January 30, 2020

2683 words 13 mins read

Paper Group ANR 264

Polyp Detection and Segmentation using Mask R-CNN: Does a Deeper Feature Extractor CNN Always Perform Better?. EVO* 2019 – Late-Breaking Abstracts Volume. Adversarial Deep Learning in EEG Biometrics. Reproducible White Matter Tract Segmentation Using 3D U-Net on a Large-scale DTI Dataset. Sentence Rewriting for Semantic Parsing. Computing Optimal …

Polyp Detection and Segmentation using Mask R-CNN: Does a Deeper Feature Extractor CNN Always Perform Better?


Title	Polyp Detection and Segmentation using Mask R-CNN: Does a Deeper Feature Extractor CNN Always Perform Better?
Authors	Hemin Ali Qadir, Younghak Shin, Johannes Solhusvik, Jacob Bergsland, Lars Aabakken, Ilangko Balasingham
Abstract	Automatic polyp detection and segmentation are highly desirable for colon screening due to polyp miss rate by physicians during colonoscopy, which is about 25%. However, this computerization is still an unsolved problem due to various polyp-like structures in the colon and high interclass polyp variations in terms of size, color, shape, and texture. In this paper, we adapt Mask R-CNN and evaluate its performance with different modern convolutional neural networks (CNN) as its feature extractor for polyp detection and segmentation. We investigate the performance improvement of each feature extractor by adding extra polyp images to the training dataset to answer whether we need deeper and more complex CNNs or better dataset for training in automatic polyp detection and segmentation. Finally, we propose an ensemble method for further performance improvement. We evaluate the performance on the 2015 MICCAI polyp detection dataset. The best results achieved are 72.59% recall, 80% precision, 70.42% dice, and 61.24% Jaccard. The model achieved state-of-the-art segmentation performance.
Tasks
Published	2019-07-22
URL	https://arxiv.org/abs/1907.09180v1
PDF	https://arxiv.org/pdf/1907.09180v1.pdf
PWC	https://paperswithcode.com/paper/polyp-detection-and-segmentation-using-mask-r
Repo
Framework

EVO* 2019 – Late-Breaking Abstracts Volume


Title	EVO* 2019 – Late-Breaking Abstracts Volume
Authors	A. M. Mora, A. I. Esparcia-Alcázar
Abstract	This volume contains the Late-Breaking Abstracts submitted to the EVO* 2019 Conference, that took place in Leipzig, from 24 to 26 of April. These papers where presented as short talks and also at the poster session of the conference together with other regular submissions. All of them present ongoing research and preliminary results investigating on the application of different approaches of Evolutionary Computation to different problems, most of them real world ones.
Tasks
Published	2019-07-30
URL	https://arxiv.org/abs/1907.12698v1
PDF	https://arxiv.org/pdf/1907.12698v1.pdf
PWC	https://paperswithcode.com/paper/evo-2019-late-breaking-abstracts-volume
Repo
Framework

Adversarial Deep Learning in EEG Biometrics


Title	Adversarial Deep Learning in EEG Biometrics
Authors	Ozan Ozdenizci, Ye Wang, Toshiaki Koike-Akino, Deniz Erdogmus
Abstract	Deep learning methods for person identification based on electroencephalographic (EEG) brain activity encounters the problem of exploiting the temporally correlated structures or recording session specific variability within EEG. Furthermore, recent methods have mostly trained and evaluated based on single session EEG data. We address this problem from an invariant representation learning perspective. We propose an adversarial inference approach to extend such deep learning models to learn session-invariant person-discriminative representations that can provide robustness in terms of longitudinal usability. Using adversarial learning within a deep convolutional network, we empirically assess and show improvements with our approach based on longitudinally collected EEG data for person identification from half-second EEG epochs.
Tasks	EEG, Person Identification, Representation Learning
Published	2019-03-27
URL	http://arxiv.org/abs/1903.11673v1
PDF	http://arxiv.org/pdf/1903.11673v1.pdf
PWC	https://paperswithcode.com/paper/adversarial-deep-learning-in-eeg-biometrics
Repo
Framework

Reproducible White Matter Tract Segmentation Using 3D U-Net on a Large-scale DTI Dataset


Title	Reproducible White Matter Tract Segmentation Using 3D U-Net on a Large-scale DTI Dataset
Authors	Bo Li, Marius de Groot, Meike Vernooij, Arfan Ikram, Wiro Niessen, Esther Bron
Abstract	Tract-specific diffusion measures, as derived from brain diffusion MRI, have been linked to white matter tract structural integrity and neurodegeneration. As a consequence, there is a large interest in the automatic segmentation of white matter tract in diffusion tensor MRI data. Methods based on the tractography are popular for white matter tract segmentation. However, because of the limited consistency and long processing time, such methods may not be suitable for clinical practice. We therefore developed a novel convolutional neural network based method to directly segment white matter tract trained on a low-resolution dataset of 9149 DTI images. The method is optimized on input, loss function and network architecture selections. We evaluated both segmentation accuracy and reproducibility, and reproducibility of determining tract-specific diffusion measures. The reproducibility of the method is higher than that of the reference standard and the determined diffusion measures are consistent. Therefore, we expect our method to be applicable in clinical practice and in longitudinal analysis of white matter microstructure.
Tasks
Published	2019-08-26
URL	https://arxiv.org/abs/1908.10219v1
PDF	https://arxiv.org/pdf/1908.10219v1.pdf
PWC	https://paperswithcode.com/paper/reproducible-white-matter-tract-segmentation
Repo
Framework

Sentence Rewriting for Semantic Parsing


Title	Sentence Rewriting for Semantic Parsing
Authors	Bo Chen, Le Sun, Xianpei Han, Bo An
Abstract	A major challenge of semantic parsing is the vocabulary mismatch problem between natural language and target ontology. In this paper, we propose a sentence rewriting based semantic parsing method, which can effectively resolve the mismatch problem by rewriting a sentence into a new form which has the same structure with its target logical form. Specifically, we propose two sentence-rewriting methods for two common types of mismatch: a dictionary-based method for 1-N mismatch and a template-based method for N-1 mismatch. We evaluate our entence rewriting based semantic parser on the benchmark semantic parsing dataset – WEBQUESTIONS. Experimental results show that our system outperforms the base system with a 3.4% gain in F1, and generates logical forms more accurately and parses sentences more robustly.
Tasks	Semantic Parsing
Published	2019-01-10
URL	http://arxiv.org/abs/1901.02998v1
PDF	http://arxiv.org/pdf/1901.02998v1.pdf
PWC	https://paperswithcode.com/paper/sentence-rewriting-for-semantic-parsing
Repo
Framework

Computing Optimal Coarse Correlated Equilibria in Sequential Games


Title	Computing Optimal Coarse Correlated Equilibria in Sequential Games
Authors	Andrea Celli, Stefano Coniglio, Nicola Gatti
Abstract	We investigate the computation of equilibria in extensive-form games where ex ante correlation is possible, focusing on correlated equilibria requiring the least amount of communication between the players and the mediator. Motivated by the hardness results on the computation of normal-form correlated equilibria, we introduce the notion of normal-form coarse correlated equilibrium, extending the definition of coarse correlated equilibrium to sequential games. We show that, in two-player games without chance moves, an optimal (e.g., social welfare maximizing) normal-form coarse correlated equilibrium can be computed in polynomial time, and that in general multi-player games (including two-player games with Chance), the problem is NP-hard. For the former case, we provide a polynomial-time algorithm based on the ellipsoid method and also propose a more practical one, which can be efficiently applied to problems of considerable size. Then, we discuss how our algorithm can be extended to games with Chance and games with more than two players.
Tasks
Published	2019-01-18
URL	http://arxiv.org/abs/1901.06221v1
PDF	http://arxiv.org/pdf/1901.06221v1.pdf
PWC	https://paperswithcode.com/paper/computing-optimal-coarse-correlated
Repo
Framework

Infinitely deep neural networks as diffusion processes


Title	Infinitely deep neural networks as diffusion processes
Authors	Stefano Peluchetti, Stefano Favaro
Abstract	When the parameters are independently and identically distributed (initialized) neural networks exhibit undesirable properties that emerge as the number of layers increases, e.g. a vanishing dependency on the input and a concentration on restrictive families of functions including constant functions. We consider parameter distributions that shrink as the number of layers increases in order to recover well-behaved stochastic processes in the limit of infinite depth. This leads to set forth a link between infinitely deep residual networks and solutions to stochastic differential equations, i.e. diffusion processes. We show that these limiting processes do not suffer from the aforementioned issues and investigate their properties.
Tasks
Published	2019-05-27
URL	https://arxiv.org/abs/1905.11065v3
PDF	https://arxiv.org/pdf/1905.11065v3.pdf
PWC	https://paperswithcode.com/paper/neural-stochastic-differential-equations
Repo
Framework

Heat Transfer Prediction for Methane in Regenerative Cooling Channels with Neural Networks


Title	Heat Transfer Prediction for Methane in Regenerative Cooling Channels with Neural Networks
Authors	Günther Waxenegger-Wilfing, Kai Dresia, Jan Christian Deeken, Michael Oschwald
Abstract	Methane is considered being a good choice as a propellant for future reusable launch systems. However, the heat transfer prediction for supercritical methane flowing in cooling channels of a regeneratively cooled combustion chamber is challenging. Because accurate heat transfer predictions are essential to design reliable and efficient cooling systems, heat transfer modeling is a fundamental issue to address. Advanced computational fluid dynamics (CFD) calculations achieve sufficient accuracy, but the associated computational cost prevents an efficient integration in optimization loops. Surrogate models based on artificial neural networks (ANNs) offer a great speed advantage. It is shown that an ANN, trained on data extracted from samples of CFD simulations, is able to predict the maximum wall temperature along straight rocket engine cooling channels using methane with convincing precision. The combination of the ANN model with simple relations for pressure drop and enthalpy rise results in a complete reduced order model, which can be used for numerically efficient design space exploration and optimization.
Tasks
Published	2019-07-24
URL	https://arxiv.org/abs/1907.11281v1
PDF	https://arxiv.org/pdf/1907.11281v1.pdf
PWC	https://paperswithcode.com/paper/heat-transfer-prediction-for-methane-in
Repo
Framework

A Model for Using Physiological Conditions for Proactive Tourist Recommendations


Title	A Model for Using Physiological Conditions for Proactive Tourist Recommendations
Authors	Rinita Roy, Linus W. Dietz
Abstract	Mobile proactive tourist recommender systems can support tourists by recommending the best choice depending on different contexts related to herself and the environment. In this paper, we propose to utilize wearable sensors to gather health information about a tourist and use them for recommending tourist activities. We discuss a range of wearable devices, sensors to infer physiological conditions of the users, and exemplify the feasibility using a popular self-quantification mobile app. Our main contribution then comprises a data model to derive relations between the parameters measured by the wearable sensors, such as heart rate, body temperature, blood pressure, and use them to infer the physiological condition of a user. This model can then be used to derive classes of tourist activities that determine which items should be recommended.
Tasks	Recommendation Systems
Published	2019-04-10
URL	http://arxiv.org/abs/1904.05247v1
PDF	http://arxiv.org/pdf/1904.05247v1.pdf
PWC	https://paperswithcode.com/paper/a-model-for-using-physiological-conditions
Repo
Framework

A Theoretical Analysis of Deep Q-Learning


Title	A Theoretical Analysis of Deep Q-Learning
Authors	Jianqing Fan, Zhaoran Wang, Yuchen Xie, Zhuoran Yang
Abstract	Despite the great empirical success of deep reinforcement learning, its theoretical foundation is less well understood. In this work, we make the first attempt to theoretically understand the deep Q-network (DQN) algorithm (Mnih et al., 2015) from both algorithmic and statistical perspectives. In specific, we focus on a slight simplification of DQN that fully captures its key features. Under mild assumptions, we establish the algorithmic and statistical rates of convergence for the action-value functions of the iterative policy sequence obtained by DQN. In particular, the statistical error characterizes the bias and variance that arise from approximating the action-value function using deep neural network, while the algorithmic error converges to zero at a geometric rate. As a byproduct, our analysis provides justifications for the techniques of experience replay and target network, which are crucial to the empirical success of DQN. Furthermore, as a simple extension of DQN, we propose the Minimax-DQN algorithm for zero-sum Markov game with two players. Borrowing the analysis of DQN, we also quantify the difference between the policies obtained by Minimax-DQN and the Nash equilibrium of the Markov game in terms of both the algorithmic and statistical rates of convergence.
Tasks	Q-Learning
Published	2019-01-01
URL	https://arxiv.org/abs/1901.00137v3
PDF	https://arxiv.org/pdf/1901.00137v3.pdf
PWC	https://paperswithcode.com/paper/a-theoretical-analysis-of-deep-q-learning
Repo
Framework

Comments on the Du-Kakade-Wang-Yang Lower Bounds


Title	Comments on the Du-Kakade-Wang-Yang Lower Bounds
Authors	Benjamin Van Roy, Shi Dong
Abstract	Du, Kakade, Wang, and Yang recently established intriguing lower bounds on sample complexity, which suggest that reinforcement learning with a misspecified representation is intractable. Another line of work, which centers around a statistic called the eluder dimension, establishes tractability of problems similar to those considered in the Du-Kakade-Wang-Yang paper. We compare these results and reconcile interpretations.
Tasks
Published	2019-11-18
URL	https://arxiv.org/abs/1911.07910v1
PDF	https://arxiv.org/pdf/1911.07910v1.pdf
PWC	https://paperswithcode.com/paper/comments-on-the-du-kakade-wang-yang-lower
Repo
Framework

Generating Relevant Counter-Examples from a Positive Unlabeled Dataset for Image Classification


Title	Generating Relevant Counter-Examples from a Positive Unlabeled Dataset for Image Classification
Authors	Florent Chiaroni, Ghazaleh Khodabandelou, Mohamed-Cherif Rahal, Nicolas Hueber, Frederic Dufaux
Abstract	With surge of available but unlabeled data, Positive Unlabeled (PU) learning is becoming a thriving challenge. This work deals with this demanding task for which recent GAN-based PU approaches have demonstrated promising results. Generative adversarial Networks (GANs) are not hampered by deterministic bias or need for specific dimensionality. However, existing GAN-based PU approaches also present some drawbacks such as sensitive dependence to prior knowledge, a cumbersome architecture or first-stage overfitting. To settle these issues, we propose to incorporate a biased PU risk within the standard GAN discriminator loss function. In this manner, the discriminator is constrained to request the generator to converge towards the unlabeled samples distribution while diverging from the positive samples distribution. This enables the proposed model, referred to as D-GAN, to exclusively learn the counter-examples distribution without prior knowledge. Experiments demonstrate that our approach outperforms state-of-the-art PU methods without prior by overcoming their issues.
Tasks	Image Classification
Published	2019-10-04
URL	https://arxiv.org/abs/1910.01968v1
PDF	https://arxiv.org/pdf/1910.01968v1.pdf
PWC	https://paperswithcode.com/paper/generating-relevant-counter-examples-from-a
Repo
Framework

CFO: A Framework for Building Production NLP Systems


Title	CFO: A Framework for Building Production NLP Systems
Authors	Rishav Chakravarti, Cezar Pendus, Andrzej Sakrajda, Anthony Ferritto, Lin Pan, Michael Glass, Vittorio Castelli, J. William Murdock, Radu Florian, Salim Roukos, Avirup Sil
Abstract	This paper introduces a novel orchestration framework, called CFO (COMPUTATION FLOW ORCHESTRATOR), for building, experimenting with, and deploying interactive NLP (Natural Language Processing) and IR (Information Retrieval) systems to production environments. We then demonstrate a question answering system built using this framework which incorporates state-of-the-art BERT based MRC (Machine Reading Comprehension) with IR components to enable end-to-end answer retrieval. Results from the demo system are shown to be high quality in both academic and industry domain specific settings. Finally, we discuss best practices when (pre-)training BERT based MRC models for production systems.
Tasks	Information Retrieval, Machine Reading Comprehension, Question Answering, Reading Comprehension
Published	2019-08-16
URL	https://arxiv.org/abs/1908.06121v2
PDF	https://arxiv.org/pdf/1908.06121v2.pdf
PWC	https://paperswithcode.com/paper/cfo-a-framework-for-building-production-nlp
Repo
Framework

Data Amplification: A Unified and Competitive Approach to Property Estimation


Title	Data Amplification: A Unified and Competitive Approach to Property Estimation
Authors	Yi Hao, Alon Orlitsky, Ananda T. Suresh, Yihong Wu
Abstract	Estimating properties of discrete distributions is a fundamental problem in statistical learning. We design the first unified, linear-time, competitive, property estimator that for a wide class of properties and for all underlying distributions uses just $2n$ samples to achieve the performance attained by the empirical estimator with $n\sqrt{\log n}$ samples. This provides off-the-shelf, distribution-independent, “amplification” of the amount of data available relative to common-practice estimators. We illustrate the estimator’s practical advantages by comparing it to existing estimators for a wide variety of properties and distributions. In most cases, its performance with $n$ samples is even as good as that of the empirical estimator with $n\log n$ samples, and for essentially all properties, its performance is comparable to that of the best existing estimator designed specifically for that property.
Tasks
Published	2019-03-29
URL	http://arxiv.org/abs/1904.00070v1
PDF	http://arxiv.org/pdf/1904.00070v1.pdf
PWC	https://paperswithcode.com/paper/data-amplification-a-unified-and-competitive-1
Repo
Framework

Explicit Facial Expression Transfer via Fine-Grained Semantic Representations


Title	Explicit Facial Expression Transfer via Fine-Grained Semantic Representations
Authors	Zhiwen Shao, Hengliang Zhu, Junshu Tang, Xuequan Lu, Lizhuang Ma
Abstract	Facial expression transfer between two unpaired images is a challenging problem, as fine-grained expressions are typically tangled with other facial attributes such as identity and pose. Most existing methods treat expression transfer as an application of expression manipulation, and use predicted facial expressions, landmarks or action units (AUs) of a source image to guide the expression edit of a target image. However, the prediction of expressions, landmarks and especially AUs may be inaccurate, which limits the accuracy of transferring fine-grained expressions. Instead of using an intermediate estimated guidance, we propose to explicitly transfer expressions by directly mapping two unpaired images to two synthesized images with swapped expressions. Since each AU semantically describes local expression details, we can synthesize new images with preserved identities and swapped expressions by combining AU-free features with swapped AU-related features. To disentangle the images into AU-related features and AU-free features, we propose a novel adversarial training method which can solve the adversarial learning of multi-class classification problems. Moreover, to obtain reliable expression transfer results of the unpaired input, we introduce a swap consistency loss to make the synthesized images and self-reconstructed images indistinguishable. Extensive experiments on RaFD, MMI and CFD datasets show that our approach can generate photo-realistic expression transfer results between unpaired images with different expression appearances including genders, ages, races and poses.
Tasks
Published	2019-09-06
URL	https://arxiv.org/abs/1909.02967v1
PDF	https://arxiv.org/pdf/1909.02967v1.pdf
PWC	https://paperswithcode.com/paper/explicit-facial-expression-transfer-via-fine
Repo
Framework