluating Conformance Measures in Process Mining using Conformance Propositions (Extended version). Multi-Modal Deep Clustering: Unsupervised …
MIDV-2019: Challenges of the modern mobile-based document OCR
| Title | MIDV-2019: Challenges of the modern mobile-based document OCR |
| Authors | Konstantin Bulatov, Daniil Matalov, Vladimir V. Arlazarov |
| Abstract | Recognition of identity documents using mobile devices has become a topic of a wide range of computer vision research. The portfolio of methods and algorithms for solving such tasks as face detection, document detection and rectification, text field recognition, and other, is growing, and the scarcity of datasets has become an important issue. One of the openly accessible datasets for evaluating such methods is MIDV-500, containing video clips of 50 identity document types in various conditions. However, the variability of capturing conditions in MIDV-500 did not address some of the key issues, mainly significant projective distortions and different lighting conditions. In this paper we present a MIDV-2019 dataset, containing video clips shot with modern high-resolution mobile cameras, with strong projective distortions and with low lighting conditions. The description of the added data is presented, and experimental baselines for text field recognition in different conditions. The dataset is available for download at ftp://smartengines.com/midv-500/extra/midv-2019/. |
| Tasks | Face Detection, Optical Character Recognition |
| Published | 2019-10-09 |
| URL | https://arxiv.org/abs/1910.04009v1 |
| https://arxiv.org/pdf/1910.04009v1.pdf | |
| PWC | https://paperswithcode.com/paper/midv-2019-challenges-of-the-modern-mobile |
| Repo | |
| Framework | |
Concept and Experimental Demonstration of Optical IM/DD End-to-End System Optimization using a Generative Model
| Title | Concept and Experimental Demonstration of Optical IM/DD End-to-End System Optimization using a Generative Model |
| Authors | Boris Karanov, Mathieu Chagnon, Vahid Aref, Domaniç Lavery, Polina Bayvel, Laurent Schmalen |
| Abstract | We perform an experimental end-to-end transceiver optimization via deep learning using a generative adversarial network to approximate the test-bed channel. Previously, optimization was only possible through a prior assumption of an explicit simplified channel model. |
| Tasks | |
| Published | 2019-12-11 |
| URL | https://arxiv.org/abs/1912.05146v2 |
| https://arxiv.org/pdf/1912.05146v2.pdf | |
| PWC | https://paperswithcode.com/paper/concept-and-experimental-demonstration-of |
| Repo | |
| Framework | |
Fair Algorithms for Clustering
| Title | Fair Algorithms for Clustering |
| Authors | Suman K. Bera, Deeparnab Chakrabarty, Nicolas J. Flores, Maryam Negahbani |
| Abstract | We study the problem of finding low-cost Fair Clusterings in data where each data point may belong to many protected groups. Our work significantly generalizes the seminal work of Chierichetti et.al. (NIPS 2017) as follows. - We allow the user to specify the parameters that define fair representation. More precisely, these parameters define the maximum over- and minimum under-representation of any group in any cluster. - Our clustering algorithm works on any $\ell_p$-norm objective (e.g. $k$-means, $k$-median, and $k$-center). Indeed, our algorithm transforms any vanilla clustering solution into a fair one incurring only a slight loss in quality. - Our algorithm also allows individuals to lie in multiple protected groups. In other words, we do not need the protected groups to partition the data and we can maintain fairness across different groups simultaneously. Our experiments show that on established data sets, our algorithm performs much better in practice than what our theoretical results suggest. |
| Tasks | |
| Published | 2019-01-08 |
| URL | https://arxiv.org/abs/1901.02393v2 |
| https://arxiv.org/pdf/1901.02393v2.pdf | |
| PWC | https://paperswithcode.com/paper/fair-algorithms-for-clustering |
| Repo | |
| Framework | |
Evaluating Conformance Measures in Process Mining using Conformance Propositions (Extended version)
| Title | Evaluating Conformance Measures in Process Mining using Conformance Propositions (Extended version) |
| Authors | Anja F. Syring, Niek Tax, Wil M. P. van der Aalst |
| Abstract | Process mining sheds new light on the relationship between process models and real-life processes. Process discovery can be used to learn process models from event logs. Conformance checking is concerned with quantifying the quality of a business process model in relation to event data that was logged during the execution of the business process. There exist different categories of conformance measures. Recall, also called fitness, is concerned with quantifying how much of the behavior that was observed in the event log fits the process model. Precision is concerned with quantifying how much behavior a process model allows for that was never observed in the event log. Generalization is concerned with quantifying how well a process model generalizes to behavior that is possible in the business process but was never observed in the event log. Many recall, precision, and generalization measures have been developed throughout the years, but they are often defined in an ad-hoc manner without formally defining the desired properties up front. To address these problems, we formulate 21 conformance propositions and we use these propositions to evaluate current and existing conformance measures. The goal is to trigger a discussion by clearly formulating the challenges and requirements (rather than proposing new measures). Additionally, this paper serves as an overview of the conformance checking measures that are available in the process mining area. |
| Tasks | |
| Published | 2019-08-30 |
| URL | https://arxiv.org/abs/1909.02393v1 |
| https://arxiv.org/pdf/1909.02393v1.pdf | |
| PWC | https://paperswithcode.com/paper/evaluating-conformance-measures-in-process |
| Repo | |
| Framework | |
Multi-Modal Deep Clustering: Unsupervised Partitioning of Images
| Title | Multi-Modal Deep Clustering: Unsupervised Partitioning of Images |
| Authors | Guy Shiran, Daphna Weinshall |
| Abstract | The clustering of unlabeled raw images is a daunting task, which has recently been approached with some success by deep learning methods. Here we propose an unsupervised clustering framework, which learns a deep neural network in an end-to-end fashion, providing direct cluster assignments of images without additional processing. Multi-Modal Deep Clustering (MMDC), trains a deep network to align its image embeddings with target points sampled from a Gaussian Mixture Model distribution. The cluster assignments are then determined by mixture component association of image embeddings. Simultaneously, the same deep network is trained to solve an additional self-supervised task. This pushes the network to learn more meaningful image representations and stabilizes the training. Experimental results show that MMDC achieves or exceeds state-of-the-art performance on five challenging benchmarks. On natural image datasets we improve on previous results with significant margins of up to 11% absolute accuracy points, yielding an accuracy of 70% on CIFAR-10, 31% on CIFAR-100 and 61% on STL-10. |
| Tasks | |
| Published | 2019-12-05 |
| URL | https://arxiv.org/abs/1912.02678v1 |
| https://arxiv.org/pdf/1912.02678v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-modal-deep-clustering-unsupervised |
| Repo | |
| Framework | |
Forecasting significant stock price changes using neural networks
| Title | Forecasting significant stock price changes using neural networks |
| Authors | Firuz Kamalov |
| Abstract | Stock price prediction is a rich research topic that has attracted interest from various areas of science. The recent success of machine learning in speech and image recognition has prompted researchers to apply these methods to asset price prediction. The majority of literature has been devoted to predicting either the actual asset price or the direction of price movement. In this paper, we study a hitherto little explored question of predicting significant changes in stock price based on previous changes using machine learning algorithms. We are particularly interested in the performance of neural network classifiers in the given context. To this end, we construct and test three neural network models including multi-layer perceptron, convolutional net, and long short term memory net. As benchmark models we use random forest and relative strength index methods. The models are tested using 10-year daily stock price data of four major US public companies. Test results show that predicting significant changes in stock price can be accomplished with a high degree of accuracy. In particular, we obtain substantially better results than similar studies that forecast the direction of price change. |
| Tasks | Stock Price Prediction |
| Published | 2019-11-21 |
| URL | https://arxiv.org/abs/1912.08791v1 |
| https://arxiv.org/pdf/1912.08791v1.pdf | |
| PWC | https://paperswithcode.com/paper/forecasting-significant-stock-price-changes |
| Repo | |
| Framework | |
Regularized Operating Envelope with Interpretability and Implementability Constraints
| Title | Regularized Operating Envelope with Interpretability and Implementability Constraints |
| Authors | Qiyao Wang, Haiyan Wang, Chetan Gupta, Susumu Serita |
| Abstract | Operating envelope is an important concept in industrial operations. Accurate identification for operating envelope can be extremely beneficial to stakeholders as it provides a set of operational parameters that optimizes some key performance indicators (KPI) such as product quality, operational safety, equipment efficiency, environmental impact, etc. Given the importance, data-driven approaches for computing the operating envelope are gaining popularity. These approaches typically use classifiers such as support vector machines, to set the operating envelope by learning the boundary in the operational parameter spaces between the manually assigned large KPI' and small KPI’ groups. One challenge to these approaches is that the assignment to these groups is often ad-hoc and hence arbitrary. However, a bigger challenge with these approaches is that they don’t take into account two key features that are needed to operationalize operating envelopes: (i) interpretability of the envelope by the operator and (ii) implementability of the envelope from a practical standpoint. In this work, we propose a new definition for operating envelope which directly targets the expected magnitude of KPI (i.e., no need to arbitrarily bin the data instances into groups) and accounts for the interpretability and the implementability. We then propose a regularized `GA + penalty’ algorithm that outputs an envelope where the user can tradeoff between bias and variance. The validity of our proposed algorithm is demonstrated by two sets of simulation studies and an application to a real-world challenge in the mining processes of a flotation plant. | |
| Tasks | |
| Published | 2019-12-21 |
| URL | https://arxiv.org/abs/1912.10158v1 |
| https://arxiv.org/pdf/1912.10158v1.pdf | |
| PWC | https://paperswithcode.com/paper/regularized-operating-envelope-with |
| Repo | |
| Framework | |
Warm-starting Contextual Bandits: Robustly Combining Supervised and Bandit Feedback
| Title | Warm-starting Contextual Bandits: Robustly Combining Supervised and Bandit Feedback |
| Authors | Chicheng Zhang, Alekh Agarwal, Hal Daumé III, John Langford, Sahand N Negahban |
| Abstract | We investigate the feasibility of learning from a mix of both fully-labeled supervised data and contextual bandit data. We specifically consider settings in which the underlying learning signal may be different between these two data sources. Theoretically, we state and prove no-regret algorithms for learning that is robust to misaligned cost distributions between the two sources. Empirically, we evaluate some of these algorithms on a large selection of datasets, showing that our approach is both feasible and helpful in practice. |
| Tasks | Multi-Armed Bandits |
| Published | 2019-01-02 |
| URL | https://arxiv.org/abs/1901.00301v2 |
| https://arxiv.org/pdf/1901.00301v2.pdf | |
| PWC | https://paperswithcode.com/paper/warm-starting-contextual-bandits-robustly |
| Repo | |
| Framework | |
Pseudo-Encoded Stochastic Variational Inference
| Title | Pseudo-Encoded Stochastic Variational Inference |
| Authors | Amir Zadeh, Smon Hessner, Yao-Chong Lim, Louis-Phlippe Morency |
| Abstract | Posterior inference in directed graphical models is commonly done using a probabilistic encoder (a.k.a inference model) conditioned on the input. Often this inference model is trained jointly with the probabilistic decoder (a.k.a generator model). If probabilistic encoder encounters complexities during training (e.g. suboptimal complxity or parameterization), then learning reaches a suboptimal objective; a phenomena commonly called inference suboptimality. In Variational Inference (VI), optimizing the ELBo using Stochastic Variational Inference (SVI) can eliminate the inference suboptimality (as demonstrated in this paper), however, this solution comes at a substantial computational cost when inference needs to be done on new data points. Essentially, a long sequential chain of gradient updates is required to fully optimize approximate posteriors. In this paper, we present an approach called Pseudo-Encoded Stochastic Variational Inference (PE-SVI), to reduce the inference complexity of SVI during test time. Our approach relies on finding a suitable initial start point for gradient operations, which naturally reduces the required gradient steps. Furthermore, this initialization allows for adopting larger step sizes (compared to random initialization used in SVI), which further reduces the inference time complexity. PE-SVI reaches the same ELBo objective as SVI using less than one percent of required steps, on average. |
| Tasks | |
| Published | 2019-12-19 |
| URL | https://arxiv.org/abs/1912.09423v1 |
| https://arxiv.org/pdf/1912.09423v1.pdf | |
| PWC | https://paperswithcode.com/paper/pseudo-encoded-stochastic-variational |
| Repo | |
| Framework | |
Supervised Classifiers for Audio Impairments with Noisy Labels
| Title | Supervised Classifiers for Audio Impairments with Noisy Labels |
| Authors | Chandan K A Reddy, Ross Cutler, Johannes Gehrke |
| Abstract | Voice-over-Internet-Protocol (VoIP) calls are prone to various speech impairments due to environmental and network conditions resulting in bad user experience. A reliable audio impairment classifier helps to identify the cause for bad audio quality. The user feedback after the call can act as the ground truth labels for training a supervised classifier on a large audio dataset. However, the labels are noisy as most of the users lack the expertise to precisely articulate the impairment in the perceived speech. In this paper, we analyze the effects of massive noise in labels in training dense networks and Convolutional Neural Networks (CNN) using engineered features, spectrograms and raw audio samples as inputs. We demonstrate that CNN can generalize better on the training data with a large number of noisy labels and gives remarkably higher test performance. The classifiers were trained both on randomly generated label noise and the label noise introduced by human errors. We also show that training with noisy labels requires a significant increase in the training dataset size, which is in proportion to the amount of noise in the labels. |
| Tasks | |
| Published | 2019-07-03 |
| URL | https://arxiv.org/abs/1907.01742v1 |
| https://arxiv.org/pdf/1907.01742v1.pdf | |
| PWC | https://paperswithcode.com/paper/supervised-classifiers-for-audio-impairments |
| Repo | |
| Framework | |
Learning Vertex Representations for Bipartite Networks
| Title | Learning Vertex Representations for Bipartite Networks |
| Authors | Ming Gao, Xiangnan He, Leihui Chen, Tingting Liu, Jinglin Zhang, Aoying Zhou |
| Abstract | Recent years have witnessed a widespread increase of interest in network representation learning (NRL). By far most research efforts have focused on NRL for homogeneous networks like social networks where vertices are of the same type, or heterogeneous networks like knowledge graphs where vertices (and/or edges) are of different types. There has been relatively little research dedicated to NRL for bipartite networks. Arguably, generic network embedding methods like node2vec and LINE can also be applied to learn vertex embeddings for bipartite networks by ignoring the vertex type information. However, these methods are suboptimal in doing so, since real-world bipartite networks concern the relationship between two types of entities, which usually exhibit different properties and patterns from other types of network data. For example, E-Commerce recommender systems need to capture the collaborative filtering patterns between customers and products, and search engines need to consider the matching signals between queries and webpages. |
| Tasks | Knowledge Graphs, Network Embedding, Recommendation Systems, Representation Learning |
| Published | 2019-01-16 |
| URL | https://arxiv.org/abs/1901.09676v2 |
| https://arxiv.org/pdf/1901.09676v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-vertex-representations-for-bipartite |
| Repo | |
| Framework | |
Overfitting in Synthesis: Theory and Practice (Extended Version)
| Title | Overfitting in Synthesis: Theory and Practice (Extended Version) |
| Authors | Saswat Padhi, Todd Millstein, Aditya Nori, Rahul Sharma |
| Abstract | In syntax-guided synthesis (SyGuS), a synthesizer’s goal is to automatically generate a program belonging to a grammar of possible implementations that meets a logical specification. We investigate a common limitation across state-of-the-art SyGuS tools that perform counterexample-guided inductive synthesis (CEGIS). We empirically observe that as the expressiveness of the provided grammar increases, the performance of these tools degrades significantly. We claim that this degradation is not only due to a larger search space, but also due to overfitting. We formally define this phenomenon and prove no-free-lunch theorems for SyGuS, which reveal a fundamental tradeoff between synthesizer performance and grammar expressiveness. A standard approach to mitigate overfitting in machine learning is to run multiple learners with varying expressiveness in parallel. We demonstrate that this insight can immediately benefit existing SyGuS tools. We also propose a novel single-threaded technique called hybrid enumeration that interleaves different grammars and outperforms the winner of the 2018 SyGuS competition (Inv track), solving more problems and achieving a $5\times$ mean speedup. |
| Tasks | |
| Published | 2019-05-17 |
| URL | https://arxiv.org/abs/1905.07457v3 |
| https://arxiv.org/pdf/1905.07457v3.pdf | |
| PWC | https://paperswithcode.com/paper/overfitting-in-synthesis-theory-and-practice |
| Repo | |
| Framework | |
Weakly Supervised Fine Tuning Approach for Brain Tumor Segmentation Problem
| Title | Weakly Supervised Fine Tuning Approach for Brain Tumor Segmentation Problem |
| Authors | Sergey Pavlov, Alexey Artemov, Maksim Sharaev, Alexander Bernstein, Evgeny Burnaev |
| Abstract | Segmentation of tumors in brain MRI images is a challenging task, where most recent methods demand large volumes of data with pixel-level annotations, which are generally costly to obtain. In contrast, image-level annotations, where only the presence of lesion is marked, are generally cheap, generated in far larger volumes compared to pixel-level labels, and contain less labeling noise. In the context of brain tumor segmentation, both pixel-level and image-level annotations are commonly available; thus, a natural question arises whether a segmentation procedure could take advantage of both. In the present work we: 1) propose a learning-based framework that allows simultaneous usage of both pixel- and image-level annotations in MRI images to learn a segmentation model for brain tumor; 2) study the influence of comparative amounts of pixel- and image-level annotations on the quality of brain tumor segmentation; 3) compare our approach to the traditional fully-supervised approach and show that the performance of our method in terms of segmentation quality may be competitive. |
| Tasks | Brain Tumor Segmentation |
| Published | 2019-11-05 |
| URL | https://arxiv.org/abs/1911.01738v2 |
| https://arxiv.org/pdf/1911.01738v2.pdf | |
| PWC | https://paperswithcode.com/paper/weakly-supervised-fine-tuning-approach-for |
| Repo | |
| Framework | |
Improving Detection of Credit Card Fraudulent Transactions using Generative Adversarial Networks
| Title | Improving Detection of Credit Card Fraudulent Transactions using Generative Adversarial Networks |
| Authors | Hung Ba |
| Abstract | In this study, we employ Generative Adversarial Networks as an oversampling method to generate artificial data to assist with the classification of credit card fraudulent transactions. GANs is a generative model based on the idea of game theory, in which a generator G and a discriminator D are trying to outsmart each other. The objective of the generator is to confuse the discriminator. The objective of the discriminator is to distinguish the instances coming from the generator and the instances coming from the original dataset. By training GANs on a set of credit card fraudulent transactions, we are able to improve the discriminatory power of classifiers. The experiment results show that the Wasserstein-GAN is more stable in training and produce more realistic fraudulent transactions than the other GANs. On the other hand, the conditional version of GANs in which labels are set by k-means clustering does not necessarily improve the non-conditional versions of GANs. |
| Tasks | |
| Published | 2019-07-07 |
| URL | https://arxiv.org/abs/1907.03355v1 |
| https://arxiv.org/pdf/1907.03355v1.pdf | |
| PWC | https://paperswithcode.com/paper/improving-detection-of-credit-card-fraudulent |
| Repo | |
| Framework | |
Auto-Vectorizing TensorFlow Graphs: Jacobians, Auto-Batching And Beyond
| Title | Auto-Vectorizing TensorFlow Graphs: Jacobians, Auto-Batching And Beyond |
| Authors | Ashish Agarwal, Igor Ganichev |
| Abstract | We propose a static loop vectorization optimization on top of high level dataflow IR used by frameworks like TensorFlow. A new statically vectorized parallel-for abstraction is provided on top of TensorFlow, and used for applications ranging from auto-batching and per-example gradients, to jacobian computation, optimized map functions and input pipeline optimization. We report huge speedups compared to both loop based implementations, as well as run-time batching adopted by the DyNet framework. |
| Tasks | |
| Published | 2019-03-08 |
| URL | http://arxiv.org/abs/1903.04243v1 |
| http://arxiv.org/pdf/1903.04243v1.pdf | |
| PWC | https://paperswithcode.com/paper/auto-vectorizing-tensorflow-graphs-jacobians |
| Repo | |
| Framework | |
