January 27, 2020

2733 words 13 mins read

Paper Group ANR 1273

Experimental Study on CTL model checking using Machine Learning. SROBB: Targeted Perceptual Loss for Single Image Super-Resolution. DeepVIO: Self-supervised Deep Learning of Monocular Visual Inertial Odometry using 3D Geometric Constraints. Mitigating Noisy Inputs for Question Answering. Architecture Search of Dynamic Cells for Semantic Video Segme …

Experimental Study on CTL model checking using Machine Learning


Title	Experimental Study on CTL model checking using Machine Learning
Authors	Weijun ZHU
Abstract	The existing core methods, which are employed by the popular CTL model checking tools, are facing the famous state explode problem. In our previous study, a method based on the Machine Learning (ML) algorithms was proposed to address this problem. However, the accuracy is not satisfactory. First, we conduct a comprehensive experiment on Graph Lab to seek the optimal accuracy using the five machine learning algorithms. Second, given the optimal accuracy, the average time is seeked. The results show that the Logistic Regressive (LR)-based approach can simulate CTL model checking with the accuracy of 98.8%, and its average efficiency is 459 times higher than that of the existing method, as well as the Boosted Tree (BT)-based approach can simulate CTL model checking with the accuracy of 98.7%, and its average efficiency is 639 times higher than that of the existing method.
Tasks
Published	2019-02-23
URL	http://arxiv.org/abs/1902.08789v1
PDF	http://arxiv.org/pdf/1902.08789v1.pdf
PWC	https://paperswithcode.com/paper/experimental-study-on-ctl-model-checking
Repo
Framework

SROBB: Targeted Perceptual Loss for Single Image Super-Resolution


Title	SROBB: Targeted Perceptual Loss for Single Image Super-Resolution
Authors	Mohammad Saeed Rad, Behzad Bozorgtabar, Urs-Viktor Marti, Max Basler, Hazim Kemal Ekenel, Jean-Philippe Thiran
Abstract	By benefiting from perceptual losses, recent studies have improved significantly the performance of the super-resolution task, where a high-resolution image is resolved from its low-resolution counterpart. Although such objective functions generate near-photorealistic results, their capability is limited, since they estimate the reconstruction error for an entire image in the same way, without considering any semantic information. In this paper, we propose a novel method to benefit from perceptual loss in a more objective way. We optimize a deep network-based decoder with a targeted objective function that penalizes images at different semantic levels using the corresponding terms. In particular, the proposed method leverages our proposed OBB (Object, Background and Boundary) labels, generated from segmentation labels, to estimate a suitable perceptual loss for boundaries, while considering texture similarity for backgrounds. We show that our proposed approach results in more realistic textures and sharper edges, and outperforms other state-of-the-art algorithms in terms of both qualitative results on standard benchmarks and results of extensive user studies.
Tasks	Image Super-Resolution, Super-Resolution
Published	2019-08-20
URL	https://arxiv.org/abs/1908.07222v1
PDF	https://arxiv.org/pdf/1908.07222v1.pdf
PWC	https://paperswithcode.com/paper/srobb-targeted-perceptual-loss-for-single
Repo
Framework

DeepVIO: Self-supervised Deep Learning of Monocular Visual Inertial Odometry using 3D Geometric Constraints


Title	DeepVIO: Self-supervised Deep Learning of Monocular Visual Inertial Odometry using 3D Geometric Constraints
Authors	Liming Han, Yimin Lin, Guoguang Du, Shiguo Lian
Abstract	This paper presents an self-supervised deep learning network for monocular visual inertial odometry (named DeepVIO). DeepVIO provides absolute trajectory estimation by directly merging 2D optical flow feature (OFF) and Inertial Measurement Unit (IMU) data. Specifically, it firstly estimates the depth and dense 3D point cloud of each scene by using stereo sequences, and then obtains 3D geometric constraints including 3D optical flow and 6-DoF pose as supervisory signals. Note that such 3D optical flow shows robustness and accuracy to dynamic objects and textureless environments. In DeepVIO training, 2D optical flow network is constrained by the projection of its corresponding 3D optical flow, and LSTM-style IMU preintegration network and the fusion network are learned by minimizing the loss functions from ego-motion constraints. Furthermore, we employ an IMU status update scheme to improve IMU pose estimation through updating the additional gyroscope and accelerometer bias. The experimental results on KITTI and EuRoC datasets show that DeepVIO outperforms state-of-the-art learning based methods in terms of accuracy and data adaptability. Compared to the traditional methods, DeepVIO reduces the impacts of inaccurate Camera-IMU calibrations, unsynchronized and missing data.
Tasks	Optical Flow Estimation, Pose Estimation
Published	2019-06-27
URL	https://arxiv.org/abs/1906.11435v2
PDF	https://arxiv.org/pdf/1906.11435v2.pdf
PWC	https://paperswithcode.com/paper/deepvio-self-supervised-deep-learning-of
Repo
Framework

Mitigating Noisy Inputs for Question Answering


Title	Mitigating Noisy Inputs for Question Answering
Authors	Denis Peskov, Joe Barrow, Pedro Rodriguez, Graham Neubig, Jordan Boyd-Graber
Abstract	Natural language processing systems are often downstream of unreliable inputs: machine translation, optical character recognition, or speech recognition. For instance, virtual assistants can only answer your questions after understanding your speech. We investigate and mitigate the effects of noise from Automatic Speech Recognition systems on two factoid Question Answering (QA) tasks. Integrating confidences into the model and forced decoding of unknown words are empirically shown to improve the accuracy of downstream neural QA systems. We create and train models on a synthetic corpus of over 500,000 noisy sentences and evaluate on two human corpora from Quizbowl and Jeopardy! competitions.
Tasks	Machine Translation, Optical Character Recognition, Question Answering, Speech Recognition
Published	2019-08-08
URL	https://arxiv.org/abs/1908.02914v1
PDF	https://arxiv.org/pdf/1908.02914v1.pdf
PWC	https://paperswithcode.com/paper/mitigating-noisy-inputs-for-question
Repo
Framework

Architecture Search of Dynamic Cells for Semantic Video Segmentation


Title	Architecture Search of Dynamic Cells for Semantic Video Segmentation
Authors	Vladimir Nekrasov, Hao Chen, Chunhua Shen, Ian Reid
Abstract	In semantic video segmentation the goal is to acquire consistent dense semantic labelling across image frames. To this end, recent approaches have been reliant on manually arranged operations applied on top of static semantic segmentation networks - with the most prominent building block being the optical flow able to provide information about scene dynamics. Related to that is the line of research concerned with speeding up static networks by approximating expensive parts of them with cheaper alternatives, while propagating information from previous frames. In this work we attempt to come up with generalisation of those methods, and instead of manually designing contextual blocks that connect per-frame outputs, we propose a neural architecture search solution, where the choice of operations together with their sequential arrangement are being predicted by a separate neural network. We showcase that such generalisation leads to stable and accurate results across common benchmarks, such as CityScapes and CamVid datasets. Importantly, the proposed methodology takes only 2 GPU-days, finds high-performing cells and does not rely on the expensive optical flow computation.
Tasks	Neural Architecture Search, Optical Flow Estimation, Semantic Segmentation, Video Semantic Segmentation
Published	2019-04-04
URL	http://arxiv.org/abs/1904.02371v1
PDF	http://arxiv.org/pdf/1904.02371v1.pdf
PWC	https://paperswithcode.com/paper/architecture-search-of-dynamic-cells-for
Repo
Framework

Entity-Centric Contextual Affective Analysis


Title	Entity-Centric Contextual Affective Analysis
Authors	Anjalie Field, Yulia Tsvetkov
Abstract	While contextualized word representations have improved state-of-the-art benchmarks in many NLP tasks, their potential usefulness for social-oriented tasks remains largely unexplored. We show how contextualized word embeddings can be used to capture affect dimensions in portrayals of people. We evaluate our methodology quantitatively, on held-out affect lexicons, and qualitatively, through case examples. We find that contextualized word representations do encode meaningful affect information, but they are heavily biased towards their training data, which limits their usefulness to in-domain analyses. We ultimately use our method to examine differences in portrayals of men and women.
Tasks	Word Embeddings
Published	2019-06-05
URL	https://arxiv.org/abs/1906.01762v1
PDF	https://arxiv.org/pdf/1906.01762v1.pdf
PWC	https://paperswithcode.com/paper/entity-centric-contextual-affective-analysis
Repo
Framework

Learning to Clear the Market


Title	Learning to Clear the Market
Authors	Weiran Shen, Sébastien Lahaie, Renato Paes Leme
Abstract	The problem of market clearing is to set a price for an item such that quantity demanded equals quantity supplied. In this work, we cast the problem of predicting clearing prices into a learning framework and use the resulting models to perform revenue optimization in auctions and markets with contextual information. The economic intuition behind market clearing allows us to obtain fine-grained control over the aggressiveness of the resulting pricing policy, grounded in theory. To evaluate our approach, we fit a model of clearing prices over a massive dataset of bids in display ad auctions from a major ad exchange. The learned prices outperform other modeling techniques in the literature in terms of revenue and efficiency trade-offs. Because of the convex nature of the clearing loss function, the convergence rate of our method is as fast as linear regression.
Tasks
Published	2019-06-04
URL	https://arxiv.org/abs/1906.01184v2
PDF	https://arxiv.org/pdf/1906.01184v2.pdf
PWC	https://paperswithcode.com/paper/learning-to-clear-the-market
Repo
Framework

NTT’s Machine Translation Systems for WMT19 Robustness Task


Title	NTT’s Machine Translation Systems for WMT19 Robustness Task
Authors	Soichiro Murakami, Makoto Morishita, Tsutomu Hirao, Masaaki Nagata
Abstract	This paper describes NTT’s submission to the WMT19 robustness task. This task mainly focuses on translating noisy text (e.g., posts on Twitter), which presents different difficulties from typical translation tasks such as news. Our submission combined techniques including utilization of a synthetic corpus, domain adaptation, and a placeholder mechanism, which significantly improved over the previous baseline. Experimental results revealed the placeholder mechanism, which temporarily replaces the non-standard tokens including emojis and emoticons with special placeholder tokens during translation, improves translation accuracy even with noisy texts.
Tasks	Domain Adaptation, Machine Translation
Published	2019-07-09
URL	https://arxiv.org/abs/1907.03927v1
PDF	https://arxiv.org/pdf/1907.03927v1.pdf
PWC	https://paperswithcode.com/paper/ntts-machine-translation-systems-for-wmt19
Repo
Framework

Model Explanations under Calibration


Title	Model Explanations under Calibration
Authors	Rishabh Jain, Pranava Madhyastha
Abstract	Explaining and interpreting the decisions of recommender systems are becoming extremely relevant both, for improving predictive performance, and providing valid explanations to users. While most of the recent interest has focused on providing local explanations, there has been a much lower emphasis on studying the effects of model dynamics and its impact on explanation. In this paper, we perform a focused study on the impact of model interpretability in the context of calibration. Specifically, we address the challenges of both over-confident and under-confident predictions with interpretability using attention distribution. Our results indicate that the means of using attention distributions for interpretability are highly unstable for un-calibrated models. Our empirical analysis on the stability of attention distribution raises questions on the utility of attention for explainability.
Tasks	Calibration, Recommendation Systems
Published	2019-06-18
URL	https://arxiv.org/abs/1906.07622v1
PDF	https://arxiv.org/pdf/1906.07622v1.pdf
PWC	https://paperswithcode.com/paper/model-explanations-under-calibration
Repo
Framework

Covariance and Correlation Kernels on a Graph in the Generalized Bag-of-Paths Formalism


Title	Covariance and Correlation Kernels on a Graph in the Generalized Bag-of-Paths Formalism
Authors	Guillaume Guex, Sylvain Courtain, Marco Saerens
Abstract	This work derives closed-form expressions computing the expectation of co-presence and of number of co-occurrences of nodes on paths sampled from a network according to general path weights (a bag of paths). The underlying idea is that two nodes are considered as similar when they often appear together on (preferably short) paths of the network. The different expressions are obtained for both regular and hitting paths and serve as a basis for computing new covariance and correlation measures between nodes, which are valid positive semi-definite kernels on a graph. Experiments on semi-supervised classification problems show that the introduced similarity measures provide competitive results compared to other state-of-the-art distance and similarity measures between nodes.
Tasks
Published	2019-02-08
URL	https://arxiv.org/abs/1902.03002v4
PDF	https://arxiv.org/pdf/1902.03002v4.pdf
PWC	https://paperswithcode.com/paper/covariance-and-correlation-kernels-on-a-graph
Repo
Framework

Semi-Unsupervised Learning: Clustering and Classifying using Ultra-Sparse Labels


Title	Semi-Unsupervised Learning: Clustering and Classifying using Ultra-Sparse Labels
Authors	Matthew Willetts, Stephen J Roberts, Christopher C Holmes
Abstract	In semi-supervised learning for classification, it is assumed that every ground truth class of data is present in the small labelled dataset. Many real-world sparsely-labelled datasets are plausibly not of this type. It could easily be the case that some classes of data are found only in the unlabelled dataset – perhaps the labelling process was biased – so we do not have any labelled examples to train on for some classes. We call this learning regime semi-unsupervised learning, an extreme case of semi-supervised learning, where some classes have no labelled exemplars in the training set. First, we outline the pitfalls associated with trying to apply deep generative model (DGM)-based semi-supervised learning algorithms to datasets of this type. We then show how a combination of clustering and semi-supervised learning, using DGMs, can be brought to bear on this problem. We study several different datasets, showing how one can still learn effectively when half of the ground truth classes are entirely unlabelled and the other half are sparsely labelled.
Tasks
Published	2019-01-24
URL	https://arxiv.org/abs/1901.08560v2
PDF	https://arxiv.org/pdf/1901.08560v2.pdf
PWC	https://paperswithcode.com/paper/semi-unsupervised-learning-with-deep
Repo
Framework

Towards Robust, Locally Linear Deep Networks


Title	Towards Robust, Locally Linear Deep Networks
Authors	Guang-He Lee, David Alvarez-Melis, Tommi S. Jaakkola
Abstract	Deep networks realize complex mappings that are often understood by their locally linear behavior at or around points of interest. For example, we use the derivative of the mapping with respect to its inputs for sensitivity analysis, or to explain (obtain coordinate relevance for) a prediction. One key challenge is that such derivatives are themselves inherently unstable. In this paper, we propose a new learning problem to encourage deep networks to have stable derivatives over larger regions. While the problem is challenging in general, we focus on networks with piecewise linear activation functions. Our algorithm consists of an inference step that identifies a region around a point where linear approximation is provably stable, and an optimization step to expand such regions. We propose a novel relaxation to scale the algorithm to realistic models. We illustrate our method with residual and recurrent networks on image and sequence datasets.
Tasks
Published	2019-07-07
URL	https://arxiv.org/abs/1907.03207v1
PDF	https://arxiv.org/pdf/1907.03207v1.pdf
PWC	https://paperswithcode.com/paper/towards-robust-locally-linear-deep-networks-1
Repo
Framework

Lexical Learning as an Online Optimal Experiment: Building Efficient Search Engines through Human-Machine Collaboration


Title	Lexical Learning as an Online Optimal Experiment: Building Efficient Search Engines through Human-Machine Collaboration
Authors	Jacopo Tagliabue, Reuben Cohn-Gordon
Abstract	Information retrieval (IR) systems need to constantly update their knowledge as target objects and user queries change over time. Due to the power-law nature of linguistic data, learning lexical concepts is a problem resisting standard machine learning approaches: while manual intervention is always possible, a more general and automated solution is desirable. In this work, we propose a novel end-to-end framework that models the interaction between a search engine and users as a virtuous human-in-the-loop inference. The proposed framework is the first to our knowledge combining ideas from psycholinguistics and experiment design to maximize efficiency in IR. We provide a brief overview of the main components and initial simulations in a toy world, showing how inference works end-to-end and discussing preliminary results and next steps.
Tasks	Information Retrieval
Published	2019-10-30
URL	https://arxiv.org/abs/1910.14164v1
PDF	https://arxiv.org/pdf/1910.14164v1.pdf
PWC	https://paperswithcode.com/paper/lexical-learning-as-an-online-optimal
Repo
Framework

Robustly Clustering a Mixture of Gaussians


Title	Robustly Clustering a Mixture of Gaussians
Authors	He Jia, Santosh Vempala
Abstract	We give an efficient algorithm for robustly clustering of a mixture of two arbitrary Gaussians, a central open problem in the theory of computationally efficient robust estimation, assuming only that the the means of the component Gaussian are well-separated or their covariances are well-separated. Our algorithm and analysis extend naturally to robustly clustering mixtures of well-separated logconcave distributions. The mean separation required is close to the smallest possible to guarantee that most of the measure of the component Gaussians can be separated by some hyperplane (for covariances, it is the same condition in the second degree polynomial kernel). Our main tools are a new identifiability criterion based on isotropic position and the Fisher discriminant, and a corresponding Sum-of-Squares convex programming relaxation.
Tasks
Published	2019-11-26
URL	https://arxiv.org/abs/1911.11838v3
PDF	https://arxiv.org/pdf/1911.11838v3.pdf
PWC	https://paperswithcode.com/paper/robustly-clustering-a-mixture-of-gaussians
Repo
Framework

Feedbackward Decoding for Semantic Segmentation


Title	Feedbackward Decoding for Semantic Segmentation
Authors	Beinan Wang, John Glossner, Daniel Iancu, Georgi N. Gaydadjiev
Abstract	We propose a novel approach for semantic segmentation that uses an encoder in the reverse direction to decode. Many semantic segmentation networks adopt a feedforward encoder-decoder architecture. Typically, an input is first downsampled by the encoder to extract high-level semantic features and continues to be fed forward through the decoder module to recover low-level spatial clues. Our method works in an alternative direction that lets information flow backward from the last layer of the encoder towards the first. The encoder performs encoding in the forward pass and the same network performs decoding in the backward pass. Therefore, the encoder itself is also the decoder. Compared to conventional encoder-decoder architectures, ours doesn’t require additional layers for decoding and further reuses the encoder weights thereby reducing the total number of parameters required for processing. We show by using only the 13 convolutional layers from VGG-16 plus one tiny classification layer, our model significantly outperforms other frequently cited models that are also adapted from VGG-16. On the Cityscapes semantic segmentation benchmark, our model uses 50.0% less parameters than SegNet and achieves an 18.1% higher “IoU class” score; it uses 28.3% less parameters than DeepLab LargeFOV and the achieved “IoU class” score is 3.9% higher; it uses 89.1% fewer parameters than FCN-8s and the achieved “IoU class” score is 3.1% higher. Our code will be publicly available on Github later.
Tasks	Semantic Segmentation
Published	2019-08-22
URL	https://arxiv.org/abs/1908.08584v1
PDF	https://arxiv.org/pdf/1908.08584v1.pdf
PWC	https://paperswithcode.com/paper/feedbackward-decoding-for-semantic
Repo
Framework