July 27, 2019

2948 words 14 mins read

Paper Group ANR 503

Exact heat kernel on a hypersphere and its applications in kernel SVM. Robust Multilingual Part-of-Speech Tagging via Adversarial Training. Joint Estimation of Camera Pose, Depth, Deblurring, and Super-Resolution from a Blurred Image Sequence. Learning with Noise: Enhance Distantly Supervised Relation Extraction with Dynamic Transition Matrix. Incr …

Exact heat kernel on a hypersphere and its applications in kernel SVM


Title	Exact heat kernel on a hypersphere and its applications in kernel SVM
Authors	Chenchao Zhao, Jun S. Song
Abstract	Many contemporary statistical learning methods assume a Euclidean feature space. This paper presents a method for defining similarity based on hyperspherical geometry and shows that it often improves the performance of support vector machine compared to other competing similarity measures. Specifically, the idea of using heat diffusion on a hypersphere to measure similarity has been previously proposed, demonstrating promising results based on a heuristic heat kernel obtained from the zeroth order parametrix expansion; however, how well this heuristic kernel agrees with the exact hyperspherical heat kernel remains unknown. This paper presents a higher order parametrix expansion of the heat kernel on a unit hypersphere and discusses several problems associated with this expansion method. We then compare the heuristic kernel with an exact form of the heat kernel expressed in terms of a uniformly and absolutely convergent series in high-dimensional angular momentum eigenmodes. Being a natural measure of similarity between sample points dwelling on a hypersphere, the exact kernel often shows superior performance in kernel SVM classifications applied to text mining, tumor somatic mutation imputation, and stock market analysis.
Tasks	Imputation
Published	2017-02-05
URL	http://arxiv.org/abs/1702.01373v2
PDF	http://arxiv.org/pdf/1702.01373v2.pdf
PWC	https://paperswithcode.com/paper/exact-heat-kernel-on-a-hypersphere-and-its
Repo
Framework

Robust Multilingual Part-of-Speech Tagging via Adversarial Training


Title	Robust Multilingual Part-of-Speech Tagging via Adversarial Training
Authors	Michihiro Yasunaga, Jungo Kasai, Dragomir Radev
Abstract	Adversarial training (AT) is a powerful regularization method for neural networks, aiming to achieve robustness to input perturbations. Yet, the specific effects of the robustness obtained from AT are still unclear in the context of natural language processing. In this paper, we propose and analyze a neural POS tagging model that exploits AT. In our experiments on the Penn Treebank WSJ corpus and the Universal Dependencies (UD) dataset (27 languages), we find that AT not only improves the overall tagging accuracy, but also 1) prevents over-fitting well in low resource languages and 2) boosts tagging accuracy for rare / unseen words. We also demonstrate that 3) the improved tagging performance by AT contributes to the downstream task of dependency parsing, and that 4) AT helps the model to learn cleaner word representations. 5) The proposed AT model is generally effective in different sequence labeling tasks. These positive results motivate further use of AT for natural language tasks.
Tasks	Dependency Parsing, Part-Of-Speech Tagging
Published	2017-11-14
URL	http://arxiv.org/abs/1711.04903v2
PDF	http://arxiv.org/pdf/1711.04903v2.pdf
PWC	https://paperswithcode.com/paper/robust-multilingual-part-of-speech-tagging
Repo
Framework

Joint Estimation of Camera Pose, Depth, Deblurring, and Super-Resolution from a Blurred Image Sequence


Title	Joint Estimation of Camera Pose, Depth, Deblurring, and Super-Resolution from a Blurred Image Sequence
Authors	Haesol Park, Kyoung Mu Lee
Abstract	The conventional methods for estimating camera poses and scene structures from severely blurry or low resolution images often result in failure. The off-the-shelf deblurring or super-resolution methods may show visually pleasing results. However, applying each technique independently before matching is generally unprofitable because this naive series of procedures ignores the consistency between images. In this paper, we propose a pioneering unified framework that solves four problems simultaneously, namely, dense depth reconstruction, camera pose estimation, super-resolution, and deblurring. By reflecting a physical imaging process, we formulate a cost minimization problem and solve it using an alternating optimization technique. The experimental results on both synthetic and real videos show high-quality depth maps derived from severely degraded images that contrast the failures of naive multi-view stereo methods. Our proposed method also produces outstanding deblurred and super-resolved images unlike the independent application or combination of conventional video deblurring, super-resolution methods.
Tasks	Deblurring, Pose Estimation, Super-Resolution
Published	2017-09-18
URL	http://arxiv.org/abs/1709.05745v1
PDF	http://arxiv.org/pdf/1709.05745v1.pdf
PWC	https://paperswithcode.com/paper/joint-estimation-of-camera-pose-depth
Repo
Framework

Learning with Noise: Enhance Distantly Supervised Relation Extraction with Dynamic Transition Matrix


Title	Learning with Noise: Enhance Distantly Supervised Relation Extraction with Dynamic Transition Matrix
Authors	Bingfeng Luo, Yansong Feng, Zheng Wang, Zhanxing Zhu, Songfang Huang, Rui Yan, Dongyan Zhao
Abstract	Distant supervision significantly reduces human efforts in building training data for many classification tasks. While promising, this technique often introduces noise to the generated training data, which can severely affect the model performance. In this paper, we take a deep look at the application of distant supervision in relation extraction. We show that the dynamic transition matrix can effectively characterize the noise in the training data built by distant supervision. The transition matrix can be effectively trained using a novel curriculum learning based method without any direct supervision about the noise. We thoroughly evaluate our approach under a wide range of extraction scenarios. Experimental results show that our approach consistently improves the extraction results and outperforms the state-of-the-art in various evaluation scenarios.
Tasks	Relation Extraction
Published	2017-05-11
URL	http://arxiv.org/abs/1705.03995v1
PDF	http://arxiv.org/pdf/1705.03995v1.pdf
PWC	https://paperswithcode.com/paper/learning-with-noise-enhance-distantly
Repo
Framework

Incremental Adversarial Domain Adaptation for Continually Changing Environments


Title	Incremental Adversarial Domain Adaptation for Continually Changing Environments
Authors	Markus Wulfmeier, Alex Bewley, Ingmar Posner
Abstract	Continuous appearance shifts such as changes in weather and lighting conditions can impact the performance of deployed machine learning models. While unsupervised domain adaptation aims to address this challenge, current approaches do not utilise the continuity of the occurring shifts. In particular, many robotics applications exhibit these conditions and thus facilitate the potential to incrementally adapt a learnt model over minor shifts which integrate to massive differences over time. Our work presents an adversarial approach for lifelong, incremental domain adaptation which benefits from unsupervised alignment to a series of intermediate domains which successively diverge from the labelled source domain. We empirically demonstrate that our incremental approach improves handling of large appearance changes, e.g. day to night, on a traversable-path segmentation task compared with a direct, single alignment step approach. Furthermore, by approximating the feature distribution for the source domain with a generative adversarial network, the deployment module can be rendered fully independent of retaining potentially large amounts of the related source training data for only a minor reduction in performance.
Tasks	Domain Adaptation, Unsupervised Domain Adaptation
Published	2017-12-20
URL	http://arxiv.org/abs/1712.07436v2
PDF	http://arxiv.org/pdf/1712.07436v2.pdf
PWC	https://paperswithcode.com/paper/incremental-adversarial-domain-adaptation-for
Repo
Framework

A vision based system for underwater docking


Title	A vision based system for underwater docking
Authors	Shuang Liu, Mete Ozay, Takayuki Okatani, Hongli Xu, Kai Sun, Yang Lin
Abstract	Autonomous underwater vehicles (AUVs) have been deployed for underwater exploration. However, its potential is confined by its limited on-board battery energy and data storage capacity. This problem has been addressed using docking systems by underwater recharging and data transfer for AUVs. In this work, we propose a vision based framework for underwater docking following these systems. The proposed framework comprises two modules; (i) a detection module which provides location information on underwater docking stations in 2D images captured by an on-board camera, and (ii) a pose estimation module which recovers the relative 3D position and orientation between docking stations and AUVs from the 2D images. For robust and credible detection of docking stations, we propose a convolutional neural network called Docking Neural Network (DoNN). For accurate pose estimation, a perspective-n-point algorithm is integrated into our framework. In order to examine our framework in underwater docking tasks, we collected a dataset of 2D images, named Underwater Docking Images Dataset (UDID), in an experimental water pool. To the best of our knowledge, UDID is the first publicly available underwater docking dataset. In the experiments, we first evaluate performance of the proposed detection module on UDID and its deformed variations. Next, we assess the accuracy of the pose estimation module by ground experiments, since it is not feasible to obtain true relative position and orientation between docking stations and AUVs under water. Then, we examine the pose estimation module by underwater experiments in our experimental water pool. Experimental results show that the proposed framework can be used to detect docking stations and estimate their relative pose efficiently and successfully, compared to the state-of-the-art baseline systems.
Tasks	Pose Estimation
Published	2017-12-12
URL	http://arxiv.org/abs/1712.04138v1
PDF	http://arxiv.org/pdf/1712.04138v1.pdf
PWC	https://paperswithcode.com/paper/a-vision-based-system-for-underwater-docking
Repo
Framework

Automatic Compositor Attribution in the First Folio of Shakespeare


Title	Automatic Compositor Attribution in the First Folio of Shakespeare
Authors	Maria Ryskina, Hannah Alpert-Abrams, Dan Garrette, Taylor Berg-Kirkpatrick
Abstract	Compositor attribution, the clustering of pages in a historical printed document by the individual who set the type, is a bibliographic task that relies on analysis of orthographic variation and inspection of visual details of the printed page. In this paper, we introduce a novel unsupervised model that jointly describes the textual and visual features needed to distinguish compositors. Applied to images of Shakespeare’s First Folio, our model predicts attributions that agree with the manual judgements of bibliographers with an accuracy of 87%, even on text that is the output of OCR.
Tasks	Optical Character Recognition
Published	2017-04-25
URL	http://arxiv.org/abs/1704.07875v1
PDF	http://arxiv.org/pdf/1704.07875v1.pdf
PWC	https://paperswithcode.com/paper/automatic-compositor-attribution-in-the-first
Repo
Framework


Title	Learning Blind Motion Deblurring
Authors	Patrick Wieschollek, Michael Hirsch, Bernhard Schölkopf, Hendrik P. A. Lensch
Abstract	As handheld video cameras are now commonplace and available in every smartphone, images and videos can be recorded almost everywhere at anytime. However, taking a quick shot frequently yields a blurry result due to unwanted camera shake during recording or moving objects in the scene. Removing these artifacts from the blurry recordings is a highly ill-posed problem as neither the sharp image nor the motion blur kernel is known. Propagating information between multiple consecutive blurry observations can help restore the desired sharp image or video. Solutions for blind deconvolution based on neural networks rely on a massive amount of ground-truth data which is hard to acquire. In this work, we propose an efficient approach to produce a significant amount of realistic training data and introduce a novel recurrent network architecture to deblur frames taking temporal information into account, which can efficiently handle arbitrary spatial and temporal input sizes. We demonstrate the versatility of our approach in a comprehensive comparison on a number of challening real-world examples.
Tasks	Deblurring
Published	2017-08-14
URL	http://arxiv.org/abs/1708.04208v1
PDF	http://arxiv.org/pdf/1708.04208v1.pdf
PWC	https://paperswithcode.com/paper/learning-blind-motion-deblurring
Repo
Framework

Distributed Representation for Traditional Chinese Medicine Herb via Deep Learning Models


Title	Distributed Representation for Traditional Chinese Medicine Herb via Deep Learning Models
Authors	Wei Li, Zheng Yang
Abstract	Traditional Chinese Medicine (TCM) has accumulated a big amount of precious resource in the long history of development. TCM prescriptions that consist of TCM herbs are an important form of TCM treatment, which are similar to natural language documents, but in a weakly ordered fashion. Directly adapting language modeling style methods to learn the embeddings of the herbs can be problematic as the herbs are not strictly in order, the herbs in the front of the prescription can be connected to the very last ones. In this paper, we propose to represent TCM herbs with distributed representations via Prescription Level Language Modeling (PLLM). In one of our experiments, the correlation between our calculated similarity between medicines and the judgment of professionals achieves a Spearman score of 55.35 indicating a strong correlation, which surpasses human beginners (TCM related field bachelor student) by a big margin (over 10%).
Tasks	Language Modelling
Published	2017-11-06
URL	http://arxiv.org/abs/1711.01701v1
PDF	http://arxiv.org/pdf/1711.01701v1.pdf
PWC	https://paperswithcode.com/paper/distributed-representation-for-traditional
Repo
Framework

Unsupervised Feature Learning for Audio Analysis


Title	Unsupervised Feature Learning for Audio Analysis
Authors	Matthias Meyer, Jan Beutel, Lothar Thiele
Abstract	Identifying acoustic events from a continuously streaming audio source is of interest for many applications including environmental monitoring for basic research. In this scenario neither different event classes are known nor what distinguishes one class from another. Therefore, an unsupervised feature learning method for exploration of audio data is presented in this paper. It incorporates the two following novel contributions: First, an audio frame predictor based on a Convolutional LSTM autoencoder is demonstrated, which is used for unsupervised feature extraction. Second, a training method for autoencoders is presented, which leads to distinct features by amplifying event similarities. In comparison to standard approaches, the features extracted from the audio frame predictor trained with the novel approach show 13 % better results when used with a classifier and 36 % better results when used for clustering.
Tasks
Published	2017-12-11
URL	http://arxiv.org/abs/1712.03835v1
PDF	http://arxiv.org/pdf/1712.03835v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-feature-learning-for-audio-1
Repo
Framework

Video Deblurring via Semantic Segmentation and Pixel-Wise Non-Linear Kernel


Title	Video Deblurring via Semantic Segmentation and Pixel-Wise Non-Linear Kernel
Authors	Wenqi Ren, Jinshan Pan, Xiaochun Cao, Ming-Hsuan Yang
Abstract	Video deblurring is a challenging problem as the blur is complex and usually caused by the combination of camera shakes, object motions, and depth variations. Optical flow can be used for kernel estimation since it predicts motion trajectories. However, the estimates are often inaccurate in complex scenes at object boundaries, which are crucial in kernel estimation. In this paper, we exploit semantic segmentation in each blurry frame to understand the scene contents and use different motion models for image regions to guide optical flow estimation. While existing pixel-wise blur models assume that the blur kernel is the same as optical flow during the exposure time, this assumption does not hold when the motion blur trajectory at a pixel is different from the estimated linear optical flow. We analyze the relationship between motion blur trajectory and optical flow, and present a novel pixel-wise non-linear kernel model to account for motion blur. The proposed blur model is based on the non-linear optical flow, which describes complex motion blur more effectively. Extensive experiments on challenging blurry videos demonstrate the proposed algorithm performs favorably against the state-of-the-art methods.
Tasks	Deblurring, Optical Flow Estimation, Semantic Segmentation
Published	2017-08-11
URL	http://arxiv.org/abs/1708.03423v1
PDF	http://arxiv.org/pdf/1708.03423v1.pdf
PWC	https://paperswithcode.com/paper/video-deblurring-via-semantic-segmentation
Repo
Framework

Modelling the Scene Dependent Imaging in Cameras with a Deep Neural Network


Title	Modelling the Scene Dependent Imaging in Cameras with a Deep Neural Network
Authors	Seonghyeon Nam, Seon Joo Kim
Abstract	We present a novel deep learning framework that models the scene dependent image processing inside cameras. Often called as the radiometric calibration, the process of recovering RAW images from processed images (JPEG format in the sRGB color space) is essential for many computer vision tasks that rely on physically accurate radiance values. All previous works rely on the deterministic imaging model where the color transformation stays the same regardless of the scene and thus they can only be applied for images taken under the manual mode. In this paper, we propose a data-driven approach to learn the scene dependent and locally varying image processing inside cameras under the automode. Our method incorporates both the global and the local scene context into pixel-wise features via multi-scale pyramid of learnable histogram layers. The results show that we can model the imaging pipeline of different cameras that operate under the automode accurately in both directions (from RAW to sRGB, from sRGB to RAW) and we show how we can apply our method to improve the performance of image deblurring.
Tasks	Calibration, Deblurring
Published	2017-07-26
URL	http://arxiv.org/abs/1707.08350v1
PDF	http://arxiv.org/pdf/1707.08350v1.pdf
PWC	https://paperswithcode.com/paper/modelling-the-scene-dependent-imaging-in
Repo
Framework

A Short Review of Ethical Challenges in Clinical Natural Language Processing


Title	A Short Review of Ethical Challenges in Clinical Natural Language Processing
Authors	Simon Šuster, Stéphan Tulkens, Walter Daelemans
Abstract	Clinical NLP has an immense potential in contributing to how clinical practice will be revolutionized by the advent of large scale processing of clinical records. However, this potential has remained largely untapped due to slow progress primarily caused by strict data access policies for researchers. In this paper, we discuss the concern for privacy and the measures it entails. We also suggest sources of less sensitive data. Finally, we draw attention to biases that can compromise the validity of empirical research and lead to socially harmful applications.
Tasks
Published	2017-03-29
URL	http://arxiv.org/abs/1703.10090v1
PDF	http://arxiv.org/pdf/1703.10090v1.pdf
PWC	https://paperswithcode.com/paper/a-short-review-of-ethical-challenges-in
Repo
Framework

Convolutional Sparse Coding: Boundary Handling Revisited


Title	Convolutional Sparse Coding: Boundary Handling Revisited
Authors	Brendt Wohlberg, Paul Rodriguez
Abstract	Two different approaches have recently been proposed for boundary handling in convolutional sparse representations, avoiding potential boundary artifacts arising from the circular boundary conditions implied by the use of frequency domain solution methods by introducing a spatial mask into the convolutional sparse coding problem. In the present paper we show that, under certain circumstances, these methods fail in their design goal of avoiding boundary artifacts. The reasons for this failure are discussed, a solution is proposed, and the practical implications are illustrated in an image deblurring problem.
Tasks	Deblurring
Published	2017-07-20
URL	http://arxiv.org/abs/1707.06718v1
PDF	http://arxiv.org/pdf/1707.06718v1.pdf
PWC	https://paperswithcode.com/paper/convolutional-sparse-coding-boundary-handling
Repo
Framework

Radical analysis network for zero-shot learning in printed Chinese character recognition


Title	Radical analysis network for zero-shot learning in printed Chinese character recognition
Authors	Jianshu Zhang, Yixing Zhu, Jun Du, Lirong Dai
Abstract	Chinese characters have a huge set of character categories, more than 20,000 and the number is still increasing as more and more novel characters continue being created. However, the enormous characters can be decomposed into a compact set of about 500 fundamental and structural radicals. This paper introduces a novel radical analysis network (RAN) to recognize printed Chinese characters by identifying radicals and analyzing two-dimensional spatial structures among them. The proposed RAN first extracts visual features from input by employing convolutional neural networks as an encoder. Then a decoder based on recurrent neural networks is employed, aiming at generating captions of Chinese characters by detecting radicals and two-dimensional structures through a spatial attention mechanism. The manner of treating a Chinese character as a composition of radicals rather than a single character class largely reduces the size of vocabulary and enables RAN to possess the ability of recognizing unseen Chinese character classes, namely zero-shot learning.
Tasks	Zero-Shot Learning
Published	2017-11-03
URL	http://arxiv.org/abs/1711.01889v2
PDF	http://arxiv.org/pdf/1711.01889v2.pdf
PWC	https://paperswithcode.com/paper/radical-analysis-network-for-zero-shot
Repo
Framework