January 28, 2020

3152 words 15 mins read

Paper Group ANR 918

The Best of Both Modes: Separately Leveraging RGB and Depth for Unseen Object Instance Segmentation. Unsupervised Linear and Nonlinear Channel Equalization and Decoding using Variational Autoencoders. Information-Theoretic Generalization Bounds for SGLD via Data-Dependent Estimates. Improving Fine-grained Entity Typing with Entity Linking. A Parame …

The Best of Both Modes: Separately Leveraging RGB and Depth for Unseen Object Instance Segmentation


Title	The Best of Both Modes: Separately Leveraging RGB and Depth for Unseen Object Instance Segmentation
Authors	Christopher Xie, Yu Xiang, Arsalan Mousavian, Dieter Fox
Abstract	In order to function in unstructured environments, robots need the ability to recognize unseen novel objects. We take a step in this direction by tackling the problem of segmenting unseen object instances in tabletop environments. However, the type of large-scale real-world dataset required for this task typically does not exist for most robotic settings, which motivates the use of synthetic data. We propose a novel method that separately leverages synthetic RGB and synthetic depth for unseen object instance segmentation. Our method is comprised of two stages where the first stage operates only on depth to produce rough initial masks, and the second stage refines these masks with RGB. Surprisingly, our framework is able to learn from synthetic RGB-D data where the RGB is non-photorealistic. To train our method, we introduce a large-scale synthetic dataset of random objects on tabletops. We show that our method, trained on this dataset, can produce sharp and accurate masks, outperforming state-of-the-art methods on unseen object instance segmentation. We also show that our method can segment unseen objects for robot grasping. Code, models and video can be found at https://rse-lab.cs.washington.edu/projects/unseen-object-instance-segmentation/.
Tasks	Instance Segmentation, Semantic Segmentation
Published	2019-07-30
URL	https://arxiv.org/abs/1907.13236v1
PDF	https://arxiv.org/pdf/1907.13236v1.pdf
PWC	https://paperswithcode.com/paper/the-best-of-both-modes-separately-leveraging
Repo
Framework

Unsupervised Linear and Nonlinear Channel Equalization and Decoding using Variational Autoencoders


Title	Unsupervised Linear and Nonlinear Channel Equalization and Decoding using Variational Autoencoders
Authors	Avi Caciularu, David Burshtein
Abstract	A new approach for blind channel equalization and decoding, using variational autoencoders (VAEs), is introduced. We first consider the reconstruction of uncoded data symbols transmitted over a noisy linear intersymbol interference (ISI) channel, with an unknown impulse response, without using pilot symbols. We derive an approximated maximum likelihood estimate to the channel parameters and reconstruct the transmitted data. We demonstrate significant and consistent improvements in the error rate of the reconstructed symbols, compared to existing blind equalization methods such as constant modulus, thus enabling faster channel acquisition. The VAE equalizer uses a fully convolutional neural network with a small number of free parameters. These results are extended to blind equalization over a noisy nonlinear ISI channel with unknown parameters. We then consider coded communication using low-density parity-check (LDPC) codes transmitted over a noisy linear or nonlinear ISI channel. The goal is to reconstruct the transmitted message from the channel observations corresponding to a transmitted codeword, without using pilot symbols. We demonstrate substantial improvements compared to expectation maximization (EM) using turbo equalization. Furthermore, in our simulations we demonstrate a relatively small gap between the performance of the new unsupervised equalization method and that of the fully channel informed (non-blind) turbo equalizer.
Tasks
Published	2019-05-21
URL	https://arxiv.org/abs/1905.08795v1
PDF	https://arxiv.org/pdf/1905.08795v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-linear-and-nonlinear-channel
Repo
Framework

Information-Theoretic Generalization Bounds for SGLD via Data-Dependent Estimates


Title	Information-Theoretic Generalization Bounds for SGLD via Data-Dependent Estimates
Authors	Jeffrey Negrea, Mahdi Haghifam, Gintare Karolina Dziugaite, Ashish Khisti, Daniel M. Roy
Abstract	In this work, we improve upon the stepwise analysis of noisy iterative learning algorithms initiated by Pensia, Jog, and Loh (2018) and recently extended by Bu, Zou, and Veeravalli (2019). Our main contributions are significantly improved mutual information bounds for Stochastic Gradient Langevin Dynamics via data-dependent estimates. Our approach is based on the variational characterization of mutual information and the use of data-dependent priors that forecast the mini-batch gradient based on a subset of the training samples. Our approach is broadly applicable within the information-theoretic framework of Russo and Zou (2015) and Xu and Raginsky (2017). Our bound can be tied to a measure of flatness of the empirical risk surface. As compared with other bounds that depend on the squared norms of gradients, empirical investigations show that the terms in our bounds are orders of magnitude smaller.
Tasks
Published	2019-11-06
URL	https://arxiv.org/abs/1911.02151v3
PDF	https://arxiv.org/pdf/1911.02151v3.pdf
PWC	https://paperswithcode.com/paper/information-theoretic-generalization-bounds
Repo
Framework

Improving Fine-grained Entity Typing with Entity Linking


Title	Improving Fine-grained Entity Typing with Entity Linking
Authors	Hongliang Dai, Donghong Du, Xin Li, Yangqiu Song
Abstract	Fine-grained entity typing is a challenging problem since it usually involves a relatively large tag set and may require to understand the context of the entity mention. In this paper, we use entity linking to help with the fine-grained entity type classification process. We propose a deep neural model that makes predictions based on both the context and the information obtained from entity linking results. Experimental results on two commonly used datasets demonstrates the effectiveness of our approach. On both datasets, it achieves more than 5% absolute strict accuracy improvement over the state of the art.
Tasks	Entity Linking, Entity Typing
Published	2019-09-26
URL	https://arxiv.org/abs/1909.12079v1
PDF	https://arxiv.org/pdf/1909.12079v1.pdf
PWC	https://paperswithcode.com/paper/improving-fine-grained-entity-typing-with
Repo
Framework

A Parameterized Perspective on Protecting Elections


Title	A Parameterized Perspective on Protecting Elections
Authors	Palash Dey, Neeldhara Misra, Swaprava Nath, Garima Shakya
Abstract	We study the parameterized complexity of the optimal defense and optimal attack problems in voting. In both the problems, the input is a set of voter groups (every voter group is a set of votes) and two integers $k_a$ and $k_d$ corresponding to respectively the number of voter groups the attacker can attack and the number of voter groups the defender can defend. A voter group gets removed from the election if it is attacked but not defended. In the optimal defense problem, we want to know if it is possible for the defender to commit to a strategy of defending at most $k_d$ voter groups such that, no matter which $k_a$ voter groups the attacker attacks, the outcome of the election does not change. In the optimal attack problem, we want to know if it is possible for the attacker to commit to a strategy of attacking $k_a$ voter groups such that, no matter which $k_d$ voter groups the defender defends, the outcome of the election is always different from the original (without any attack) one.
Tasks
Published	2019-05-28
URL	https://arxiv.org/abs/1905.11838v1
PDF	https://arxiv.org/pdf/1905.11838v1.pdf
PWC	https://paperswithcode.com/paper/a-parameterized-perspective-on-protecting
Repo
Framework

Robust commuter movement inference from connected mobile devices


Title	Robust commuter movement inference from connected mobile devices
Authors	Baoyang Song, Hasan Poonawala, Laura Wynter, Sebastien Blandin
Abstract	The preponderance of connected devices provides unprecedented opportunities for fine-grained monitoring of the public infrastructure. However while classical models expect high quality application-specific data streams, the promise of the Internet of Things (IoT) is that of an abundance of disparate and noisy datasets from connected devices. In this context, we consider the problem of estimation of the level of service of a city-wide public transport network. We first propose a robust unsupervised model for train movement inference from wifi traces, via the application of robust clustering methods to a one dimensional spatio-temporal setting. We then explore the extent to which the demand-supply gap can be estimated from connected devices. We propose a classification model of real-time commuter patterns, including both a batch training phase and an online learning component. We describe our deployment architecture and assess our system accuracy on a large-scale anonymized dataset comprising more than 10 billion records.
Tasks
Published	2019-03-04
URL	http://arxiv.org/abs/1903.01045v1
PDF	http://arxiv.org/pdf/1903.01045v1.pdf
PWC	https://paperswithcode.com/paper/robust-commuter-movement-inference-from
Repo
Framework

MoBiNet: A Mobile Binary Network for Image Classification


Title	MoBiNet: A Mobile Binary Network for Image Classification
Authors	Hai Phan, Dang Huynh, Yihui He, Marios Savvides, Zhiqiang Shen
Abstract	MobileNet and Binary Neural Networks are two among the most widely used techniques to construct deep learning models for performing a variety of tasks on mobile and embedded platforms.In this paper, we present a simple yet efficient scheme to exploit MobileNet binarization at activation function and model weights. However, training a binary network from scratch with separable depth-wise and point-wise convolutions in case of MobileNet is not trivial and prone to divergence. To tackle this training issue, we propose a novel neural network architecture, namely MoBiNet - Mobile Binary Network in which skip connections are manipulated to prevent information loss and vanishing gradient, thus facilitate the training process. More importantly, while existing binary neural networks often make use of cumbersome backbones such as Alex-Net, ResNet, VGG-16 with float-type pre-trained weights initialization, our MoBiNet focuses on binarizing the already-compressed neural networks like MobileNet without the need of a pre-trained model to start with. Therefore, our proposal results in an effectively small model while keeping the accuracy comparable to existing ones. Experiments on ImageNet dataset show the potential of the MoBiNet as it achieves 54.40% top-1 accuracy and dramatically reduces the computational cost with binary operators.
Tasks	Image Classification
Published	2019-07-29
URL	https://arxiv.org/abs/1907.12629v2
PDF	https://arxiv.org/pdf/1907.12629v2.pdf
PWC	https://paperswithcode.com/paper/mobinet-a-mobile-binary-network-for-image
Repo
Framework

Syntax-Enhanced Neural Machine Translation with Syntax-Aware Word Representations


Title	Syntax-Enhanced Neural Machine Translation with Syntax-Aware Word Representations
Authors	Meishan Zhang, Zhenghua Li, Guohong Fu, Min Zhang
Abstract	Syntax has been demonstrated highly effective in neural machine translation (NMT). Previous NMT models integrate syntax by representing 1-best tree outputs from a well-trained parsing system, e.g., the representative Tree-RNN and Tree-Linearization methods, which may suffer from error propagation. In this work, we propose a novel method to integrate source-side syntax implicitly for NMT. The basic idea is to use the intermediate hidden representations of a well-trained end-to-end dependency parser, which are referred to as syntax-aware word representations (SAWRs). Then, we simply concatenate such SAWRs with ordinary word embeddings to enhance basic NMT models. The method can be straightforwardly integrated into the widely-used sequence-to-sequence (Seq2Seq) NMT models. We start with a representative RNN-based Seq2Seq baseline system, and test the effectiveness of our proposed method on two benchmark datasets of the Chinese-English and English-Vietnamese translation tasks, respectively. Experimental results show that the proposed approach is able to bring significant BLEU score improvements on the two datasets compared with the baseline, 1.74 points for Chinese-English translation and 0.80 point for English-Vietnamese translation, respectively. In addition, the approach also outperforms the explicit Tree-RNN and Tree-Linearization methods.
Tasks	Machine Translation, Word Embeddings
Published	2019-05-08
URL	https://arxiv.org/abs/1905.02878v1
PDF	https://arxiv.org/pdf/1905.02878v1.pdf
PWC	https://paperswithcode.com/paper/syntax-enhanced-neural-machine-translation
Repo
Framework

Investigating Wave Energy Potential in Southern Coasts of the Caspian Sea and Evaluating the Application of Gray Wolf Optimizer Algorithm


Title	Investigating Wave Energy Potential in Southern Coasts of the Caspian Sea and Evaluating the Application of Gray Wolf Optimizer Algorithm
Authors	Erfan Amini, Sayyed Taghi Omid Naeeni, Pedram Ghaderi
Abstract	There is a significantly accelerating trend in the application of the wave energy converters. As a result, it is imperative to adopt a suitable point for implementing these systems. Besides, the Caspian Sea, as one of the most important marine renewable energy sources in Asia, is capable of supplying the coastal areas with a large amount of energy. Therefore, areas around nine ports in the southern coasts of the Caspian Sea were selected to measure their wave energy potential. Initially, the amount of energy on these points was measured using the irregular energy theory. A new approach was developed to compare these points and measure their fitness in supplying the maximum energy using the Grey Wolf optimizer (GWO) algorithm and time history analysis. In this method, the optimal parameters were first extracted from the algorithm for assessing the points within the southern areas of the Caspian Sea. These values were regarded as the assessment indices. Then, the fitness of each point was obtained using the correlation function and the norm vector to present the most optimal point with maximum waver energy exploitation potential. Finally, the side-by-side comparison of the parameters affecting the wave energy showed that an increase or decrease in the wave energy along the southern areas of the Caspian Sea is influenced more by the wave height than the depth on that points. Moreover, the waver energy concentration occurs in the range of Hs = 3 and $T_e$ range is between $0.75\times T_{e_{max}}$ and $0.85\times T_{e_{max}}$.
Tasks
Published	2019-12-31
URL	https://arxiv.org/abs/1912.13201v1
PDF	https://arxiv.org/pdf/1912.13201v1.pdf
PWC	https://paperswithcode.com/paper/investigating-wave-energy-potential-in
Repo
Framework

Failure-Scenario Maker for Rule-Based Agent using Multi-agent Adversarial Reinforcement Learning and its Application to Autonomous Driving


Title	Failure-Scenario Maker for Rule-Based Agent using Multi-agent Adversarial Reinforcement Learning and its Application to Autonomous Driving
Authors	Akifumi Wachi
Abstract	We examine the problem of adversarial reinforcement learning for multi-agent domains including a rule-based agent. Rule-based algorithms are required in safety-critical applications for them to work properly in a wide range of situations. Hence, every effort is made to find failure scenarios during the development phase. However, as the software becomes complicated, finding failure cases becomes difficult. Especially in multi-agent domains, such as autonomous driving environments, it is much harder to find useful failure scenarios that help us improve the algorithm. We propose a method for efficiently finding failure scenarios; this method trains the adversarial agents using multi-agent reinforcement learning such that the tested rule-based agent fails. We demonstrate the effectiveness of our proposed method using a simple environment and autonomous driving simulator.
Tasks	Autonomous Driving, Multi-agent Reinforcement Learning
Published	2019-03-26
URL	https://arxiv.org/abs/1903.10654v3
PDF	https://arxiv.org/pdf/1903.10654v3.pdf
PWC	https://paperswithcode.com/paper/failure-scenario-maker-for-rule-based-agent
Repo
Framework

Single-Net Continual Learning with Progressive Segmented Training (PST)


Title	Single-Net Continual Learning with Progressive Segmented Training (PST)
Authors	Xiaocong Du, Gouranga Charan, Frank Liu, Yu Cao
Abstract	There is an increasing need of continual learning in dynamic systems, such as the self-driving vehicle, the surveillance drone, and the robotic system. Such a system requires learning from the data stream, training the model to preserve previous information and adapt to a new task, and generating a single-headed vector for future inference. Different from previous approaches with dynamic structures, this work focuses on a single network and model segmentation to prevent catastrophic forgetting. Leveraging the redundant capacity of a single network, model parameters for each task are separated into two groups: one important group which is frozen to preserve current knowledge, and secondary group to be saved (not pruned) for a future learning. A fixed-size memory containing a small amount of previously seen data is further adopted to assist the training. Without additional regularization, the simple yet effective approach of PST successfully incorporates multiple tasks and achieves the state-of-the-art accuracy in the single-head evaluation on CIFAR-10 and CIFAR-100 datasets. Moreover, the segmented training significantly improves computation efficiency in continual learning.
Tasks	Continual Learning
Published	2019-05-28
URL	https://arxiv.org/abs/1905.11550v4
PDF	https://arxiv.org/pdf/1905.11550v4.pdf
PWC	https://paperswithcode.com/paper/single-net-continual-learning-with
Repo
Framework

Handwritten and Machine printed OCR for Geez Numbers Using Artificial Neural Network


Title	Handwritten and Machine printed OCR for Geez Numbers Using Artificial Neural Network
Authors	Eyob Gebretinsae Beyene
Abstract	Researches have been done on Ethiopic scripts. However studies excluded the Geez numbers from the studies because of different reasons. This paper presents offline handwritten and machine printed Geez number recognition using feed forward back propagation artificial neural network. On this study, different Geez image characters were collected from google image search and three persons are instructed to write the numbers using pencil. In total we have collected 560 numbers of characters. We have used 460 of the characters for training and 100 are used for testing. Accordingly we have achieved overall all classification ~89:88%
Tasks	Image Retrieval, Optical Character Recognition
Published	2019-11-15
URL	https://arxiv.org/abs/1911.06845v1
PDF	https://arxiv.org/pdf/1911.06845v1.pdf
PWC	https://paperswithcode.com/paper/handwritten-and-machine-printed-ocr-for-geez
Repo
Framework

Semi-Supervised Multi-Task Learning With Chest X-Ray Images


Title	Semi-Supervised Multi-Task Learning With Chest X-Ray Images
Authors	Abdullah-Al-Zubaer Imran, Demetri Terzopoulos
Abstract	Discriminative models that require full supervision are inefficacious in the medical imaging domain when large labeled datasets are unavailable. By contrast, generative modeling—i.e., learning data generation and classification—facilitates semi-supervised training with limited labeled data. Moreover, generative modeling can be advantageous in accomplishing multiple objectives for better generalization. We propose a novel multi-task learning model for jointly learning a classifier and a segmentor, from chest X-ray images, through semi-supervised learning. In addition, we propose a new loss function that combines absolute KL divergence with Tversky loss (KLTV) to yield faster convergence and better segmentation performance. Based on our experimental results using a novel segmentation model, an Adversarial Pyramid Progressive Attention U-Net (APPAU-Net), we hypothesize that KLTV can be more effective for generalizing multi-tasking models while being competitive in segmentation-only tasks.
Tasks	Multi-Task Learning
Published	2019-08-10
URL	https://arxiv.org/abs/1908.03693v2
PDF	https://arxiv.org/pdf/1908.03693v2.pdf
PWC	https://paperswithcode.com/paper/semi-supervised-multi-task-learning-with
Repo
Framework

What is the dimension of your binary data?


Title	What is the dimension of your binary data?
Authors	Nikolaj Tatti, Taneli Mielikainen, Aristides Gionis, Heikki Mannila
Abstract	Many 0/1 datasets have a very large number of variables; on the other hand, they are sparse and the dependency structure of the variables is simpler than the number of variables would suggest. Defining the effective dimensionality of such a dataset is a nontrivial problem. We consider the problem of defining a robust measure of dimension for 0/1 datasets, and show that the basic idea of fractal dimension can be adapted for binary data. However, as such the fractal dimension is difficult to interpret. Hence we introduce the concept of normalized fractal dimension. For a dataset $D$, its normalized fractal dimension is the number of columns in a dataset $D'$ with independent columns and having the same (unnormalized) fractal dimension as $D$. The normalized fractal dimension measures the degree of dependency structure of the data. We study the properties of the normalized fractal dimension and discuss its computation. We give empirical results on the normalized fractal dimension, comparing it against baseline measures such as PCA. We also study the relationship of the dimension of the whole dataset and the dimensions of subgroups formed by clustering. The results indicate interesting differences between and within datasets.
Tasks
Published	2019-02-04
URL	http://arxiv.org/abs/1902.01480v1
PDF	http://arxiv.org/pdf/1902.01480v1.pdf
PWC	https://paperswithcode.com/paper/what-is-the-dimension-of-your-binary-data
Repo
Framework

Sentiment and position-taking analysis of parliamentary debates: A systematic literature review


Title	Sentiment and position-taking analysis of parliamentary debates: A systematic literature review
Authors	Gavin Abercrombie, Riza Batista-Navarro
Abstract	Parliamentary and legislative debate transcripts provide access to information concerning the opinions, positions and policy preferences of elected politicians. They attract attention from researchers from a wide variety of backgrounds, from political and social sciences to computer science. As a result, the problem of automatic sentiment and position-taking analysis has been tackled from different perspectives, using varying approaches and methods, and with relatively little collaboration or cross-pollination of ideas. The existing research is scattered across publications from various fields and venues. In this article we present the results of a systematic literature review of 61 studies, all of which address the automatic analysis of the sentiment and opinions expressed and positions taken by speakers in parliamentary (and other legislative) debates. In this review, we discuss the available research with regard to the aims and objectives of the researchers who work on these problems, the automatic analysis tasks they undertake, and the approaches and methods they use. We conclude by summarizing their findings, discussing the challenges of applying computational analysis to parliamentary debates, and suggesting possible avenues for further research.
Tasks
Published	2019-07-09
URL	https://arxiv.org/abs/1907.04126v2
PDF	https://arxiv.org/pdf/1907.04126v2.pdf
PWC	https://paperswithcode.com/paper/sentiment-and-position-taking-analysis-of
Repo
Framework