January 30, 2020

3024 words 15 mins read

Paper Group ANR 357

Thinking Globally, Acting Locally: Distantly Supervised Global-to-Local Knowledge Selection for Background Based Conversation. Metamorphic Testing for Object Detection Systems. Deep Multi-Task Learning for Anomalous Driving Detection Using CAN Bus Scalar Sensor Data. Inferring linear and nonlinear Interaction networks using neighborhood support vec …

Thinking Globally, Acting Locally: Distantly Supervised Global-to-Local Knowledge Selection for Background Based Conversation


Title	Thinking Globally, Acting Locally: Distantly Supervised Global-to-Local Knowledge Selection for Background Based Conversation
Authors	Pengjie Ren, Zhumin Chen, Christof Monz, Jun Ma, Maarten de Rijke
Abstract	Background Based Conversations (BBCs) have been introduced to help conversational systems avoid generating overly generic responses. In a BBC, the conversation is grounded in a knowledge source. A key challenge in BBCs is Knowledge Selection (KS): given a conversational context, try to find the appropriate background knowledge (a text fragment containing related facts or comments, etc.) based on which to generate the next response. Previous work addresses KS by employing attention and/or pointer mechanisms. These mechanisms use a local perspective, i.e., they select a token at a time based solely on the current decoding state. We argue for the adoption of a global perspective, i.e., pre-selecting some text fragments from the background knowledge that could help determine the topic of the next response. We enhance KS in BBCs by introducing a Global-to-Local Knowledge Selection (GLKS) mechanism. Given a conversational context and background knowledge, we first learn a topic transition vector to encode the most likely text fragments to be used in the next response, which is then used to guide the local KS at each decoding timestamp. In order to effectively learn the topic transition vector, we propose a distantly supervised learning schema. Experimental results show that the GLKS model significantly outperforms state-of-the-art methods in terms of both automatic and human evaluation. More importantly, GLKS achieves this without requiring any extra annotations, which demonstrates its high degree of scalability.
Tasks
Published	2019-08-26
URL	https://arxiv.org/abs/1908.09528v2
PDF	https://arxiv.org/pdf/1908.09528v2.pdf
PWC	https://paperswithcode.com/paper/thinking-globally-acting-locally-distantly
Repo
Framework

Metamorphic Testing for Object Detection Systems


Title	Metamorphic Testing for Object Detection Systems
Authors	Shuai Wang, Zhendong Su
Abstract	Recent advances in deep neural networks (DNNs) have led to object detectors that can rapidly process pictures or videos, and recognize the objects that they contain. Despite the promising progress by industrial manufacturers such as Amazon and Google in commercializing deep learning-based object detection as a standard computer vision service, object detection systems - similar to traditional software - may still produce incorrect results. These errors, in turn, can lead to severe negative outcomes for the users of these object detection systems. For instance, an autonomous driving system that fails to detect pedestrians can cause accidents or even fatalities. However, principled, systematic methods for testing object detection systems do not yet exist, despite their importance. To fill this critical gap, we introduce the design and realization of MetaOD, the first metamorphic testing system for object detectors to effectively reveal erroneous detection results by commercial object detectors. To this end, we (1) synthesize natural-looking images by inserting extra object instances into background images, and (2) design metamorphic conditions asserting the equivalence of object detection results between the original and synthetic images after excluding the prediction results on the inserted objects. MetaOD is designed as a streamlined workflow that performs object extraction, selection, and insertion. Evaluated on four commercial object detection services and four pretrained models provided by the TensorFlow API, MetaOD found tens of thousands of detection defects in these object detectors. To further demonstrate the practical usage of MetaOD, we use the synthetic images that cause erroneous detection results to retrain the model. Our results show that the model performance is increased significantly, from an mAP score of 9.3 to an mAP score of 10.5.
Tasks	Autonomous Driving, Object Detection
Published	2019-12-19
URL	https://arxiv.org/abs/1912.12162v1
PDF	https://arxiv.org/pdf/1912.12162v1.pdf
PWC	https://paperswithcode.com/paper/metamorphic-testing-for-object-detection
Repo
Framework

Deep Multi-Task Learning for Anomalous Driving Detection Using CAN Bus Scalar Sensor Data


Title	Deep Multi-Task Learning for Anomalous Driving Detection Using CAN Bus Scalar Sensor Data
Authors	Vidyasagar Sadhu, Teruhisa Misu, Dario Pompili
Abstract	Corner cases are the main bottlenecks when applying Artificial Intelligence (AI) systems to safety-critical applications. An AI system should be intelligent enough to detect such situations so that system developers can prepare for subsequent planning. In this paper, we propose semi-supervised anomaly detection considering the imbalance of normal situations. In particular, driving data consists of multiple positive/normal situations (e.g., right turn, going straight), some of which (e.g., U-turn) could be as rare as anomalous situations. Existing machine learning based anomaly detection approaches do not fare sufficiently well when applied to such imbalanced data. In this paper, we present a novel multi-task learning based approach that leverages domain-knowledge (maneuver labels) for anomaly detection in driving data. We evaluate the proposed approach both quantitatively and qualitatively on 150 hours of real-world driving data and show improved performance over baseline approaches.
Tasks	Anomaly Detection, Multi-Task Learning
Published	2019-06-28
URL	https://arxiv.org/abs/1907.00749v1
PDF	https://arxiv.org/pdf/1907.00749v1.pdf
PWC	https://paperswithcode.com/paper/deep-multi-task-learning-for-anomalous
Repo
Framework

Inferring linear and nonlinear Interaction networks using neighborhood support vector machines


Title	Inferring linear and nonlinear Interaction networks using neighborhood support vector machines
Authors	Kamel Jebreen, Badih Ghattas
Abstract	In this paper, we consider modelling interaction between a set of variables in the context of time series and high dimension. We suggest two approaches. The first is similar to the neighborhood lasso when the lasso model is replaced by a support vector machine (SVMs). The second is a restricted Bayesian network adapted for time series. We show the efficiency of our approaches by simulations using linear, nonlinear data set and a mixture of both.
Tasks	Time Series
Published	2019-08-02
URL	https://arxiv.org/abs/1908.00762v1
PDF	https://arxiv.org/pdf/1908.00762v1.pdf
PWC	https://paperswithcode.com/paper/inferring-linear-and-nonlinear-interaction
Repo
Framework

Channel Decomposition into Painting Actions


Title	Channel Decomposition into Painting Actions
Authors	Shih-Chieh Su
Abstract	This work presents a method to decompose a convolutional layer of the deep neural network into painting actions. To behave like the human painter, these actions are driven by the cost simulating the hand movement, the paint color change, the stroke shape and the stroking style. To help planning, the Mask R-CNN is applied to detect the object areas and decide the painting order. The proposed painting system introduces a variety of extensions in artistic styles, based on the chosen parameters. Further experiments are performed to evaluate the channel penetration and the channel sensitivity on the strokes.
Tasks
Published	2019-08-10
URL	https://arxiv.org/abs/1908.04694v4
PDF	https://arxiv.org/pdf/1908.04694v4.pdf
PWC	https://paperswithcode.com/paper/channel-decomposition-on-generative-networks
Repo
Framework

Can Monolingual Pretrained Models Help Cross-Lingual Classification?


Title	Can Monolingual Pretrained Models Help Cross-Lingual Classification?
Authors	Zewen Chi, Li Dong, Furu Wei, Xian-Ling Mao, Heyan Huang
Abstract	Multilingual pretrained language models (such as multilingual BERT) have achieved impressive results for cross-lingual transfer. However, due to the constant model capacity, multilingual pre-training usually lags behind the monolingual competitors. In this work, we present two approaches to improve zero-shot cross-lingual classification, by transferring the knowledge from monolingual pretrained models to multilingual ones. Experimental results on two cross-lingual classification benchmarks show that our methods outperform vanilla multilingual fine-tuning.
Tasks	Cross-Lingual Transfer
Published	2019-11-10
URL	https://arxiv.org/abs/1911.03913v1
PDF	https://arxiv.org/pdf/1911.03913v1.pdf
PWC	https://paperswithcode.com/paper/can-monolingual-pretrained-models-help-cross
Repo
Framework

Deep learning architectures for nonlinear operator functions and nonlinear inverse problems


Title	Deep learning architectures for nonlinear operator functions and nonlinear inverse problems
Authors	Maarten V. de Hoop, Matti Lassas, Christopher A. Wong
Abstract	We develop a theoretical analysis for special neural network architectures, termed operator recurrent neural networks, for approximating highly nonlinear functions whose inputs are linear operators. Such functions commonly arise in solution algorithms for inverse problems for the wave equation. Traditional neural networks treat input data as vectors, and thus they do not effectively capture the multiplicative structure associated with the linear operators that correspond to the measurement data in such inverse problems. We therefore introduce a new parametric family that resembles a standard neural network architecture, but where the input data acts multiplicatively on vectors. Motivated by compact operators appearing in boundary control and the analysis of inverse boundary value problems for the wave equation, we promote structure and sparsity in selected weight matrices in the network. After describing this architecture, we study its representation properties as well as its approximation properties. We furthermore show that an explicit regularization can be introduced that can be derived from the mathematical analysis of the mentioned inverse problems, and which leads to some guarantees on the generalization properties. We observe that the sparsity of the weight matrices improves the generalization estimates. Lastly, we discuss how operator recurrent networks can be viewed as a deep learning analogue to deterministic algorithms such as boundary control for reconstructing the unknown wavespeed in the acoustic wave equation from boundary measurements.
Tasks
Published	2019-12-23
URL	https://arxiv.org/abs/1912.11090v2
PDF	https://arxiv.org/pdf/1912.11090v2.pdf
PWC	https://paperswithcode.com/paper/deep-learning-architectures-for-nonlinear
Repo
Framework

Waiting but not Aging: Age-of-Information and Utility Optimization Under the Pull Model


Title	Waiting but not Aging: Age-of-Information and Utility Optimization Under the Pull Model
Authors	Fengjiao Li, Yu Sang, Zhongdong Liu, Bin Li, Huasen Wu, Bo Ji
Abstract	The Age-of-Information (AoI) has recently been proposed as an important metric for investigating the timeliness performance in information-update systems. In this paper, we introduce a new Pull model and study the AoI optimization problem under replication schemes. Interestingly, we find that under this new Pull model, replication schemes capture a novel tradeoff between different levels of information freshness and different response times across the servers, which can be exploited to minimize the expected AoI at the user’s side. Specifically, assuming Poisson updating process for the servers and exponentially distributed response time, we derive a closed-form formula for computing the expected AoI and obtain the optimal number of responses to wait for to minimize the expected AoI. Then, we extend our analysis to the setting where the user aims to maximize the AoI-based utility, which represents the user’s satisfaction level with respect to freshness of the received information. Furthermore, we consider a more realistic scenario where the user has no knowledge of the system. In this case, we reformulate the utility maximization problem as a stochastic Multi-Armed Bandit problem with side observations and leverage the unique structure of the problem to design learning algorithms with improved performance guarantees. Finally, we conduct extensive simulations to elucidate our theoretical results and compare the performance of different algorithms. Our findings reveal that under the Pull model, waiting for more than one response can significantly reduce the AoI and improve the AoI-based utility in most scenarios.
Tasks
Published	2019-12-17
URL	https://arxiv.org/abs/1912.08722v1
PDF	https://arxiv.org/pdf/1912.08722v1.pdf
PWC	https://paperswithcode.com/paper/waiting-but-not-aging-age-of-information-and
Repo
Framework

A Universal Logic Operator for Interpretable Deep Convolution Networks


Title	A Universal Logic Operator for Interpretable Deep Convolution Networks
Authors	KamWoh Ng, Lixin Fan, Chee Seng Chan
Abstract	Explaining neural network computation in terms of probabilistic/fuzzy logical operations has attracted much attention due to its simplicity and high interpretability. Different choices of logical operators such as AND, OR and XOR give rise to another dimension for network optimization, and in this paper, we study the open problem of learning a universal logical operator without prescribing to any logical operations manually. Insightful observations along this exploration furnish deep convolution networks with a novel logical interpretation.
Tasks
Published	2019-01-20
URL	http://arxiv.org/abs/1901.08551v1
PDF	http://arxiv.org/pdf/1901.08551v1.pdf
PWC	https://paperswithcode.com/paper/a-universal-logic-operator-for-interpretable
Repo
Framework

Barriers towards no-reference metrics application to compressed video quality analysis: on the example of no-reference metric NIQE


Title	Barriers towards no-reference metrics application to compressed video quality analysis: on the example of no-reference metric NIQE
Authors	Anastasia Zvezdakova, Dmitriy Kulikov, Denis Kondranin, Dmitriy Vatolin
Abstract	This paper analyses the application of no-reference metric NIQE to the task of video-codec comparison. A number of issues in the metric behaviour on videos was detected and described. The metric has outlying scores on black and solid-coloured frames. The proposed averaging technique for metric quality scores helped to improve the results in some cases. Also, NIQE has low-quality scores for videos with detailed textures and higher scores for videos of lower bitrates due to the blurring of these textures after compression. Although NIQE showed natural results for many tested videos, it is not universal and currently can not be used for video-codec comparisons.
Tasks
Published	2019-07-08
URL	https://arxiv.org/abs/1907.03842v2
PDF	https://arxiv.org/pdf/1907.03842v2.pdf
PWC	https://paperswithcode.com/paper/barriers-towards-no-reference-metrics
Repo
Framework

Backronym


Title	Backronym
Authors	Arip Asadulaev
Abstract	The field of Machine Learning research is divided into subject areas, where each area tries to solve a specific problem, using specific methods. In recent years, borders have almost been erased, and many areas inherit methods from other areas. This trend leads to better results and the number of papers in the field is growing every year. The problem is that the amount of information is also growing, and many methods remain unknown in a large number of papers. In this work, we propose the concept of inheritance between machine learning models, which allows conducting research, processing much less information, and pay attention to previously unnoticed models. We hope that this project will allow researchers to find ways to improve their ideas. In addition, it can be used by researchers to publish their methods too. Project is available by link: https://www.infornopolitan.xyz/backronym
Tasks
Published	2019-08-05
URL	https://arxiv.org/abs/1908.01874v3
PDF	https://arxiv.org/pdf/1908.01874v3.pdf
PWC	https://paperswithcode.com/paper/backronym
Repo
Framework

Learning a Static Bug Finder from Data


Title	Learning a Static Bug Finder from Data
Authors	Yu Wang, Fengjuan Gao, Linzhang Wang, Ke Wang
Abstract	We present an alternative approach to creating static bug finders. Instead of relying on human expertise, we utilize deep neural networks to train static analyzers directly from data. In particular, we frame the problem of bug finding as a classification task and train a classifier to differentiate the buggy from non-buggy programs using Graph Neural Network (GNN). Crucially, we propose a novel interval-based propagation mechanism that leads to a significantly more efficient, accurate and scalable generalization of GNN. We have realized our approach into a framework, NeurSA, and extensively evaluated it. In a cross-project prediction task, three neural bug detectors we instantiate from NeurSA are effective in catching null pointer dereference, array index out of bound and class cast bugs in unseen code. We compare NeurSA against several static analyzers (e.g. Facebook Infer and Pinpoint) on a set of null pointer dereference bugs. Results show that NeurSA is more precise in catching the real bugs and suppressing the spurious warnings. We also apply NeurSA to several popular Java projects on GitHub and discover 50 new bugs, among which 9 have been fixed, and 3 have been confirmed.
Tasks
Published	2019-07-12
URL	https://arxiv.org/abs/1907.05579v3
PDF	https://arxiv.org/pdf/1907.05579v3.pdf
PWC	https://paperswithcode.com/paper/learning-a-static-bug-finder-from-data
Repo
Framework

Machine learning approach to remove ion interference effect in agricultural nutrient solutions


Title	Machine learning approach to remove ion interference effect in agricultural nutrient solutions
Authors	Byunghyun Ban, Donghun Ryu, Minwoo Lee
Abstract	High concentration agricultural facilities such as vertical farms or plant factories consider hydroponic techniques as optimal solutions. Although closed-system dramatically reduces water consumption and pollution issues, it has ion-ratio related problem. As the root absorbs individual ions with different rate, ion rate in a nutrient solution should be adjusted periodically. But traditional method only considers pH and electrical conductivity to adjust the nutrient solution, leading to ion imbalance and accumulation of excessive salts. To avoid those problems, some researchers have proposed ion-balancing methods which measure and control each ion concentration. However, those approaches do not overcome the innate limitations of ISEs, especially ion interference effect. An anion sensor is affected by other anions, and the error grows larger in higher concentration solution. A machine learning approach to modify ISE data distorted by ion interference effect is proposed in this paper. As measurement of TDS value is relatively robust than any other signals, we applied TDS as key parameter to build a readjustment function to remove the artifact. Once a readjustment model is established, application on ISE data can be done in real time. Readjusted data with proposed model showed about 91.6 ~ 98.3% accuracies. This method will enable the fields to apply recent methods in feasible status.
Tasks
Published	2019-07-25
URL	https://arxiv.org/abs/1907.10794v4
PDF	https://arxiv.org/pdf/1907.10794v4.pdf
PWC	https://paperswithcode.com/paper/machine-learning-approach-to-remove-ion
Repo
Framework

Lattice-Based Unsupervised Test-Time Adaptation of Neural Network Acoustic Models


Title	Lattice-Based Unsupervised Test-Time Adaptation of Neural Network Acoustic Models
Authors	Ondrej Klejch, Joachim Fainberg, Peter Bell, Steve Renals
Abstract	Acoustic model adaptation to unseen test recordings aims to reduce the mismatch between training and testing conditions. Most adaptation schemes for neural network models require the use of an initial one-best transcription for the test data, generated by an unadapted model, in order to estimate the adaptation transform. It has been found that adaptation methods using discriminative objective functions - such as cross-entropy loss - often require careful regularisation to avoid over-fitting to errors in the one-best transcriptions. In this paper we solve this problem by performing discriminative adaptation using lattices obtained from a first pass decoding, an approach that can be readily integrated into the lattice-free maximum mutual information (LF-MMI) framework. We investigate this approach on three transcription tasks of varying difficulty: TED talks, multi-genre broadcast (MGB) and a low-resource language (Somali). We find that our proposed approach enables many more parameters to be adapted without over-fitting being observed, and is successful even when the initial transcription has a WER in excess of 50%.
Tasks
Published	2019-06-27
URL	https://arxiv.org/abs/1906.11521v1
PDF	https://arxiv.org/pdf/1906.11521v1.pdf
PWC	https://paperswithcode.com/paper/lattice-based-unsupervised-test-time
Repo
Framework

BioFaceNet: Deep Biophysical Face Image Interpretation


Title	BioFaceNet: Deep Biophysical Face Image Interpretation
Authors	Sarah Alotaibi, William Smith
Abstract	In this paper we present BioFaceNet, a deep CNN that learns to decompose a single face image into biophysical parameters maps, diffuse and specular shading maps as well as estimating the spectral power distribution of the scene illuminant and the spectral sensitivity of the camera. The network comprises a fully convolutional encoder for estimating the spatial maps with a fully connected branch for estimating the vector quantities. The network is trained using a self-supervised appearance loss computed via a model-based decoder. The task is highly underconstrained so we impose a number of model-based priors. Skin spectral reflectance is restricted to a biophysical model, we impose a statistical prior on camera spectral sensitivities, a physical constraint on illumination spectra, a sparsity prior on specular reflections and direct supervision on diffuse shading using a rough shape proxy. We show convincing qualitative results on in-the-wild data and introduce a benchmark for quantitative evaluation on this new task.
Tasks
Published	2019-08-28
URL	https://arxiv.org/abs/1908.10578v2
PDF	https://arxiv.org/pdf/1908.10578v2.pdf
PWC	https://paperswithcode.com/paper/biofacenet-deep-biophysical-face-image
Repo
Framework