October 18, 2019

3215 words 16 mins read

Paper Group ANR 446

Depth Image Upsampling based on Guided Filter with Low Gradient Minimization. Dense Object Reconstruction from RGBD Images with Embedded Deep Shape Representations. CS-VQA: Visual Question Answering with Compressively Sensed Images. Approximate Knowledge Compilation by Online Collapsed Importance Sampling. Semantic Topic Analysis of Traffic Camera …

Depth Image Upsampling based on Guided Filter with Low Gradient Minimization


Title	Depth Image Upsampling based on Guided Filter with Low Gradient Minimization
Authors	Hang Yang, Zhongbo Zhang
Abstract	In this paper, we present a novel upsampling framework to enhance the spatial resolution of the depth image. In our framework, the upscaling of a low-resolution depth image is guided by a corresponding intensity images, we formulate it as a cost aggregation problem with the guided filter. However, the guided filter does not make full use of the properties of the depth image. Since depth images have quite sparse gradients, it inspires us to regularize the gradients for improving depth upscaling results. Statistics show a special property of depth images, that is, there is a non-ignorable part of pixels whose horizontal or vertical derivatives are equal to $\pm 1$. Considering this special property, we propose a low gradient regularization method which reduces the penalty for horizontal or vertical derivative $\pm1$. The proposed low gradient regularization is integrated with the guided filter into the depth image upsampling method. Experimental results demonstrate the effectiveness of our proposed approach both qualitatively and quantitatively compared with the state-of-the-art methods.
Tasks	Depth Image Upsampling
Published	2018-11-12
URL	http://arxiv.org/abs/1811.04620v1
PDF	http://arxiv.org/pdf/1811.04620v1.pdf
PWC	https://paperswithcode.com/paper/depth-image-upsampling-based-on-guided-filter
Repo
Framework

Dense Object Reconstruction from RGBD Images with Embedded Deep Shape Representations


Title	Dense Object Reconstruction from RGBD Images with Embedded Deep Shape Representations
Authors	Lan Hu, Yuchen Cao, Peng Wu, Laurent Kneip
Abstract	Most problems involving simultaneous localization and mapping can nowadays be solved using one of two fundamentally different approaches. The traditional approach is given by a least-squares objective, which minimizes many local photometric or geometric residuals over explicitly parametrized structure and camera parameters. Unmodeled effects violating the lambertian surface assumption or geometric invariances of individual residuals are encountered through statistical averaging or the addition of robust kernels and smoothness terms. Aiming at more accurate measurement models and the inclusion of higher-order shape priors, the community more recently shifted its attention to deep end-to-end models for solving geometric localization and mapping problems. However, at test-time, these feed-forward models ignore the more traditional geometric or photometric consistency terms, thus leading to a low ability to recover fine details and potentially complete failure in corner case scenarios. With an application to dense object modeling from RGBD images, our work aims at taking the best of both worlds by embedding modern higher-order object shape priors into classical iterative residual minimization objectives. We demonstrate a general ability to improve mapping accuracy with respect to each modality alone, and present a successful application to real data.
Tasks	Object Reconstruction, Simultaneous Localization and Mapping
Published	2018-10-11
URL	http://arxiv.org/abs/1810.04891v1
PDF	http://arxiv.org/pdf/1810.04891v1.pdf
PWC	https://paperswithcode.com/paper/dense-object-reconstruction-from-rgbd-images
Repo
Framework

CS-VQA: Visual Question Answering with Compressively Sensed Images


Title	CS-VQA: Visual Question Answering with Compressively Sensed Images
Authors	Li-Chi Huang, Kuldeep Kulkarni, Anik Jha, Suhas Lohit, Suren Jayasuriya, Pavan Turaga
Abstract	Visual Question Answering (VQA) is a complex semantic task requiring both natural language processing and visual recognition. In this paper, we explore whether VQA is solvable when images are captured in a sub-Nyquist compressive paradigm. We develop a series of deep-network architectures that exploit available compressive data to increasing degrees of accuracy, and show that VQA is indeed solvable in the compressed domain. Our results show that there is nominal degradation in VQA performance when using compressive measurements, but that accuracy can be recovered when VQA pipelines are used in conjunction with state-of-the-art deep neural networks for CS reconstruction. The results presented yield important implications for resource-constrained VQA applications.
Tasks	Question Answering, Visual Question Answering
Published	2018-06-08
URL	http://arxiv.org/abs/1806.03379v1
PDF	http://arxiv.org/pdf/1806.03379v1.pdf
PWC	https://paperswithcode.com/paper/cs-vqa-visual-question-answering-with
Repo
Framework

Approximate Knowledge Compilation by Online Collapsed Importance Sampling


Title	Approximate Knowledge Compilation by Online Collapsed Importance Sampling
Authors	Tal Friedman, Guy Van den Broeck
Abstract	We introduce collapsed compilation, a novel approximate inference algorithm for discrete probabilistic graphical models. It is a collapsed sampling algorithm that incrementally selects which variable to sample next based on the partial sample obtained so far. This online collapsing, together with knowledge compilation inference on the remaining variables, naturally exploits local structure and context- specific independence in the distribution. These properties are naturally exploited in exact inference, but are difficult to harness for approximate inference. More- over, by having a partially compiled circuit available during sampling, collapsed compilation has access to a highly effective proposal distribution for importance sampling. Our experimental evaluation shows that collapsed compilation performs well on standard benchmarks. In particular, when the amount of exact inference is equally limited, collapsed compilation is competitive with the state of the art, and outperforms it on several benchmarks.
Tasks
Published	2018-05-31
URL	http://arxiv.org/abs/1805.12565v1
PDF	http://arxiv.org/pdf/1805.12565v1.pdf
PWC	https://paperswithcode.com/paper/approximate-knowledge-compilation-by-online
Repo
Framework

Semantic Topic Analysis of Traffic Camera Images


Title	Semantic Topic Analysis of Traffic Camera Images
Authors	Jeffrey Liu, Andrew Weinert, Saurabh Amin
Abstract	Traffic cameras are commonly deployed monitoring components in road infrastructure networks, providing operators visual information about conditions at critical points in the network. However, human observers are often limited in their ability to process simultaneous information sources. Recent advancements in computer vision, driven by deep learning methods, have enabled general object recognition, unlocking opportunities for camera-based sensing beyond the existing human observer paradigm. In this paper, we present a Natural Language Processing (NLP)-inspired approach, entitled Bag-of-Label-Words (BoLW), for analyzing image data sets using exclusively textual labels. The BoLW model represents the data in a conventional matrix form, enabling data compression and decomposition techniques, while preserving semantic interpretability. We apply the Latent Dirichlet Allocation (LDA) topic model to decompose the label data into a small number of semantic topics. To illustrate our approach, we use freeway camera images collected from the Boston area between December 2017-January 2018. We analyze the cameras’ sensitivity to weather events; identify temporal traffic patterns; and analyze the impact of infrequent events, such as the winter holidays and the “bomb cyclone” winter storm. This study demonstrates the flexibility of our approach, which allows us to analyze weather events and freeway traffic using only traffic camera image labels.
Tasks	Object Recognition
Published	2018-09-27
URL	http://arxiv.org/abs/1809.10707v1
PDF	http://arxiv.org/pdf/1809.10707v1.pdf
PWC	https://paperswithcode.com/paper/semantic-topic-analysis-of-traffic-camera
Repo
Framework

Colorless green recurrent networks dream hierarchically


Title	Colorless green recurrent networks dream hierarchically
Authors	Kristina Gulordava, Piotr Bojanowski, Edouard Grave, Tal Linzen, Marco Baroni
Abstract	Recurrent neural networks (RNNs) have achieved impressive results in a variety of linguistic processing tasks, suggesting that they can induce non-trivial properties of language. We investigate here to what extent RNNs learn to track abstract hierarchical syntactic structure. We test whether RNNs trained with a generic language modeling objective in four languages (Italian, English, Hebrew, Russian) can predict long-distance number agreement in various constructions. We include in our evaluation nonsensical sentences where RNNs cannot rely on semantic or lexical cues (“The colorless green ideas I ate with the chair sleep furiously”), and, for Italian, we compare model performance to human intuitions. Our language-model-trained RNNs make reliable predictions about long-distance agreement, and do not lag much behind human performance. We thus bring support to the hypothesis that RNNs are not just shallow-pattern extractors, but they also acquire deeper grammatical competence.
Tasks	Language Modelling
Published	2018-03-29
URL	http://arxiv.org/abs/1803.11138v1
PDF	http://arxiv.org/pdf/1803.11138v1.pdf
PWC	https://paperswithcode.com/paper/colorless-green-recurrent-networks-dream
Repo
Framework

Semantic Role Labeling for Learner Chinese: the Importance of Syntactic Parsing and L2-L1 Parallel Data


Title	Semantic Role Labeling for Learner Chinese: the Importance of Syntactic Parsing and L2-L1 Parallel Data
Authors	Zi Lin, Yuguang Duan, Yuanyuan Zhao, Weiwei Sun, Xiaojun Wan
Abstract	This paper studies semantic parsing for interlanguage (L2), taking semantic role labeling (SRL) as a case task and learner Chinese as a case language. We first manually annotate the semantic roles for a set of learner texts to derive a gold standard for automatic SRL. Based on the new data, we then evaluate three off-the-shelf SRL systems, i.e., the PCFGLA-parser-based, neural-parser-based and neural-syntax-agnostic systems, to gauge how successful SRL for learner Chinese can be. We find two non-obvious facts: 1) the L1-sentence-trained systems performs rather badly on the L2 data; 2) the performance drop from the L1 data to the L2 data of the two parser-based systems is much smaller, indicating the importance of syntactic parsing in SRL for interlanguages. Finally, the paper introduces a new agreement-based model to explore the semantic coherency information in the large-scale L2-L1 parallel data. We then show such information is very effective to enhance SRL for learner texts. Our model achieves an F-score of 72.06, which is a 2.02 point improvement over the best baseline.
Tasks	Semantic Parsing, Semantic Role Labeling
Published	2018-08-28
URL	http://arxiv.org/abs/1808.09409v2
PDF	http://arxiv.org/pdf/1808.09409v2.pdf
PWC	https://paperswithcode.com/paper/semantic-role-labeling-for-learner-chinese
Repo
Framework

Discrete flow posteriors for variational inference in discrete dynamical systems


Title	Discrete flow posteriors for variational inference in discrete dynamical systems
Authors	Laurence Aitchison, Vincent Adam, Srinivas C. Turaga
Abstract	Each training step for a variational autoencoder (VAE) requires us to sample from the approximate posterior, so we usually choose simple (e.g. factorised) approximate posteriors in which sampling is an efficient computation that fully exploits GPU parallelism. However, such simple approximate posteriors are often insufficient, as they eliminate statistical dependencies in the posterior. While it is possible to use normalizing flow approximate posteriors for continuous latents, some problems have discrete latents and strong statistical dependencies. The most natural approach to model these dependencies is an autoregressive distribution, but sampling from such distributions is inherently sequential and thus slow. We develop a fast, parallel sampling procedure for autoregressive distributions based on fixed-point iterations which enables efficient and accurate variational inference in discrete state-space latent variable dynamical systems. To optimize the variational bound, we considered two ways to evaluate probabilities: inserting the relaxed samples directly into the pmf for the discrete distribution, or converting to continuous logistic latent variables and interpreting the K-step fixed-point iterations as a normalizing flow. We found that converting to continuous latent variables gave considerable additional scope for mismatch between the true and approximate posteriors, which resulted in biased inferences, we thus used the former approach. Using our fast sampling procedure, we were able to realize the benefits of correlated posteriors, including accurate uncertainty estimates for one cell, and accurate connectivity estimates for multiple cells, in an order of magnitude less time.
Tasks
Published	2018-05-28
URL	http://arxiv.org/abs/1805.10958v1
PDF	http://arxiv.org/pdf/1805.10958v1.pdf
PWC	https://paperswithcode.com/paper/discrete-flow-posteriors-for-variational
Repo
Framework

Sequential model aggregation for production forecasting


Title	Sequential model aggregation for production forecasting
Authors	Raphaël Deswarte, Véronique Gervais, Gilles Stoltz, Sébastien da Veiga
Abstract	Production forecasting is a key step to design the future development of a reservoir. A classical way to generate such forecasts consists in simulating future production for numerical models representative of the reservoir. However, identifying such models can be very challenging as they need to be constrained to all available data. In particular, they should reproduce past production data, which requires to solve a complex non-linear inverse problem. In this paper, we thus propose to investigate the potential of machine learning algorithms to predict the future production of a reservoir based on past production data without model calibration. We focus more specifically on robust online aggregation, a deterministic approach that provides a robust framework to make forecasts on a regular basis. This method does not rely on any specific assumption or need for stochastic modeling. Forecasts are first simulated for a set of base reservoir models representing the prior uncertainty, and then combined to predict production at the next time step. The weight associated to each forecast is related to its past performance. Three different algorithms are considered for weight computations: the exponentially weighted average algorithm, ridge regression and the Lasso regression. They are applied on a synthetic reservoir case study, the Brugge case, for sequential predictions. To estimate the potential of development scenarios, production forecasts are needed on long periods of time without intermediary data acquisition. An extension of the deterministic aggregation approach is thus proposed in this paper to provide such multi-step-ahead forecasts.
Tasks	Calibration
Published	2018-11-30
URL	https://arxiv.org/abs/1812.10389v2
PDF	https://arxiv.org/pdf/1812.10389v2.pdf
PWC	https://paperswithcode.com/paper/sequential-model-aggregation-for-production
Repo
Framework

Transition-based Parsing with Lighter Feed-Forward Networks


Title	Transition-based Parsing with Lighter Feed-Forward Networks
Authors	David Vilares, Carlos Gómez-Rodríguez
Abstract	We explore whether it is possible to build lighter parsers, that are statistically equivalent to their corresponding standard version, for a wide set of languages showing different structures and morphologies. As testbed, we use the Universal Dependencies and transition-based dependency parsers trained on feed-forward networks. For these, most existing research assumes de facto standard embedded features and relies on pre-computation tricks to obtain speed-ups. We explore how these features and their size can be reduced and whether this translates into speed-ups with a negligible impact on accuracy. The experiments show that grand-daughter features can be removed for the majority of treebanks without a significant (negative or positive) LAS difference. They also show how the size of the embeddings can be notably reduced.
Tasks
Published	2018-10-21
URL	http://arxiv.org/abs/1810.08997v1
PDF	http://arxiv.org/pdf/1810.08997v1.pdf
PWC	https://paperswithcode.com/paper/transition-based-parsing-with-lighter-feed
Repo
Framework

A Probabilistic Extension of Action Language BC+


Title	A Probabilistic Extension of Action Language BC+
Authors	Joohyung Lee, Yi Wang
Abstract	We present a probabilistic extension of action language BC+. Just like BC+ is defined as a high-level notation of answer set programs for describing transition systems, the proposed language, which we call pBC+, is defined as a high-level notation of LPMLN programs—a probabilistic extension of answer set programs. We show how probabilistic reasoning about transition systems, such as prediction, postdiction, and planning problems, as well as probabilistic diagnosis for dynamic domains, can be modeled in pBC+ and computed using an implementation of LPMLN.
Tasks
Published	2018-05-02
URL	http://arxiv.org/abs/1805.00634v2
PDF	http://arxiv.org/pdf/1805.00634v2.pdf
PWC	https://paperswithcode.com/paper/a-probabilistic-extension-of-action-language
Repo
Framework

Learning Contextual Hierarchical Structure of Medical Concepts with Poincairé Embeddings to Clarify Phenotypes


Title	Learning Contextual Hierarchical Structure of Medical Concepts with Poincairé Embeddings to Clarify Phenotypes
Authors	Brett K. Beaulieu-Jones, Isaac S. Kohane, Andrew L. Beam
Abstract	Biomedical association studies are increasingly done using clinical concepts, and in particular diagnostic codes from clinical data repositories as phenotypes. Clinical concepts can be represented in a meaningful, vector space using word embedding models. These embeddings allow for comparison between clinical concepts or for straightforward input to machine learning models. Using traditional approaches, good representations require high dimensionality, making downstream tasks such as visualization more difficult. We applied Poincar'e embeddings in a 2-dimensional hyperbolic space to a large-scale administrative claims database and show performance comparable to 100-dimensional embeddings in a euclidean space. We then examine disease relationships under different disease contexts to better understand potential phenotypes.
Tasks
Published	2018-11-03
URL	http://arxiv.org/abs/1811.01294v1
PDF	http://arxiv.org/pdf/1811.01294v1.pdf
PWC	https://paperswithcode.com/paper/learning-contextual-hierarchical-structure-of
Repo
Framework

Automated Tactical Decision Planning Model with Strategic Values Guidance for Local Action-Value-Ambiguity


Title	Automated Tactical Decision Planning Model with Strategic Values Guidance for Local Action-Value-Ambiguity
Authors	Daniel Muller, Erez Karpas
Abstract	In many real-world planning problems, action’s impact differs with a place, time and the context in which the action is applied. The same action with the same effects in a different context or states can cause a different change. In actions with incomplete precondition list, that applicable in several states and circumstances, ambiguity regarding the impact of the action is challenging even in small domains. To estimate the real impact of actions, an evaluation of the effect list will not be enough; a relative estimation is more informative and suitable for estimation of action’s real impact. Recent work on Over-subscription Planning (OSP) defined the net utility of action as the net change in the state’s value caused by the action. The notion of net utility of action allows for a broader perspective on value action impact and use for a more accurate evaluation of achievements of the action, considering inter-state and intra-state dependencies. To achieve value-rational decisions in complex reality often requires strategic, high level, planning with a global perspective and values, while many local tactical decisions require real-time information to estimate the impact of actions. This paper proposes an offline action-value structure analysis to exploit the compactly represented informativeness of net utility of actions to extend the scope of planning to value uncertainty scenarios and to provide a real-time value-rational decision planning tool. The result of the offline pre-processing phase is a compact decision planning model representation for flexible, local reasoning of net utility of actions with (offline) value ambiguity. The obtained flexibility is beneficial for the online planning phase and real-time execution of actions with value ambiguity. Our empirical evaluation shows the effectiveness of this approach in domains with value ambiguity in their action-value-structure.
Tasks
Published	2018-11-30
URL	http://arxiv.org/abs/1811.12917v1
PDF	http://arxiv.org/pdf/1811.12917v1.pdf
PWC	https://paperswithcode.com/paper/automated-tactical-decision-planning-model
Repo
Framework

Collaborative Human-AI (CHAI): Evidence-Based Interpretable Melanoma Classification in Dermoscopic Images


Title	Collaborative Human-AI (CHAI): Evidence-Based Interpretable Melanoma Classification in Dermoscopic Images
Authors	Noel C. F. Codella, Chung-Ching Lin, Allan Halpern, Michael Hind, Rogerio Feris, John R. Smith
Abstract	Automated dermoscopic image analysis has witnessed rapid growth in diagnostic performance. Yet adoption faces resistance, in part, because no evidence is provided to support decisions. In this work, an approach for evidence-based classification is presented. A feature embedding is learned with CNNs, triplet-loss, and global average pooling, and used to classify via kNN search. Evidence is provided as both the discovered neighbors, as well as localized image regions most relevant to measuring distance between query and neighbors. To ensure that results are relevant in terms of both label accuracy and human visual similarity for any skill level, a novel hierarchical triplet logic is implemented to jointly learn an embedding according to disease labels and non-expert similarity. Results are improved over baselines trained on disease labels alone, as well as standard multiclass loss. Quantitative relevance of results, according to non-expert similarity, as well as localized image regions, are also significantly improved.
Tasks
Published	2018-05-30
URL	http://arxiv.org/abs/1805.12234v3
PDF	http://arxiv.org/pdf/1805.12234v3.pdf
PWC	https://paperswithcode.com/paper/collaborative-human-ai-chai-evidence-based
Repo
Framework

MMSE Approximation For Sparse Coding Algorithms Using Stochastic Resonance


Title	MMSE Approximation For Sparse Coding Algorithms Using Stochastic Resonance
Authors	Dror Simon, Jeremias Sulam, Yaniv Romano, Yue M. Lu, Michael Elad
Abstract	Sparse coding refers to the pursuit of the sparsest representation of a signal in a typically overcomplete dictionary. From a Bayesian perspective, sparse coding provides a Maximum a Posteriori (MAP) estimate of the unknown vector under a sparse prior. In this work, we suggest enhancing the performance of sparse coding algorithms by a deliberate and controlled contamination of the input with random noise, a phenomenon known as stochastic resonance. The proposed method adds controlled noise to the input and estimates a sparse representation from the perturbed signal. A set of such solutions is then obtained by projecting the original input signal onto the recovered set of supports. We present two variants of the described method, which differ in their final step. The first is a provably convergent approximation to the Minimum Mean Square Error (MMSE) estimator, relying on the generative model and applying a weighted average over the recovered solutions. The second is a relaxed variant of the former that simply applies an empirical mean. We show that both methods provide a computationally efficient approximation to the MMSE estimator, which is typically intractable to compute. We demonstrate our findings empirically and provide a theoretical analysis of our method under several different cases.
Tasks
Published	2018-06-26
URL	http://arxiv.org/abs/1806.10171v5
PDF	http://arxiv.org/pdf/1806.10171v5.pdf
PWC	https://paperswithcode.com/paper/mmse-approximation-for-sparse-coding
Repo
Framework