April 2, 2020

3552 words 17 mins read

Paper Group ANR 188

Semantic sensor fusion: from camera to sparse lidar information. Using generative adversarial networks to synthesize artificial financial datasets. Generalized Bayesian Cramér-Rao Inequality via Information Geometry of Relative $α$-Entropy. Disentangling Representations using Gaussian Processes in Variational Autoencoders for Video Prediction. Inte …

Semantic sensor fusion: from camera to sparse lidar information


Title	Semantic sensor fusion: from camera to sparse lidar information
Authors	Julie Stephany Berrio, Mao Shan, Stewart Worrall, James Ward, Eduardo Nebot
Abstract	To navigate through urban roads, an automated vehicle must be able to perceive and recognize objects in a three-dimensional environment. A high-level contextual understanding of the surroundings is necessary to plan and execute accurate driving maneuvers. This paper presents an approach to fuse different sensory information, Light Detection and Ranging (lidar) scans and camera images. The output of a convolutional neural network (CNN) is used as classifier to obtain the labels of the environment. The transference of semantic information between the labelled image and the lidar point cloud is performed in four steps: initially, we use heuristic methods to associate probabilities to all the semantic classes contained in the labelled images. Then, the lidar points are corrected to compensate for the vehicle’s motion given the difference between the timestamps of each lidar scan and camera image. In a third step, we calculate the pixel coordinate for the corresponding camera image. In the last step we perform the transfer of semantic information from the heuristic probability images to the lidar frame, while removing the lidar information that is not visible to the camera. We tested our approach in the Usyd Dataset \cite{usyd_dataset}, obtaining qualitative and quantitative results that demonstrate the validity of our probabilistic sensory fusion approach.
Tasks	Sensor Fusion
Published	2020-03-04
URL	https://arxiv.org/abs/2003.01871v1
PDF	https://arxiv.org/pdf/2003.01871v1.pdf
PWC	https://paperswithcode.com/paper/semantic-sensor-fusion-from-camera-to-sparse
Repo
Framework

Using generative adversarial networks to synthesize artificial financial datasets


Title	Using generative adversarial networks to synthesize artificial financial datasets
Authors	Dmitry Efimov, Di Xu, Luyang Kong, Alexey Nefedov, Archana Anandakrishnan
Abstract	Generative Adversarial Networks (GANs) became very popular for generation of realistically looking images. In this paper, we propose to use GANs to synthesize artificial financial data for research and benchmarking purposes. We test this approach on three American Express datasets, and show that properly trained GANs can replicate these datasets with high fidelity. For our experiments, we define a novel type of GAN, and suggest methods for data preprocessing that allow good training and testing performance of GANs. We also discuss methods for evaluating the quality of generated data, and their comparison with the original real data.
Tasks
Published	2020-02-06
URL	https://arxiv.org/abs/2002.02271v1
PDF	https://arxiv.org/pdf/2002.02271v1.pdf
PWC	https://paperswithcode.com/paper/using-generative-adversarial-networks-to
Repo
Framework

Generalized Bayesian Cramér-Rao Inequality via Information Geometry of Relative $α$-Entropy


Title	Generalized Bayesian Cramér-Rao Inequality via Information Geometry of Relative $α$-Entropy
Authors	Kumar Vijay Mishra, M. Ashok Kumar
Abstract	The relative $\alpha$-entropy is the R'enyi analog of relative entropy and arises prominently in information-theoretic problems. Recent information geometric investigations on this quantity have enabled the generalization of the Cram'{e}r-Rao inequality, which provides a lower bound for the variance of an estimator of an escort of the underlying parametric probability distribution. However, this framework remains unexamined in the Bayesian framework. In this paper, we propose a general Riemannian metric based on relative $\alpha$-entropy to obtain a generalized Bayesian Cram'{e}r-Rao inequality. This establishes a lower bound for the variance of an unbiased estimator for the $\alpha$-escort distribution starting from an unbiased estimator for the underlying distribution. We show that in the limiting case when the entropy order approaches unity, this framework reduces to the conventional Bayesian Cram'{e}r-Rao inequality. Further, in the absence of priors, the same framework yields the deterministic Cram'{e}r-Rao inequality.
Tasks
Published	2020-02-11
URL	https://arxiv.org/abs/2002.04732v1
PDF	https://arxiv.org/pdf/2002.04732v1.pdf
PWC	https://paperswithcode.com/paper/generalized-bayesian-cramer-rao-inequality
Repo
Framework

Disentangling Representations using Gaussian Processes in Variational Autoencoders for Video Prediction


Title	Disentangling Representations using Gaussian Processes in Variational Autoencoders for Video Prediction
Authors	Sarthak Bhagat, Shagun Uppal, Vivian Yin, Nengli Lim
Abstract	We introduce MGP-VAE, a variational autoencoder which uses Gaussian processes (GP) to model the latent space distribution. We employ MGP-VAE for the unsupervised learning of video sequences to obtain disentangled representations. Previous work in this area has mainly been confined to separating dynamic information from static content. We improve on previous results by establishing a framework by which multiple features, static or dynamic, can be disentangled. Specifically we use fractional Brownian motions (fBM) and Brownian bridges (BB) to enforce an inter-frame correlation structure in each independent channel. We show that varying this correlation structure enables one to capture different aspects of variation in the data. We demonstrate the quality of our disentangled representations on numerous experiments on three publicly available datasets, and also perform quantitative tests on a video prediction task. In addition, we introduce a novel geodesic loss function which takes into account the curvature of the data manifold to improve learning in the prediction task. Our experiments show quantitatively that the combination of our improved disentangled representations with the novel loss function enable MGP-VAE to outperform the state-of-the-art in video prediction.
Tasks	Gaussian Processes, Video Prediction
Published	2020-01-08
URL	https://arxiv.org/abs/2001.02408v1
PDF	https://arxiv.org/pdf/2001.02408v1.pdf
PWC	https://paperswithcode.com/paper/disentangling-representations-using-gaussian
Repo
Framework

Interpreting Galaxy Deblender GAN from the Discriminator’s Perspective


Title	Interpreting Galaxy Deblender GAN from the Discriminator’s Perspective
Authors	Heyi Li, Yuewei Lin, Klaus Mueller, Wei Xu
Abstract	Generative adversarial networks (GANs) are well known for their unsupervised learning capabilities. A recent success in the field of astronomy is deblending two overlapping galaxy images via a branched GAN model. However, it remains a significant challenge to comprehend how the network works, which is particularly difficult for non-expert users. This research focuses on behaviors of one of the network’s major components, the Discriminator, which plays a vital role but is often overlooked, Specifically, we enhance the Layer-wise Relevance Propagation (LRP) scheme to generate a heatmap-based visualization. We call this technique Polarized-LRP and it consists of two parts i.e. positive contribution heatmaps for ground truth images and negative contribution heatmaps for generated images. Using the Galaxy Zoo dataset we demonstrate that our method clearly reveals attention areas of the Discriminator when differentiating generated galaxy images from ground truth images. To connect the Discriminator’s impact on the Generator, we visualize the gradual changes of the Generator across the training process. An interesting result we have achieved there is the detection of a problematic data augmentation procedure that would else have remained hidden. We find that our proposed method serves as a useful visual analytical tool for a deeper understanding of GAN models.
Tasks	Data Augmentation
Published	2020-01-17
URL	https://arxiv.org/abs/2001.06151v1
PDF	https://arxiv.org/pdf/2001.06151v1.pdf
PWC	https://paperswithcode.com/paper/interpreting-galaxy-deblender-gan-from-the
Repo
Framework

Controlling Rayleigh-Bénard convection via Reinforcement Learning


Title	Controlling Rayleigh-Bénard convection via Reinforcement Learning
Authors	Gerben Beintema, Alessandro Corbetta, Luca Biferale, Federico Toschi
Abstract	Thermal convection is ubiquitous in nature as well as in many industrial applications. The identification of effective control strategies to, e.g., suppress or enhance the convective heat exchange under fixed external thermal gradients is an outstanding fundamental and technological issue. In this work, we explore a novel approach, based on a state-of-the-art Reinforcement Learning (RL) algorithm, which is capable of significantly reducing the heat transport in a two-dimensional Rayleigh-B'enard system by applying small temperature fluctuations to the lower boundary of the system. By using numerical simulations, we show that our RL-based control is able to stabilize the conductive regime and bring the onset of convection up to a Rayleigh number $Ra_c \approx 3 \cdot 10^4$, whereas in the uncontrolled case it holds $Ra_{c}=1708$. Additionally, for $Ra > 3 \cdot 10^4$, our approach outperforms other state-of-the-art control algorithms reducing the heat flux by a factor of about $2.5$. In the last part of the manuscript, we address theoretical limits connected to controlling an unstable and chaotic dynamics as the one considered here. We show that controllability is hindered by observability and/or capabilities of actuating actions, which can be quantified in terms of characteristic time delays. When these delays become comparable with the Lyapunov time of the system, control becomes impossible.
Tasks
Published	2020-03-31
URL	https://arxiv.org/abs/2003.14358v1
PDF	https://arxiv.org/pdf/2003.14358v1.pdf
PWC	https://paperswithcode.com/paper/controlling-rayleigh-benard-convection-via
Repo
Framework

SimEx: Express Prediction of Inter-dataset Similarity by a Fleet of Autoencoders


Title	SimEx: Express Prediction of Inter-dataset Similarity by a Fleet of Autoencoders
Authors	Inseok Hwang, Jinho Lee, Frank Liu, Minsik Cho
Abstract	Knowing the similarity between sets of data has a number of positive implications in training an effective model, such as assisting an informed selection out of known datasets favorable to model transfer or data augmentation problems with an unknown dataset. Common practices to estimate the similarity between data include comparing in the original sample space, comparing in the embedding space from a model performing a certain task, or fine-tuning a pretrained model with different datasets and evaluating the performance changes therefrom. However, these practices would suffer from shallow comparisons, task-specific biases, or extensive time and computations required to perform comparisons. We present SimEx, a new method for early prediction of inter-dataset similarity using a set of pretrained autoencoders each of which is dedicated to reconstructing a specific part of known data. Specifically, our method takes unknown data samples as input to those pretrained autoencoders, and evaluate the difference between the reconstructed output samples against their original input samples. Our intuition is that, the more similarity exists between the unknown data samples and the part of known data that an autoencoder was trained with, the better chances there could be that this autoencoder makes use of its trained knowledge, reconstructing output samples closer to the originals. We demonstrate that our method achieves more than 10x speed-up in predicting inter-dataset similarity compared to common similarity-estimating practices. We also demonstrate that the inter-dataset similarity estimated by our method is well-correlated with common practices and outperforms the baselines approaches of comparing at sample- or embedding-spaces, without newly training anything at the comparison time.
Tasks	Data Augmentation
Published	2020-01-14
URL	https://arxiv.org/abs/2001.04893v1
PDF	https://arxiv.org/pdf/2001.04893v1.pdf
PWC	https://paperswithcode.com/paper/simex-express-prediction-of-inter-dataset
Repo
Framework

A Post-processing Method for Detecting Unknown Intent of Dialogue System via Pre-trained Deep Neural Network Classifier


Title	A Post-processing Method for Detecting Unknown Intent of Dialogue System via Pre-trained Deep Neural Network Classifier
Authors	Ting-En Lin, Hua Xu
Abstract	With the maturity and popularity of dialogue systems, detecting user’s unknown intent in dialogue systems has become an important task. It is also one of the most challenging tasks since we can hardly get examples, prior knowledge or the exact numbers of unknown intents. In this paper, we propose SofterMax and deep novelty detection (SMDN), a simple yet effective post-processing method for detecting unknown intent in dialogue systems based on pre-trained deep neural network classifiers. Our method can be flexibly applied on top of any classifiers trained in deep neural networks without changing the model architecture. We calibrate the confidence of the softmax outputs to compute the calibrated confidence score (i.e., SofterMax) and use it to calculate the decision boundary for unknown intent detection. Furthermore, we feed the feature representations learned by the deep neural networks into traditional novelty detection algorithm to detect unknown intents from different perspectives. Finally, we combine the methods above to perform the joint prediction. Our method classifies examples that differ from known intents as unknown and does not require any examples or prior knowledge of it. We have conducted extensive experiments on three benchmark dialogue datasets. The results show that our method can yield significant improvements compared with the state-of-the-art baselines
Tasks	Intent Detection
Published	2020-03-07
URL	https://arxiv.org/abs/2003.03504v1
PDF	https://arxiv.org/pdf/2003.03504v1.pdf
PWC	https://paperswithcode.com/paper/a-post-processing-method-for-detecting
Repo
Framework

ScopeIt: Scoping Task Relevant Sentences in Documents


Title	ScopeIt: Scoping Task Relevant Sentences in Documents
Authors	Vishwas Suryanarayanan, Barun Patra, Pamela Bhattacharya, Chala Fufa, Charles Lee
Abstract	Intelligent assistants like Cortana, Siri, Alexa, and Google Assistant are trained to parse information when the conversation is synchronous and short; however, for email-based conversational agents, the communication is asynchronous, and often contains information irrelevant to the assistant. This makes it harder for the system to accurately detect intents, extract entities relevant to those intents and thereby perform the desired action. We present a neural model for scoping relevant information for the agent from a large query. We show that when used as a preprocessing step, the model improves performance of both intent detection and entity extraction tasks. We demonstrate the model’s impact on Scheduler (Cortana is the persona of the agent, while Scheduler is the name of the service. We use them interchangeably in the context of this paper.) - a virtual conversational meeting scheduling assistant that interacts asynchronously with users through email. The model helps the entity extraction and intent detection tasks requisite by Scheduler achieve an average gain of 35% in precision without any drop in recall. Additionally, we demonstrate that the same approach can be used for component level analysis in large documents, such as signature block identification.
Tasks	Entity Extraction, Intent Detection
Published	2020-02-23
URL	https://arxiv.org/abs/2003.04988v1
PDF	https://arxiv.org/pdf/2003.04988v1.pdf
PWC	https://paperswithcode.com/paper/scopeit-scoping-task-relevant-sentences-in
Repo
Framework

Asymmetric Distribution Measure for Few-shot Learning


Title	Asymmetric Distribution Measure for Few-shot Learning
Authors	Wenbin Li, Lei Wang, Jing Huo, Yinghuan Shi, Yang Gao, Jiebo Luo
Abstract	The core idea of metric-based few-shot image classification is to directly measure the relations between query images and support classes to learn transferable feature embeddings. Previous work mainly focuses on image-level feature representations, which actually cannot effectively estimate a class’s distribution due to the scarcity of samples. Some recent work shows that local descriptor based representations can achieve richer representations than image-level based representations. However, such works are still based on a less effective instance-level metric, especially a symmetric metric, to measure the relations between query images and support classes. Given the natural asymmetric relation between a query image and a support class, we argue that an asymmetric measure is more suitable for metric-based few-shot learning. To that end, we propose a novel Asymmetric Distribution Measure (ADM) network for few-shot learning by calculating a joint local and global asymmetric measure between two multivariate local distributions of queries and classes. Moreover, a task-aware Contrastive Measure Strategy (CMS) is proposed to further enhance the measure function. On popular miniImageNet and tieredImageNet, we achieve $3.02%$ and $1.56%$ gains over the state-of-the-art method on the $5$-way $1$-shot task, respectively, validating our innovative design of asymmetric distribution measures for few-shot learning.
Tasks	Few-Shot Image Classification, Few-Shot Learning, Image Classification
Published	2020-02-01
URL	https://arxiv.org/abs/2002.00153v1
PDF	https://arxiv.org/pdf/2002.00153v1.pdf
PWC	https://paperswithcode.com/paper/asymmetric-distribution-measure-for-few-shot
Repo
Framework

A$^3$: Accelerating Attention Mechanisms in Neural Networks with Approximation


Title	A$^3$: Accelerating Attention Mechanisms in Neural Networks with Approximation
Authors	Tae Jun Ham, Sung Jun Jung, Seonghak Kim, Young H. Oh, Yeonhong Park, Yoonho Song, Jung-Hun Park, Sanghee Lee, Kyoung Park, Jae W. Lee, Deog-Kyoon Jeong
Abstract	With the increasing computational demands of neural networks, many hardware accelerators for the neural networks have been proposed. Such existing neural network accelerators often focus on popular neural network types such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs); however, not much attention has been paid to attention mechanisms, an emerging neural network primitive that enables neural networks to retrieve most relevant information from a knowledge-base, external memory, or past states. The attention mechanism is widely adopted by many state-of-the-art neural networks for computer vision, natural language processing, and machine translation, and accounts for a large portion of total execution time. We observe today’s practice of implementing this mechanism using matrix-vector multiplication is suboptimal as the attention mechanism is semantically a content-based search where a large portion of computations ends up not being used. Based on this observation, we design and architect A3, which accelerates attention mechanisms in neural networks with algorithmic approximation and hardware specialization. Our proposed accelerator achieves multiple orders of magnitude improvement in energy efficiency (performance/watt) as well as substantial speedup over the state-of-the-art conventional hardware.
Tasks	Machine Translation
Published	2020-02-22
URL	https://arxiv.org/abs/2002.10941v1
PDF	https://arxiv.org/pdf/2002.10941v1.pdf
PWC	https://paperswithcode.com/paper/a3-accelerating-attention-mechanisms-in
Repo
Framework

Validating uncertainty in medical image translation


Title	Validating uncertainty in medical image translation
Authors	Jacob C. Reinhold, Yufan He, Shizhong Han, Yunqiang Chen, Dashan Gao, Junghoon Lee, Jerry L. Prince, Aaron Carass
Abstract	Medical images are increasingly used as input to deep neural networks to produce quantitative values that aid researchers and clinicians. However, standard deep neural networks do not provide a reliable measure of uncertainty in those quantitative values. Recent work has shown that using dropout during training and testing can provide estimates of uncertainty. In this work, we investigate using dropout to estimate epistemic and aleatoric uncertainty in a CT-to-MR image translation task. We show that both types of uncertainty are captured, as defined, providing confidence in the output uncertainty estimates.
Tasks
Published	2020-02-11
URL	https://arxiv.org/abs/2002.04639v1
PDF	https://arxiv.org/pdf/2002.04639v1.pdf
PWC	https://paperswithcode.com/paper/validating-uncertainty-in-medical-image
Repo
Framework

Layerwise Knowledge Extraction from Deep Convolutional Networks


Title	Layerwise Knowledge Extraction from Deep Convolutional Networks
Authors	Simon Odense, Artur d’Avila Garcez
Abstract	Knowledge extraction is used to convert neural networks into symbolic descriptions with the objective of producing more comprehensible learning models. The central challenge is to find an explanation which is more comprehensible than the original model while still representing that model faithfully. The distributed nature of deep networks has led many to believe that the hidden features of a neural network cannot be explained by logical descriptions simple enough to be comprehensible. In this paper, we propose a novel layerwise knowledge extraction method using M-of-N rules which seeks to obtain the best trade-off between the complexity and accuracy of rules describing the hidden features of a deep network. We show empirically that this approach produces rules close to an optimal complexity-error tradeoff. We apply this method to a variety of deep networks and find that in the internal layers we often cannot find rules with a satisfactory complexity and accuracy, suggesting that rule extraction as a general purpose method for explaining the internal logic of a neural network may be impossible. However, we also find that the softmax layer in Convolutional Neural Networks and Autoencoders using either tanh or relu activation functions is highly explainable by rule extraction, with compact rules consisting of as little as 3 units out of 128 often reaching over 99% accuracy. This shows that rule extraction can be a useful component for explaining parts (or modules) of a deep neural network.
Tasks
Published	2020-03-19
URL	https://arxiv.org/abs/2003.09000v1
PDF	https://arxiv.org/pdf/2003.09000v1.pdf
PWC	https://paperswithcode.com/paper/layerwise-knowledge-extraction-from-deep
Repo
Framework

CodeBERT: A Pre-Trained Model for Programming and Natural Languages


Title	CodeBERT: A Pre-Trained Model for Programming and Natural Languages
Authors	Zhangyin Feng, Daya Guo, Duyu Tang, Nan Duan, Xiaocheng Feng, Ming Gong, Linjun Shou, Bing Qin, Ting Liu, Daxin Jiang, Ming Zhou
Abstract	We present CodeBERT, a bimodal pre-trained model for programming language (PL) and nat-ural language (NL). CodeBERT learns general-purpose representations that support downstream NL-PL applications such as natural language codesearch, code documentation generation, etc. We develop CodeBERT with Transformer-based neural architecture, and train it with a hybrid objective function that incorporates the pre-training task of replaced token detection, which is to detect plausible alternatives sampled from generators. This enables us to utilize both bimodal data of NL-PL pairs and unimodal data, where the former provides input tokens for model training while the latter helps to learn better generators. We evaluate CodeBERT on two NL-PL applications by fine-tuning model parameters. Results show that CodeBERT achieves state-of-the-art performance on both natural language code search and code documentation generation tasks. Furthermore, to investigate what type of knowledge is learned in CodeBERT, we construct a dataset for NL-PL probing, and evaluate in a zero-shot setting where parameters of pre-trained models are fixed. Results show that CodeBERT performs better than previous pre-trained models on NL-PL probing.
Tasks	Code Search
Published	2020-02-19
URL	https://arxiv.org/abs/2002.08155v1
PDF	https://arxiv.org/pdf/2002.08155v1.pdf
PWC	https://paperswithcode.com/paper/codebert-a-pre-trained-model-for-programming
Repo
Framework

Inference for Network Structure and Dynamics from Time Series Data via Graph Neural Network


Title	Inference for Network Structure and Dynamics from Time Series Data via Graph Neural Network
Authors	Mengyuan Chen, Jiang Zhang, Zhang Zhang, Lun Du, Qiao Hu, Shuo Wang, Jiaqi Zhu
Abstract	Network structures in various backgrounds play important roles in social, technological, and biological systems. However, the observable network structures in real cases are often incomplete or unavailable due to measurement errors or private protection issues. Therefore, inferring the complete network structure is useful for understanding complex systems. The existing studies have not fully solved the problem of inferring network structure with partial or no information about connections or nodes. In this paper, we tackle the problem by utilizing time series data generated by network dynamics. We regard the network inference problem based on dynamical time series data as a problem of minimizing errors for predicting future states and proposed a novel data-driven deep learning model called Gumbel Graph Network (GGN) to solve the two kinds of network inference problems: Network Reconstruction and Network Completion. For the network reconstruction problem, the GGN framework includes two modules: the dynamics learner and the network generator. For the network completion problem, GGN adds a new module called the States Learner to infer missing parts of the network. We carried out experiments on discrete and continuous time series data. The experiments show that our method can reconstruct up to 100% network structure on the network reconstruction task. While the model can also infer the unknown parts of the structure with up to 90% accuracy when some nodes are missing. And the accuracy decays with the increase of the fractions of missing nodes. Our framework may have wide application areas where the network structure is hard to obtained and the time series data is rich.
Tasks	Time Series
Published	2020-01-18
URL	https://arxiv.org/abs/2001.06576v1
PDF	https://arxiv.org/pdf/2001.06576v1.pdf
PWC	https://paperswithcode.com/paper/inference-for-network-structure-and-dynamics
Repo
Framework