January 26, 2020

2990 words 15 mins read

Paper Group ANR 1591

Attention-based Lane Change Prediction. Deploying AI Frameworks on Secure HPC Systems with Containers. Differential Imaging Forensics. Deep learning surrogate models for spatial and visual connectivity. Model Inversion Networks for Model-Based Optimization. MuSE-ing on the Impact of Utterance Ordering On Crowdsourced Emotion Annotations. Towards Ro …

Attention-based Lane Change Prediction


Title	Attention-based Lane Change Prediction
Authors	Oliver Scheel, Naveen Shankar Nagaraja, Loren Schwarz, Nassir Navab, Federico Tombari
Abstract	Lane change prediction of surrounding vehicles is a key building block of path planning. The focus has been on increasing the accuracy of prediction by posing it purely as a function estimation problem at the cost of model understandability. However, the efficacy of any lane change prediction model can be improved when both corner and failure cases are humanly understandable. We propose an attention-based recurrent model to tackle both understandability and prediction quality. We also propose metrics which reflect the discomfort felt by the driver. We show encouraging results on a publicly available dataset and proprietary fleet data.
Tasks
Published	2019-03-04
URL	http://arxiv.org/abs/1903.01246v2
PDF	http://arxiv.org/pdf/1903.01246v2.pdf
PWC	https://paperswithcode.com/paper/attention-based-lane-change-prediction
Repo
Framework

Deploying AI Frameworks on Secure HPC Systems with Containers


Title	Deploying AI Frameworks on Secure HPC Systems with Containers
Authors	David Brayford, Sofia Vallecorsa, Atanas Atanasov, Fabio Baruffa, Walter Riviera
Abstract	The increasing interest in the usage of Artificial Intelligence techniques (AI) from the research community and industry to tackle “real world” problems, requires High Performance Computing (HPC) resources to efficiently compute and scale complex algorithms across thousands of nodes. Unfortunately, typical data scientists are not familiar with the unique requirements and characteristics of HPC environments. They usually develop their applications with high-level scripting languages or frameworks such as TensorFlow and the installation process often requires connection to external systems to download open source software during the build. HPC environments, on the other hand, are often based on closed source applications that incorporate parallel and distributed computing API’s such as MPI and OpenMP, while users have restricted administrator privileges, and face security restrictions such as not allowing access to external systems. In this paper we discuss the issues associated with the deployment of AI frameworks in a secure HPC environment and how we successfully deploy AI frameworks on SuperMUC-NG with Charliecloud.
Tasks
Published	2019-05-24
URL	https://arxiv.org/abs/1905.10090v1
PDF	https://arxiv.org/pdf/1905.10090v1.pdf
PWC	https://paperswithcode.com/paper/deploying-ai-frameworks-on-secure-hpc-systems
Repo
Framework

Differential Imaging Forensics


Title	Differential Imaging Forensics
Authors	Aurélien Bourquard, Jeff Yan
Abstract	We introduce some new forensics based on differential imaging, where a novel category of visual evidence created via subtle interactions of light with a scene, such as dim reflections, can be computationally extracted and amplified from an image of interest through a comparative analysis with an additional reference baseline image acquired under similar conditions. This paradigm of differential imaging forensics (DIF) enables forensic examiners for the first time to retrieve the said visual evidence that is readily available in an image or video footage but would otherwise remain faint or even invisible to a human observer. We demonstrate the relevance and effectiveness of our approach through practical experiments. We also show that DIF provides a novel method for detecting forged images and video clips, including deep fakes.
Tasks
Published	2019-06-12
URL	https://arxiv.org/abs/1906.05268v1
PDF	https://arxiv.org/pdf/1906.05268v1.pdf
PWC	https://paperswithcode.com/paper/differential-imaging-forensics
Repo
Framework

Deep learning surrogate models for spatial and visual connectivity


Title	Deep learning surrogate models for spatial and visual connectivity
Authors	Sherif Tarabishy, Stamatios Psarras, Marcin Kosicki, Martha Tsigkari
Abstract	Spatial and visual connectivity are important metrics when developing workplace layouts. Calculating those metrics in real-time can be difficult, depending on the size of the floor plan being analysed and the resolution of the analyses. This paper investigates the possibility of considerably speeding up the outcomes of such computationally intensive simulations by using machine learning to create models capable of identifying the spatial and visual connectivity potential of a space. To that end we present the entire process of investigating different machine learning models and a pipeline for training them on such task, from the incorporation of a bespoke spatial and visual connectivity analysis engine through a distributed computation pipeline, to the process of synthesizing training data and evaluating the performance of different neural networks.
Tasks
Published	2019-12-29
URL	https://arxiv.org/abs/1912.12616v1
PDF	https://arxiv.org/pdf/1912.12616v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-surrogate-models-for-spatial
Repo
Framework

Model Inversion Networks for Model-Based Optimization


Title	Model Inversion Networks for Model-Based Optimization
Authors	Aviral Kumar, Sergey Levine
Abstract	In this work, we aim to solve data-driven optimization problems, where the goal is to find an input that maximizes an unknown score function given access to a dataset of inputs with corresponding scores. When the inputs are high-dimensional and valid inputs constitute a small subset of this space (e.g., valid protein sequences or valid natural images), such model-based optimization problems become exceptionally difficult, since the optimizer must avoid out-of-distribution and invalid inputs. We propose to address such problem with model inversion networks (MINs), which learn an inverse mapping from scores to inputs. MINs can scale to high-dimensional input spaces and leverage offline logged data for both contextual and non-contextual optimization problems. MINs can also handle both purely offline data sources and active data collection. We evaluate MINs on tasks from the Bayesian optimization literature, high-dimensional model-based optimization problems over images and protein designs, and contextual bandit optimization from logged data.
Tasks
Published	2019-12-31
URL	https://arxiv.org/abs/1912.13464v1
PDF	https://arxiv.org/pdf/1912.13464v1.pdf
PWC	https://paperswithcode.com/paper/model-inversion-networks-for-model-based-1
Repo
Framework

MuSE-ing on the Impact of Utterance Ordering On Crowdsourced Emotion Annotations


Title	MuSE-ing on the Impact of Utterance Ordering On Crowdsourced Emotion Annotations
Authors	Mimansa Jaiswal, Zakaria Aldeneh, Cristian-Paul Bara, Yuanhang Luo, Mihai Burzo, Rada Mihalcea, Emily Mower Provost
Abstract	Emotion recognition algorithms rely on data annotated with high quality labels. However, emotion expression and perception are inherently subjective. There is generally not a single annotation that can be unambiguously declared “correct”. As a result, annotations are colored by the manner in which they were collected. In this paper, we conduct crowdsourcing experiments to investigate this impact on both the annotations themselves and on the performance of these algorithms. We focus on one critical question: the effect of context. We present a new emotion dataset, Multimodal Stressed Emotion (MuSE), and annotate the dataset using two conditions: randomized, in which annotators are presented with clips in random order, and contextualized, in which annotators are presented with clips in order. We find that contextual labeling schemes result in annotations that are more similar to a speaker’s own self-reported labels and that labels generated from randomized schemes are most easily predictable by automated systems.
Tasks	Emotion Recognition
Published	2019-03-27
URL	http://arxiv.org/abs/1903.11672v1
PDF	http://arxiv.org/pdf/1903.11672v1.pdf
PWC	https://paperswithcode.com/paper/muse-ing-on-the-impact-of-utterance-ordering
Repo
Framework

Towards Robust Learning with Different Label Noise Distributions


Title	Towards Robust Learning with Different Label Noise Distributions
Authors	Diego Ortego, Eric Arazo, Paul Albert, Noel E. O’Connor, Kevin McGuinness
Abstract	Noisy labels are an unavoidable consequence of automatic image labeling processes to reduce human supervision. Training in these conditions leads Convolutional Neural Networks to memorize label noise and degrade performance. Noisy labels are therefore dispensable, while image content can be exploited in a semi-supervised learning (SSL) setup. Handling label noise then becomes a label noise detection task. Noisy/clean samples are usually identified using the \textit{small loss trick}, which is based on the observation that clean samples represent easier patterns and, therefore, exhibit a lower loss. However, we show that different noise distributions make the application of this trick less straightforward. We propose to continuously relabel all images to reveal a loss that facilitates the use of the small loss trick with different noise distributions. SSL is then applied twice, once to improve the clean-noisy detection and again for training the final model. We design an experimental setup for better understanding the consequences of differing label noise distributions and find that non-uniform out-of-distribution noise better resembles real-world noise. We show that SSL outperforms other alternatives when using oracles and demonstrate substantial improvements across five datasets of our label noise Distribution Robust Pseudo-Labeling (DRPL). We further study the effects of label noise memorization via linear probes and find that in most cases intermediate features are not affected by label noise corruption. Code and details to reproduce our framework will be made available.
Tasks
Published	2019-12-18
URL	https://arxiv.org/abs/1912.08741v1
PDF	https://arxiv.org/pdf/1912.08741v1.pdf
PWC	https://paperswithcode.com/paper/towards-robust-learning-with-different-label
Repo
Framework

Probabilistic Permutation Invariant Training for Speech Separation


Title	Probabilistic Permutation Invariant Training for Speech Separation
Authors	Midia Yousefi, Soheil Khorram, John H. L. Hansen
Abstract	Single-microphone, speaker-independent speech separation is normally performed through two steps: (i) separating the specific speech sources, and (ii) determining the best output-label assignment to find the separation error. The second step is the main obstacle in training neural networks for speech separation. Recently proposed Permutation Invariant Training (PIT) addresses this problem by determining the output-label assignment which minimizes the separation error. In this study, we show that a major drawback of this technique is the overconfident choice of the output-label assignment, especially in the initial steps of training when the network generates unreliable outputs. To solve this problem, we propose Probabilistic PIT (Prob-PIT) which considers the output-label permutation as a discrete latent random variable with a uniform prior distribution. Prob-PIT defines a log-likelihood function based on the prior distributions and the separation errors of all permutations; it trains the speech separation networks by maximizing the log-likelihood function. Prob-PIT can be easily implemented by replacing the minimum function of PIT with a soft-minimum function. We evaluate our approach for speech separation on both TIMIT and CHiME datasets. The results show that the proposed method significantly outperforms PIT in terms of Signal to Distortion Ratio and Signal to Interference Ratio.
Tasks	Speech Separation
Published	2019-08-04
URL	https://arxiv.org/abs/1908.01768v1
PDF	https://arxiv.org/pdf/1908.01768v1.pdf
PWC	https://paperswithcode.com/paper/probabilistic-permutation-invariant-training
Repo
Framework

Training Deep Neural Networks by optimizing over nonlocal paths in hyperparameter space


Title	Training Deep Neural Networks by optimizing over nonlocal paths in hyperparameter space
Authors	Vlad Pushkarov, Jonathan Efroni, Mykola Maksymenko, Maciej Koch-Janusz
Abstract	Hyperparameter optimization is both a practical issue and an interesting theoretical problem in training of deep architectures. Despite many recent advances the most commonly used methods almost universally involve training multiple and decoupled copies of the model, in effect sampling the hyperparameter space. We show that at a negligible additional computational cost, results can be improved by sampling nonlocal paths instead of points in hyperparameter space. To this end we interpret hyperparameters as controlling the level of correlated noise in training, which can be mapped to an effective temperature. The usually independent instances of the model are coupled and allowed to exchange their hyperparameters throughout the training using the well established parallel tempering technique of statistical physics. Each simulation corresponds then to a unique path, or history, in the joint hyperparameter/model-parameter space. We provide empirical tests of our method, in particular for dropout and learning rate optimization. We observed faster training and improved resistance to overfitting and showed a systematic decrease in the absolute validation error, improving over benchmark results.
Tasks	Hyperparameter Optimization
Published	2019-09-09
URL	https://arxiv.org/abs/1909.04013v1
PDF	https://arxiv.org/pdf/1909.04013v1.pdf
PWC	https://paperswithcode.com/paper/training-deep-neural-networks-by-optimizing
Repo
Framework

Ensemble Pruning via Margin Maximization


Title	Ensemble Pruning via Margin Maximization
Authors	Waldyn Martinez
Abstract	Ensemble models refer to methods that combine a typically large number of classifiers into a compound prediction. The output of an ensemble method is the result of fitting a base-learning algorithm to a given data set, and obtaining diverse answers by reweighting the observations or by resampling them using a given probabilistic selection. A key challenge of using ensembles in large-scale multidimensional data lies in the complexity and the computational burden associated with them. The models created by ensembles are often difficult, if not impossible, to interpret and their implementation requires more computational power than single classifiers. Recent research effort in the field has concentrated in reducing ensemble size, while maintaining their predictive accuracy. We propose a method to prune an ensemble solution by optimizing its margin distribution, while increasing its diversity. The proposed algorithm results in an ensemble that uses only a fraction of the original classifiers, with improved or similar generalization performance. We analyze and test our method on both synthetic and real data sets. The simulations show that the proposed method compares favorably to the original ensemble solutions and to other existing ensemble pruning methodologies.
Tasks
Published	2019-06-07
URL	https://arxiv.org/abs/1906.03247v1
PDF	https://arxiv.org/pdf/1906.03247v1.pdf
PWC	https://paperswithcode.com/paper/ensemble-pruning-via-margin-maximization
Repo
Framework

An Adaptive Approach for Anomaly Detector Selection and Fine-Tuning in Time Series


Title	An Adaptive Approach for Anomaly Detector Selection and Fine-Tuning in Time Series
Authors	Hui Ye, Xiaopeng Ma, Qingfeng Pan, Huaqiang Fang, Hang Xiang, Tongzhen Shao
Abstract	The anomaly detection of time series is a hotspot of time series data mining. The own characteristics of different anomaly detectors determine the abnormal data that they are good at. There is no detector can be optimizing in all types of anomalies. Moreover, it still has difficulties in industrial production due to problems such as a single detector can’t be optimized at different time windows of the same time series. This paper proposes an adaptive model based on time series characteristics and selecting appropriate detector and run-time parameters for anomaly detection, which is called ATSDLN(Adaptive Time Series Detector Learning Network). We take the time series as the input of the model, and learn the time series representation through FCN. In order to realize the adaptive selection of detectors and run-time parameters according to the input time series, the outputs of FCN are the inputs of two sub-networks: the detector selection network and the run-time parameters selection network. In addition, the way that the variable layer width design of the parameter selection sub-network and the introduction of transfer learning make the model be with more expandability. Through experiments, it is found that ATSDLN can select appropriate anomaly detector and run-time parameters, and have strong expandability, which can quickly transfer. We investigate the performance of ATSDLN in public data sets, our methods outperform other methods in most cases with higher effect and better adaptation. We also show experimental results on public data sets to demonstrate how model structure and transfer learning affect the effectiveness.
Tasks	Anomaly Detection, Time Series, Transfer Learning
Published	2019-07-18
URL	https://arxiv.org/abs/1907.07843v1
PDF	https://arxiv.org/pdf/1907.07843v1.pdf
PWC	https://paperswithcode.com/paper/an-adaptive-approach-for-anomaly-detector
Repo
Framework

Automatic microscopic cell counting by use of unsupervised adversarial domain adaptation and supervised density regression


Title	Automatic microscopic cell counting by use of unsupervised adversarial domain adaptation and supervised density regression
Authors	Shenghua He, Kyaw Thu Minn, Lilianna Solnica-Krezel, Hua Li, Mark Anastasio
Abstract	Accurate cell counting in microscopic images is important for medical diagnoses and biological studies. However, manual cell counting is very time-consuming, tedious, and prone to subjective errors. We propose a new density regression-based method for automatic cell counting that reduces the need to manually annotate experimental images. A supervised learning-based density regression model (DRM) is trained with annotated synthetic images (the source domain) and their corresponding ground truth density maps. A domain adaptation model (DAM) is built to map experimental images (the target domain) to the feature space of the source domain. By use of the unsupervised learning-based DAM and supervised learning-based DRM, a cell density map of a given target image can be estimated, from which the number of cells can be counted. Results from experimental immunofluorescent microscopic images of human embryonic stem cells demonstrate the promising performance of the proposed counting method.
Tasks	Domain Adaptation
Published	2019-03-01
URL	http://arxiv.org/abs/1903.00388v2
PDF	http://arxiv.org/pdf/1903.00388v2.pdf
PWC	https://paperswithcode.com/paper/automatic-microscopic-cell-counting-by-use-of
Repo
Framework

Improving Facial Emotion Recognition Systems Using Gradient and Laplacian Images


Title	Improving Facial Emotion Recognition Systems Using Gradient and Laplacian Images
Authors	Ram Krishna Pandey, Souvik Karmakar, A G Ramakrishnan, Nabagata Saha
Abstract	In this work, we have proposed several enhancements to improve the performance of any facial emotion recognition (FER) system. We believe that the changes in the positions of the fiducial points and the intensities capture the crucial information regarding the emotion of a face image. We propose the use of the gradient and the Laplacian of the input image together with the original input into a convolutional neural network (CNN). These modifications help the network learn additional information from the gradient and Laplacian of the images. However, the plain CNN is not able to extract this information from the raw images. We have performed a number of experiments on two well known datasets KDEF and FERplus. Our approach enhances the already high performance of state-of-the-art FER systems by 3 to 5%.
Tasks	Emotion Recognition
Published	2019-02-12
URL	http://arxiv.org/abs/1902.05411v1
PDF	http://arxiv.org/pdf/1902.05411v1.pdf
PWC	https://paperswithcode.com/paper/improving-facial-emotion-recognition-systems
Repo
Framework

Deep Graph Similarity Learning: A Survey


Title	Deep Graph Similarity Learning: A Survey
Authors	Guixiang Ma, Nesreen K. Ahmed, Theodore L. Willke, Philip S. Yu
Abstract	In many domains where data are represented as graphs, learning a similarity metric among graphs is considered a key problem, which can further facilitate various learning tasks, such as classification, clustering, and similarity search. Recently, there has been an increasing interest in deep graph similarity learning, where the key idea is to learn a deep learning model that maps input graphs to a target space such that the distance in the target space approximates the structural distance in the input space. Here, we provide a comprehensive review of the existing literature of deep graph similarity learning. We propose a systematic taxonomy for the methods and applications. Finally, we discuss the challenges and future directions for this problem.
Tasks	Graph Similarity
Published	2019-12-25
URL	https://arxiv.org/abs/1912.11615v1
PDF	https://arxiv.org/pdf/1912.11615v1.pdf
PWC	https://paperswithcode.com/paper/deep-graph-similarity-learning-a-survey
Repo
Framework

Using Entity Relations for Opinion Mining of Vietnamese Comments


Title	Using Entity Relations for Opinion Mining of Vietnamese Comments
Authors	P. T. Nguyen, L. T. Le, V. M. Ngo, P. M. Nguyen
Abstract	In this paper, we propose several novel techniques to extract and mining opinions of Vietnamese reviews of customers about a number of products traded on e-commerce in Vietnam. The assessment is based on the emotional level of customers on a specific product such as mobile and laptop. We exploit the features of the products because they are much interested by customers and have many products in the Vietnam e-commerce market. Thence, it can be known the favorites and dislikes of customers about exploited products.
Tasks	Opinion Mining
Published	2019-05-16
URL	https://arxiv.org/abs/1905.06647v1
PDF	https://arxiv.org/pdf/1905.06647v1.pdf
PWC	https://paperswithcode.com/paper/using-entity-relations-for-opinion-mining-of
Repo
Framework