January 26, 2020

3031 words 15 mins read

Paper Group ANR 1435

Fixed-Confidence Guarantees for Bayesian Best-Arm Identification. Revealing Scenes by Inverting Structure from Motion Reconstructions. ClsGAN: Selective Attribute Editing Based On Classification Adversarial Network. Multiobjective Coverage Path Planning: Enabling Automated Inspection of Complex, Real-World Structures. Learning with Partially Ordere …

Fixed-Confidence Guarantees for Bayesian Best-Arm Identification


Title	Fixed-Confidence Guarantees for Bayesian Best-Arm Identification
Authors	Xuedong Shang, Rianne de Heide, Emilie Kaufmann, Pierre Ménard, Michal Valko
Abstract	We investigate and provide new insights on the sampling rule called Top-Two Thompson Sampling (TTTS). In particular, we justify its use for fixed-confidence best-arm identification. We further propose a variant of TTTS called Top-Two Transportation Cost (T3C), which disposes of the computational burden of TTTS. As our main contribution, we provide the first sample complexity analysis of TTTS and T3C when coupled with a very natural Bayesian stopping rule, for bandits with Gaussian rewards, solving one of the open questions raised by Russo (2016). We also provide new posterior convergence results for TTTS under two models that are commonly used in practice: bandits with Gaussian and Bernoulli rewards and conjugate priors.
Tasks
Published	2019-10-24
URL	https://arxiv.org/abs/1910.10945v3
PDF	https://arxiv.org/pdf/1910.10945v3.pdf
PWC	https://paperswithcode.com/paper/fixed-confidence-guarantees-for-bayesian-best
Repo
Framework

Revealing Scenes by Inverting Structure from Motion Reconstructions


Title	Revealing Scenes by Inverting Structure from Motion Reconstructions
Authors	Francesco Pittaluga, Sanjeev J. Koppal, Sing Bing Kang, Sudipta N. Sinha
Abstract	Many 3D vision systems localize cameras within a scene using 3D point clouds. Such point clouds are often obtained using structure from motion (SfM), after which the images are discarded to preserve privacy. In this paper, we show, for the first time, that such point clouds retain enough information to reveal scene appearance and compromise privacy. We present a privacy attack that reconstructs color images of the scene from the point cloud. Our method is based on a cascaded U-Net that takes as input, a 2D multichannel image of the points rendered from a specific viewpoint containing point depth and optionally color and SIFT descriptors and outputs a color image of the scene from that viewpoint. Unlike previous feature inversion methods, we deal with highly sparse and irregular 2D point distributions and inputs where many point attributes are missing, namely keypoint orientation and scale, the descriptor image source and the 3D point visibility. We evaluate our attack algorithm on public datasets and analyze the significance of the point cloud attributes. Finally, we show that novel views can also be generated thereby enabling compelling virtual tours of the underlying scene.
Tasks
Published	2019-04-05
URL	http://arxiv.org/abs/1904.03303v1
PDF	http://arxiv.org/pdf/1904.03303v1.pdf
PWC	https://paperswithcode.com/paper/revealing-scenes-by-inverting-structure-from
Repo
Framework

ClsGAN: Selective Attribute Editing Based On Classification Adversarial Network


Title	ClsGAN: Selective Attribute Editing Based On Classification Adversarial Network
Authors	Liu Ying, Heng Fan, Fuchuan Ni, Jinhai Xiang
Abstract	Attribution editing has shown remarking progress by the incorporating of encoder-decoder structure and generative adversarial network. However, there are still some challenges in the quality and attribute transformation of the generated images. Encoder-decoder structure leads to blurring of images and the skip-connection of encoder-decoder structure weakens the attribute transfer ability. To address these limitations, we propose a classification adversarial model(Cls-GAN) that can balance between attribute transfer and generated photo-realistic images. Considering that the transfer images are affected by the original attribute using skip-connection, we introduce upper convolution residual network(Tr-resnet) to selectively extract information from the source image and target label. Specially, we apply to the attribute classification adversarial network to learn about the defects of attribute transfer images so as to guide the generator. Finally, to meet the requirement of multimodal and improve reconstruction effect, we build two encoders including the content and style network, and select a attribute label approximation between source label and the output of style network. Experiments that operates at the dataset of CelebA show that images are superiority against the existing state-of-the-art models in image quality and transfer accuracy. Experiments on wikiart and seasonal datasets demonstrate that ClsGAN can effectively implement styel transfer.
Tasks
Published	2019-10-25
URL	https://arxiv.org/abs/1910.11764v1
PDF	https://arxiv.org/pdf/1910.11764v1.pdf
PWC	https://paperswithcode.com/paper/clsgan-selective-attribute-editing-based-on
Repo
Framework

Multiobjective Coverage Path Planning: Enabling Automated Inspection of Complex, Real-World Structures


Title	Multiobjective Coverage Path Planning: Enabling Automated Inspection of Complex, Real-World Structures
Authors	Kai Olav Ellefsen, Herman A. Lepikson, Jan C. Albiez
Abstract	An important open problem in robotic planning is the autonomous generation of 3D inspection paths – that is, planning the best path to move a robot along in order to inspect a target structure. We recently suggested a new method for planning paths allowing the inspection of complex 3D structures, given a triangular mesh model of the structure. The method differs from previous approaches in its emphasis on generating and considering also plans that result in imperfect coverage of the inspection target. In many practical tasks, one would accept imperfections in coverage if this results in a substantially more energy efficient inspection path. The key idea is using a multiobjective evolutionary algorithm to optimize the energy usage and coverage of inspection plans simultaneously - and the result is a set of plans exploring the different ways to balance the two objectives. We here test our method on a set of inspection targets with large variation in size and complexity, and compare its performance with two state-of-the-art methods for complete coverage path planning. The results strengthen our confidence in the ability of our method to generate good inspection plans for different types of targets. The method’s advantage is most clearly seen for real-world inspection targets, since traditional complete coverage methods have no good way of generating plans for structures with hidden parts. Multiobjective evolution, by optimizing energy usage and coverage together ensures a good balance between the two - both when 100% coverage is feasible, and when large parts of the object are hidden.
Tasks
Published	2019-01-22
URL	http://arxiv.org/abs/1901.07272v1
PDF	http://arxiv.org/pdf/1901.07272v1.pdf
PWC	https://paperswithcode.com/paper/multiobjective-coverage-path-planning
Repo
Framework

Learning with Partially Ordered Representations


Title	Learning with Partially Ordered Representations
Authors	Jane Chandlee, Remi Eyraud, Jeffrey Heinz, Adam Jardine, Jonathan Rawski
Abstract	This paper examines the characterization and learning of grammars defined with enriched representational models. Model-theoretic approaches to formal language theory traditionally assume that each position in a string belongs to exactly one unary relation. We consider unconventional string models where positions can have multiple, shared properties, which are arguably useful in many applications. We show the structures given by these models are partially ordered, and present a learning algorithm that exploits this ordering relation to effectively prune the hypothesis space. We prove this learning algorithm, which takes positive examples as input, finds the most general grammar which covers the data.
Tasks
Published	2019-06-19
URL	https://arxiv.org/abs/1906.07886v2
PDF	https://arxiv.org/pdf/1906.07886v2.pdf
PWC	https://paperswithcode.com/paper/learning-with-partially-ordered
Repo
Framework

Theory III: Dynamics and Generalization in Deep Networks – a simple solution


Title	Theory III: Dynamics and Generalization in Deep Networks – a simple solution
Authors	Andrzej Banburski, Qianli Liao, Brando Miranda, Lorenzo Rosasco, Jack Hidary, Tomaso Poggio
Abstract	Classical generalization bounds for classification in the setting of separable data can be optimized by maximizing the margin of a deep network under the constraint of unit p-norm of the weight matrix at each layer. A possible approach for solving numerically this problem uses gradient algorithms on exponential-type loss functions, enforcing a unit constraint in the p-norm. In the limiting case of continuous gradient flow, we analyze the dynamical systems associated with three algorithms of this kind and their close relation for $p=2$ with existing weight normalization and batch normalization algorithms. An interesting observation is that unconstrained gradient descent has a similar dynamics with the same critical points and thus also optimizes the generalization bounds. Our approach extends some of the results of Srebro from linear networks to deep networks and provides a new perspective on the implicit bias of gradient descent. This elusive complexity control is likely to be responsible for generalization despite overparametrization in deep networks.
Tasks
Published	2019-03-12
URL	https://arxiv.org/abs/1903.04991v4
PDF	https://arxiv.org/pdf/1903.04991v4.pdf
PWC	https://paperswithcode.com/paper/theory-iii-dynamics-and-generalization-in
Repo
Framework

Reinforcement Learning for Personalized Dialogue Management


Title	Reinforcement Learning for Personalized Dialogue Management
Authors	Floris den Hengst, Mark Hoogendoorn, Frank van Harmelen, Joost Bosman
Abstract	Language systems have been of great interest to the research community and have recently reached the mass market through various assistant platforms on the web. Reinforcement Learning methods that optimize dialogue policies have seen successes in past years and have recently been extended into methods that personalize the dialogue, e.g. take the personal context of users into account. These works, however, are limited to personalization to a single user with whom they require multiple interactions and do not generalize the usage of context across users. This work introduces a problem where a generalized usage of context is relevant and proposes two Reinforcement Learning (RL)-based approaches to this problem. The first approach uses a single learner and extends the traditional POMDP formulation of dialogue state with features that describe the user context. The second approach segments users by context and then employs a learner per context. We compare these approaches in a benchmark of existing non-RL and RL-based methods in three established and one novel application domain of financial product recommendation. We compare the influence of context and training experiences on performance and find that learning approaches generally outperform a handcrafted gold standard.
Tasks	Dialogue Management, Product Recommendation
Published	2019-08-01
URL	https://arxiv.org/abs/1908.00286v1
PDF	https://arxiv.org/pdf/1908.00286v1.pdf
PWC	https://paperswithcode.com/paper/reinforcement-learning-for-personalized
Repo
Framework

A Machine Learning Dataset Prepared From the NASA Solar Dynamics Observatory Mission


Title	A Machine Learning Dataset Prepared From the NASA Solar Dynamics Observatory Mission
Authors	Richard Galvez, David F. Fouhey, Meng Jin, Alexandre Szenicer, Andrés Muñoz-Jaramillo, Mark C. M. Cheung, Paul J. Wright, Monica G. Bobra, Yang Liu, James Mason, Rajat Thomas
Abstract	In this paper we present a curated dataset from the NASA Solar Dynamics Observatory (SDO) mission in a format suitable for machine learning research. Beginning from level 1 scientific products we have processed various instrumental corrections, downsampled to manageable spatial and temporal resolutions, and synchronized observations spatially and temporally. We illustrate the use of this dataset with two example applications: forecasting future EVE irradiance from present EVE irradiance and translating HMI observations into AIA observations. For each application we provide metrics and baselines for future model comparison. We anticipate this curated dataset will facilitate machine learning research in heliophysics and the physical sciences generally, increasing the scientific return of the SDO mission. This work is a direct result of the 2018 NASA Frontier Development Laboratory Program. Please see the appendix for access to the dataset.
Tasks
Published	2019-03-11
URL	http://arxiv.org/abs/1903.04538v1
PDF	http://arxiv.org/pdf/1903.04538v1.pdf
PWC	https://paperswithcode.com/paper/a-machine-learning-dataset-prepared-from-the
Repo
Framework

Unconstrained Church-Turing thesis cannot possibly be true


Title	Unconstrained Church-Turing thesis cannot possibly be true
Authors	Yuri Gurevich
Abstract	The Church-Turing thesis asserts that if a partial strings-to-strings function is effectively computable then it is computable by a Turing machine. In the 1930s, when Church and Turing worked on their versions of the thesis, there was a robust notion of algorithm. These traditional algorithms are known also as classical or sequential. In the original thesis, effectively computable meant computable by an effective classical algorithm. Based on an earlier axiomatization of classical algorithms, the original thesis was proven in 2008. Since the 1930s, the notion of algorithm has changed dramatically. New species of algorithms have been and are being introduced. We argue that the generalization of the original thesis, where effectively computable means computable by an effective algorithm of any species, cannot possibly be true.
Tasks
Published	2019-01-15
URL	http://arxiv.org/abs/1901.04911v1
PDF	http://arxiv.org/pdf/1901.04911v1.pdf
PWC	https://paperswithcode.com/paper/unconstrained-church-turing-thesis-cannot
Repo
Framework

Fluent Translations from Disfluent Speech in End-to-End Speech Translation


Title	Fluent Translations from Disfluent Speech in End-to-End Speech Translation
Authors	Elizabeth Salesky, Matthias Sperber, Alex Waibel
Abstract	Spoken language translation applications for speech suffer due to conversational speech phenomena, particularly the presence of disfluencies. With the rise of end-to-end speech translation models, processing steps such as disfluency removal that were previously an intermediate step between speech recognition and machine translation need to be incorporated into model architectures. We use a sequence-to-sequence model to translate from noisy, disfluent speech to fluent text with disfluencies removed using the recently collected `copy-edited’ references for the Fisher Spanish-English dataset. We are able to directly generate fluent translations and introduce considerations about how to evaluate success on this task. This work provides a baseline for a new task, the translation of conversational speech with joint removal of disfluencies. \|
Tasks	Machine Translation, Speech Recognition
Published	2019-06-03
URL	https://arxiv.org/abs/1906.00556v1
PDF	https://arxiv.org/pdf/1906.00556v1.pdf
PWC	https://paperswithcode.com/paper/190600556
Repo
Framework

A Massive Collection of Cross-Lingual Web-Document Pairs


Title	A Massive Collection of Cross-Lingual Web-Document Pairs
Authors	Ahmed El-Kishky, Vishrav Chaudhary, Francisco Guzman, Philipp Koehn
Abstract	Cross-lingual document alignment aims to identify pairs of documents in two distinct languages that are of comparable content or translations of each other. Small-scale efforts have been made to collect aligned document level data on a limited set of language-pairs such as English-German or on limited comparable collections such as Wikipedia. In this paper, we mine twelve snapshots of the Common Crawl corpus and identify web document pairs that are translations of each other. We release a new web dataset consisting of 54 million URL pairs from Common Crawl covering documents in 92 languages paired with English. We evaluate the quality of the dataset by measuring the quality of machine translations from models that have been trained on mined parallel sentence pairs from this aligned corpora and introduce a simple yet effective baseline for identifying these aligned documents. The objective of this dataset and paper is to foster new research in cross-lingual NLP across a variety of low, mid, and high-resource languages.
Tasks
Published	2019-11-10
URL	https://arxiv.org/abs/1911.06154v1
PDF	https://arxiv.org/pdf/1911.06154v1.pdf
PWC	https://paperswithcode.com/paper/a-massive-collection-of-cross-lingual-web
Repo
Framework

Augmented Ultrasonic Data for Machine Learning


Title	Augmented Ultrasonic Data for Machine Learning
Authors	Iikka Virkkunen, Tuomas Koskinen, Oskari Jessen-Juhler, Jari Rinta-Aho
Abstract	Flaw detection in non-destructive testing, especially in complex signals like ultrasonic data, has thus far relied heavily on the expertise and judgement of trained human inspectors. While automated systems have been used for a long time, these have mostly been limited to using simple decision automation, such as signal amplitude threshold. The recent advances in various machine learning algorithms have solved many similarly difficult classification problems, that have previously been considered intractable. For non-destructive testing, encouraging results have already been reported in the open literature, but the use of machine learning is still very limited in NDT applications in the field. Key issue hindering their use, is the limited availability of representative flawed data-sets to be used for training. In the present paper, we develop modern, very deep convolutional network to detect flaws from phased-array ultrasonic data. We make extensive use of data augmentation to enhance the initially limited raw data and to aid learning. The data augmentation utilizes virtual flaws - a technique, that has successfully been used in training human inspectors and is soon to be used in nuclear inspection qualification. The results from the machine learning classifier are compared to human performance. We show, that using sophisticated data augmentation, modern deep learning networks can be trained to achieve superhuman performance by significant margin.
Tasks	Data Augmentation
Published	2019-03-26
URL	http://arxiv.org/abs/1903.11399v1
PDF	http://arxiv.org/pdf/1903.11399v1.pdf
PWC	https://paperswithcode.com/paper/augmented-ultrasonic-data-for-machine
Repo
Framework

Source codes in human communication


Title	Source codes in human communication
Authors	Michael Ramscar
Abstract	Although information theoretic characterizations of human communication have become increasingly popular in linguistics, to date they have largely involved grafting probabilistic constructs onto older ideas about grammar. Similarities between human and digital communication have been strongly emphasized, and differences largely ignored. However, some of these differences matter: communication systems are based on predefined codes shared by every sender-receiver, whereas the distributions of words in natural languages guarantee that no speaker-hearer ever has access to an entire linguistic code, which seemingly undermines the idea that natural languages are probabilistic systems in any meaningful sense. This paper describes how the distributional properties of languages meet the various challenges arising from the differences between information systems and natural languages, along with the very different view of human communication these properties suggest.
Tasks
Published	2019-03-08
URL	http://arxiv.org/abs/1904.03991v1
PDF	http://arxiv.org/pdf/1904.03991v1.pdf
PWC	https://paperswithcode.com/paper/190403991
Repo
Framework

A weakly supervised sequence tagging and grammar induction approach to semantic frame slot filling


Title	A weakly supervised sequence tagging and grammar induction approach to semantic frame slot filling
Authors	Janneke van de Loo, Guy De Pauw, Walter Daelemans
Abstract	This paper describes continuing work on semantic frame slot filling for a command and control task using a weakly-supervised approach. We investigate the advantages of using retraining techniques that take the output of a hierarchical hidden markov model as input to two inductive approaches: (1) discriminative sequence labelers based on conditional random fields and memory-based learning and (2) probabilistic context-free grammar induction. Experimental results show that this setup can significantly improve F-scores without the need for additional information sources. Furthermore, qualitative analysis shows that the weakly supervised technique is able to automatically induce an easily interpretable and syntactically appropriate grammar for the domain and task at hand.
Tasks	Slot Filling
Published	2019-06-15
URL	https://arxiv.org/abs/1906.06493v1
PDF	https://arxiv.org/pdf/1906.06493v1.pdf
PWC	https://paperswithcode.com/paper/a-weakly-supervised-sequence-tagging-and
Repo
Framework

Perceive Where to Focus: Learning Visibility-aware Part-level Features for Partial Person Re-identification


Title	Perceive Where to Focus: Learning Visibility-aware Part-level Features for Partial Person Re-identification
Authors	Yifan Sun, Qin Xu, Yali Li, Chi Zhang, Yikang Li, Shengjin Wang, Jian Sun
Abstract	This paper considers a realistic problem in person re-identification (re-ID) task, i.e., partial re-ID. Under partial re-ID scenario, the images may contain a partial observation of a pedestrian. If we directly compare a partial pedestrian image with a holistic one, the extreme spatial misalignment significantly compromises the discriminative ability of the learned representation. We propose a Visibility-aware Part Model (VPM), which learns to perceive the visibility of regions through self-supervision. The visibility awareness allows VPM to extract region-level features and compare two images with focus on their shared regions (which are visible on both images). VPM gains two-fold benefit toward higher accuracy for partial re-ID. On the one hand, compared with learning a global feature, VPM learns region-level features and benefits from fine-grained information. On the other hand, with visibility awareness, VPM is capable to estimate the shared regions between two images and thus suppresses the spatial misalignment. Experimental results confirm that our method significantly improves the learned representation and the achieved accuracy is on par with the state of the art.
Tasks	Person Re-Identification
Published	2019-04-01
URL	http://arxiv.org/abs/1904.00537v1
PDF	http://arxiv.org/pdf/1904.00537v1.pdf
PWC	https://paperswithcode.com/paper/perceive-where-to-focus-learning-visibility
Repo
Framework