October 19, 2019

3229 words 16 mins read

Paper Group ANR 122

Channel Attention and Multi-level Features Fusion for Single Image Super-Resolution. Online Adaptive Image Reconstruction (OnAIR) Using Dictionary Models. The Window Validity Problem in Rule-Based Stream Reasoning. PDNet: Semantic Segmentation integrated with a Primal-Dual Network for Document binarization. A Model for General Intelligence. Kinetic …

Channel Attention and Multi-level Features Fusion for Single Image Super-Resolution


Title	Channel Attention and Multi-level Features Fusion for Single Image Super-Resolution
Authors	Yue Lu, Yun Zhou, Zhuqing Jiang, Xiaoqiang Guo, Zixuan Yang
Abstract	Convolutional neural networks (CNNs) have demonstrated superior performance in super-resolution (SR). However, most CNN-based SR methods neglect the different importance among feature channels or fail to take full advantage of the hierarchical features. To address these issues, this paper presents a novel recursive unit. Firstly, at the beginning of each unit, we adopt a compact channel attention mechanism to adaptively recalibrate the channel importance of input features. Then, the multi-level features, rather than only deep-level features, are extracted and fused. Additionally, we find that it will force our model to learn more details by using the learnable upsampling method (i.e., transposed convolution) only on residual branch (instead of using it both on residual branch and identity branch) while using the bicubic interpolation on the other branch. Analytic experiments show that our method achieves competitive results compared with the state-of-the-art methods and maintains faster speed as well.
Tasks	Image Super-Resolution, Super-Resolution
Published	2018-10-16
URL	http://arxiv.org/abs/1810.06935v1
PDF	http://arxiv.org/pdf/1810.06935v1.pdf
PWC	https://paperswithcode.com/paper/channel-attention-and-multi-level-features
Repo
Framework

Online Adaptive Image Reconstruction (OnAIR) Using Dictionary Models


Title	Online Adaptive Image Reconstruction (OnAIR) Using Dictionary Models
Authors	Brian E. Moore, Saiprasad Ravishankar, Raj Rao Nadakuditi, Jeffrey A. Fessler
Abstract	Sparsity and low-rank models have been popular for reconstructing images and videos from limited or corrupted measurements. Dictionary or transform learning methods are useful in applications such as denoising, inpainting, and medical image reconstruction. This paper proposes a framework for online (or time-sequential) adaptive reconstruction of dynamic image sequences from linear (typically undersampled) measurements. We model the spatiotemporal patches of the underlying dynamic image sequence as sparse in a dictionary, and we simultaneously estimate the dictionary and the images sequentially from streaming measurements. Multiple constraints on the adapted dictionary are also considered such as a unitary matrix, or low-rank dictionary atoms that provide additional efficiency or robustness. The proposed online algorithms are memory efficient and involve simple updates of the dictionary atoms, sparse coefficients, and images. Numerical experiments demonstrate the usefulness of the proposed methods in inverse problems such as video reconstruction or inpainting from noisy, subsampled pixels, and dynamic magnetic resonance image reconstruction from very limited measurements.
Tasks	Denoising, Image Reconstruction, Video Reconstruction
Published	2018-09-06
URL	https://arxiv.org/abs/1809.01817v3
PDF	https://arxiv.org/pdf/1809.01817v3.pdf
PWC	https://paperswithcode.com/paper/online-adaptive-image-reconstruction-onair
Repo
Framework

The Window Validity Problem in Rule-Based Stream Reasoning


Title	The Window Validity Problem in Rule-Based Stream Reasoning
Authors	Alessandro Ronca, Mark Kaminski, Bernardo Cuenca Grau, Ian Horrocks
Abstract	Rule-based temporal query languages provide the expressive power and flexibility required to capture in a natural way complex analysis tasks over streaming data. Stream processing applications, however, typically require near real-time response using limited resources. In particular, it becomes essential that the underpinning query language has favourable computational properties and that stream processing algorithms are able to keep only a small number of previously received facts in memory at any point in time without sacrificing correctness. In this paper, we propose a recursive fragment of temporal Datalog with tractable data complexity and study the properties of a generic stream reasoning algorithm for this fragment. We focus on the window validity problem as a way to minimise the number of time points for which the stream reasoning algorithm needs to keep data in memory at any point in time.
Tasks
Published	2018-08-07
URL	http://arxiv.org/abs/1808.02291v3
PDF	http://arxiv.org/pdf/1808.02291v3.pdf
PWC	https://paperswithcode.com/paper/the-window-validity-problem-in-rule-based
Repo
Framework

PDNet: Semantic Segmentation integrated with a Primal-Dual Network for Document binarization


Title	PDNet: Semantic Segmentation integrated with a Primal-Dual Network for Document binarization
Authors	Kalyan Ram Ayyalasomayajula, Filip Malmberg, Anders Brun
Abstract	Binarization of digital documents is the task of classifying each pixel in an image of the document as belonging to the background (parchment/paper) or foreground (text/ink). Historical documents are often subjected to degradations, that make the task challenging. In the current work a deep neural network architecture is proposed that combines a fully convolutional network with an unrolled primal-dual network that can be trained end-to-end to achieve state of the art binarization on four out of seven datasets. Document binarization is formulated as an energy minimization problem. A fully convolutional neural network is trained for semantic segmentation of pixels that provides labeling cost associated with each pixel. This cost estimate is refined along the edges to compensate for any over or under estimation of the foreground class using a primal-dual approach. We provide necessary overview on proximal operator that facilitates theoretical underpinning required to train a primal-dual network using a gradient descent algorithm. Numerical instabilities encountered due to the recurrent nature of primal-dual approach are handled. We provide experimental results on document binarization competition dataset along with network changes and hyperparameter tuning required for stability and performance of the network. The network when pre-trained on synthetic dataset performs better as per the competition metrics.
Tasks	Document Binarization, Semantic Segmentation
Published	2018-01-26
URL	http://arxiv.org/abs/1801.08694v3
PDF	http://arxiv.org/pdf/1801.08694v3.pdf
PWC	https://paperswithcode.com/paper/pdnet-semantic-segmentation-integrated-with-a
Repo
Framework

A Model for General Intelligence


Title	A Model for General Intelligence
Authors	Paul Yaworsky
Abstract	The overarching problem in artificial intelligence (AI) is that we do not understand the intelligence process well enough to enable the development of adequate computational models. Much work has been done in AI over the years at lower levels, but a big part of what has been missing involves the high level, abstract, general nature of intelligence. We address this gap by developing a model for general intelligence. To accomplish this, we focus on three basic aspects of intelligence. First, we must realize the general order and nature of intelligence at a high level. Second, we must come to know what these realizations mean with respect to the overall intelligence process. Third, we must describe these realizations as clearly as possible. We propose a hierarchical model to help capture and exploit the order within intelligence. The underlying order involves patterns of signals that become organized, stored and activated in space and time. These patterns can be described using a simple, general hierarchy, with physical signals at the lowest level, information in the middle, and abstract signal representations at the top. This high level perspective provides a big picture that literally helps us see the intelligence process, thereby enabling fundamental realizations, a better understanding and clear descriptions of the intelligence process. The resulting model can be used to support all kinds of information processing across multiple levels of abstraction. As computer technology improves, and as cooperation increases between humans and computers, people will become more efficient and more productive in performing their information processing tasks.
Tasks
Published	2018-11-06
URL	http://arxiv.org/abs/1811.02546v2
PDF	http://arxiv.org/pdf/1811.02546v2.pdf
PWC	https://paperswithcode.com/paper/a-model-for-general-intelligence
Repo
Framework

Kinetic Compressive Sensing


Title	Kinetic Compressive Sensing
Authors	Michele Scipioni, Maria F. Santarelli, Luigi Landini, Ciprian Catana, Douglas N. Greve, Julie C. Price, Stefano Pedemonte
Abstract	Parametric images provide insight into the spatial distribution of physiological parameters, but they are often extremely noisy, due to low SNR of tomographic data. Direct estimation from projections allows accurate noise modeling, improving the results of post-reconstruction fitting. We propose a method, which we name kinetic compressive sensing (KCS), based on a hierarchical Bayesian model and on a novel reconstruction algorithm, that encodes sparsity of kinetic parameters. Parametric maps are reconstructed by maximizing the joint probability, with an Iterated Conditional Modes (ICM) approach, alternating the optimization of activity time series (OS-MAP-OSL), and kinetic parameters (MAP-LM). We evaluated the proposed algorithm on a simulated dynamic phantom: a bias/variance study confirmed how direct estimates can improve the quality of parametric maps over a post-reconstruction fitting, and showed how the novel sparsity prior can further reduce their variance, without affecting bias. Real FDG PET human brain data (Siemens mMR, 40min) images were also processed. Results enforced how the proposed KCS-regularized direct method can produce spatially coherent images and parametric maps, with lower spatial noise and better tissue contrast. A GPU-based open source implementation of the algorithm is provided.
Tasks	Compressive Sensing, Time Series
Published	2018-03-27
URL	http://arxiv.org/abs/1803.10045v1
PDF	http://arxiv.org/pdf/1803.10045v1.pdf
PWC	https://paperswithcode.com/paper/kinetic-compressive-sensing
Repo
Framework

Exploiting Semantics in Adversarial Training for Image-Level Domain Adaptation


Title	Exploiting Semantics in Adversarial Training for Image-Level Domain Adaptation
Authors	Pierluigi Zama Ramirez, Alessio Tonioni, Luigi Di Stefano
Abstract	Performance achievable by modern deep learning approaches are directly related to the amount of data used at training time. Unfortunately, the annotation process is notoriously tedious and expensive, especially for pixel-wise tasks like semantic segmentation. Recent works have proposed to rely on synthetically generated imagery to ease the training set creation. However, models trained on these kind of data usually under-perform on real images due to the well known issue of domain shift. We address this problem by learning a domain-to-domain image translation GAN to shrink the gap between real and synthetic images. Peculiarly to our method, we introduce semantic constraints into the generation process to both avoid artifacts and guide the synthesis. To prove the effectiveness of our proposal, we show how a semantic segmentation CNN trained on images from the synthetic GTA dataset adapted by our method can improve performance by more than 16% mIoU with respect to the same model trained on synthetic images.
Tasks	Domain Adaptation, Semantic Segmentation
Published	2018-10-13
URL	http://arxiv.org/abs/1810.05852v1
PDF	http://arxiv.org/pdf/1810.05852v1.pdf
PWC	https://paperswithcode.com/paper/exploiting-semantics-in-adversarial-training
Repo
Framework

Understanding Weight Normalized Deep Neural Networks with Rectified Linear Units


Title	Understanding Weight Normalized Deep Neural Networks with Rectified Linear Units
Authors	Yixi Xu, Xiao Wang
Abstract	This paper presents a general framework for norm-based capacity control for $L_{p,q}$ weight normalized deep neural networks. We establish the upper bound on the Rademacher complexities of this family. With an $L_{p,q}$ normalization where $q\le p^$, and $1/p+1/p^{}=1$, we discuss properties of a width-independent capacity control, which only depends on depth by a square root term. We further analyze the approximation properties of $L_{p,q}$ weight normalized deep neural networks. In particular, for an $L_{1,\infty}$ weight normalized network, the approximation error can be controlled by the $L_1$ norm of the output layer, and the corresponding generalization error only depends on the architecture by the square root of the depth.
Tasks
Published	2018-10-03
URL	http://arxiv.org/abs/1810.01877v3
PDF	http://arxiv.org/pdf/1810.01877v3.pdf
PWC	https://paperswithcode.com/paper/understanding-weight-normalized-deep-neural
Repo
Framework

Detect, anticipate and generate: Semi-supervised recurrent latent variable models for human activity modeling


Title	Detect, anticipate and generate: Semi-supervised recurrent latent variable models for human activity modeling
Authors	Judith Bütepage, Danica Kragic
Abstract	Successful Human-Robot collaboration requires a predictive model of human behavior. The robot needs to be able to recognize current goals and actions and to predict future activities in a given context. However, the spatio-temporal sequence of human actions is difficult to model since latent factors such as intention, task, knowledge, intuition and preference determine the action choices of each individual. In this work we introduce semi-supervised variational recurrent neural networks which are able to a) model temporal distributions over latent factors and the observable feature space, b) incorporate discrete labels such as activity type when available, and c) generate possible future action sequences on both feature and label level. We evaluate our model on the Cornell Activity Dataset CAD-120 dataset. Our model outperforms state-of-the-art approaches in both activity and affordance detection and anticipation. Additionally, we show how samples of possible future action sequences are in line with past observations.
Tasks	Latent Variable Models
Published	2018-09-19
URL	http://arxiv.org/abs/1809.07075v1
PDF	http://arxiv.org/pdf/1809.07075v1.pdf
PWC	https://paperswithcode.com/paper/detect-anticipate-and-generate-semi
Repo
Framework

Fairness Through Causal Awareness: Learning Latent-Variable Models for Biased Data


Title	Fairness Through Causal Awareness: Learning Latent-Variable Models for Biased Data
Authors	David Madras, Elliot Creager, Toniann Pitassi, Richard Zemel
Abstract	How do we learn from biased data? Historical datasets often reflect historical prejudices; sensitive or protected attributes may affect the observed treatments and outcomes. Classification algorithms tasked with predicting outcomes accurately from these datasets tend to replicate these biases. We advocate a causal modeling approach to learning from biased data, exploring the relationship between fair classification and intervention. We propose a causal model in which the sensitive attribute confounds both the treatment and the outcome. Building on prior work in deep learning and generative modeling, we describe how to learn the parameters of this causal model from observational data alone, even in the presence of unobserved confounders. We show experimentally that fairness-aware causal modeling provides better estimates of the causal effects between the sensitive attribute, the treatment, and the outcome. We further present evidence that estimating these causal effects can help learn policies that are both more accurate and fair, when presented with a historically biased dataset.
Tasks	Latent Variable Models
Published	2018-09-07
URL	http://arxiv.org/abs/1809.02519v3
PDF	http://arxiv.org/pdf/1809.02519v3.pdf
PWC	https://paperswithcode.com/paper/fairness-through-causal-awareness-learning
Repo
Framework

Online convex optimization for cumulative constraints


Title	Online convex optimization for cumulative constraints
Authors	Jianjun Yuan, Andrew Lamperski
Abstract	We propose the algorithms for online convex optimization which lead to cumulative squared constraint violations of the form $\sum\limits_{t=1}^T\big([g(x_t)]_+\big)^2=O(T^{1-\beta})$, where $\beta\in(0,1)$. Previous literature has focused on long-term constraints of the form $\sum\limits_{t=1}^Tg(x_t)$. There, strictly feasible solutions can cancel out the effects of violated constraints. In contrast, the new form heavily penalizes large constraint violations and cancellation effects cannot occur. Furthermore, useful bounds on the single step constraint violation $[g(x_t)]_+$ are derived. For convex objectives, our regret bounds generalize existing bounds, and for strongly convex objectives we give improved regret bounds. In numerical experiments, we show that our algorithm closely follows the constraint boundary leading to low cumulative violation.
Tasks
Published	2018-02-19
URL	http://arxiv.org/abs/1802.06472v4
PDF	http://arxiv.org/pdf/1802.06472v4.pdf
PWC	https://paperswithcode.com/paper/online-convex-optimization-for-cumulative
Repo
Framework

Reference Model of Multi-Entity Bayesian Networks for Predictive Situation Awareness


Title	Reference Model of Multi-Entity Bayesian Networks for Predictive Situation Awareness
Authors	Cheol Young Park, Kathryn Blackmond Laskey
Abstract	During the past quarter-century, situation awareness (SAW) has become a critical research theme, because of its importance. Since the concept of SAW was first introduced during World War I, various versions of SAW have been researched and introduced. Predictive Situation Awareness (PSAW) focuses on the ability to predict aspects of a temporally evolving situation over time. PSAW requires a formal representation and a reasoning method using such a representation. A Multi-Entity Bayesian Network (MEBN) is a knowledge representation formalism combining Bayesian Networks (BN) with First-Order Logic (FOL). MEBN can be used to represent uncertain situations (supported by BN) as well as complex situations (supported by FOL). Also, efficient reasoning algorithms for MEBN have been developed. MEBN can be a formal representation to support PSAW and has been used for several PSAW systems. Although several MEBN applications for PSAW exist, very little work can be found in the literature that attempts to generalize a MEBN model to support PSAW. In this research, we define a reference model for MEBN in PSAW, called a PSAW-MEBN reference model. The PSAW-MEBN reference model enables us to easily develop a MEBN model for PSAW by supporting the design of a MEBN model for PSAW. In this research, we introduce two example use cases using the PSAW-MEBN reference model to develop MEBN models to support PSAW: a Smart Manufacturing System and a Maritime Domain Awareness System.
Tasks
Published	2018-06-06
URL	http://arxiv.org/abs/1806.02457v2
PDF	http://arxiv.org/pdf/1806.02457v2.pdf
PWC	https://paperswithcode.com/paper/reference-model-of-multi-entity-bayesian
Repo
Framework


Title	Semi-Blind Inference of Topologies and Dynamical Processes over Graphs
Authors	Vassilis N. Ioannidis, Yanning Shen, Georgios B. Giannakis
Abstract	Network science provides valuable insights across numerous disciplines including sociology, biology, neuroscience and engineering. A task of major practical importance in these application domains is inferring the network structure from noisy observations at a subset of nodes. Available methods for topology inference typically assume that the process over the network is observed at all nodes. However, application-specific constraints may prevent acquiring network-wide observations. Alleviating the limited flexibility of existing approaches, this work advocates structural models for graph processes and develops novel algorithms for joint inference of the network topology and processes from partial nodal observations. Structural equation models (SEMs) and structural vector autoregressive models (SVARMs) have well-documented merits in identifying even directed topologies of complex graphs; while SEMs capture contemporaneous causal dependencies among nodes, SVARMs further account for time-lagged influences. This paper develops algorithms that iterate between inferring directed graphs that “best” fit the data, and estimating the network processes at reduced computational complexity by leveraging tools related to Kalman smoothing. To further accommodate delay-sensitive applications, an online joint inference approach is put forth that even tracks time-evolving topologies. Furthermore, conditions for identifying the network topology given partial observations are specified. It is proved that the required number of observations for unique identification reduces significantly when the network structure is sparse. Numerical tests with synthetic as well as real datasets corroborate the effectiveness of the novel approach.
Tasks
Published	2018-05-16
URL	http://arxiv.org/abs/1805.06095v1
PDF	http://arxiv.org/pdf/1805.06095v1.pdf
PWC	https://paperswithcode.com/paper/semi-blind-inference-of-topologies-and
Repo
Framework

Sample complexity of partition identification using multi-armed bandits


Title	Sample complexity of partition identification using multi-armed bandits
Authors	Sandeep Juneja, Subhashini Krishnasamy
Abstract	Given a vector of probability distributions, or arms, each of which can be sampled independently, we consider the problem of identifying the partition to which this vector belongs from a finitely partitioned universe of such vector of distributions. We study this as a pure exploration problem in multi armed bandit settings and develop sample complexity bounds on the total mean number of samples required for identifying the correct partition with high probability. This framework subsumes well studied problems such as finding the best arm or the best few arms. We consider distributions belonging to the single parameter exponential family and primarily consider partitions where the vector of means of arms lie either in a given set or its complement. The sets considered correspond to distributions where there exists a mean above a specified threshold, where the set is a half space and where either the set or its complement is a polytope, or more generally, a convex set. In these settings, we characterize the lower bounds on mean number of samples for each arm highlighting their dependence on the problem geometry. Further, inspired by the lower bounds, we propose algorithms that can match these bounds asymptotically with decreasing probability of error. Applications of this framework may be diverse. We briefly discuss one associated with finance.
Tasks	Multi-Armed Bandits
Published	2018-11-14
URL	http://arxiv.org/abs/1811.05654v2
PDF	http://arxiv.org/pdf/1811.05654v2.pdf
PWC	https://paperswithcode.com/paper/sample-complexity-of-partition-identification
Repo
Framework

Globally Continuous and Non-Markovian Activity Analysis from Videos


Title	Globally Continuous and Non-Markovian Activity Analysis from Videos
Authors	He Wang, Carol O’Sullivan
Abstract	Automatically recognizing activities in video is a classic problem in vision and helps to understand behaviors, describe scenes and detect anomalies. We propose an unsupervised method for such purposes. Given video data, we discover recurring activity patterns that appear, peak, wane and disappear over time. By using non-parametric Bayesian methods, we learn coupled spatial and temporal patterns with minimum prior knowledge. To model the temporal changes of patterns, previous works compute Markovian progressions or locally continuous motifs whereas we model time in a globally continuous and non-Markovian way. Visually, the patterns depict flows of major activities. Temporally, each pattern has its own unique appearance-disappearance cycles. To compute compact pattern representations, we also propose a hybrid sampling method. By combining these patterns with detailed environment information, we interpret the semantics of activities and report anomalies. Also, our method fits data better and detects anomalies that were difficult to detect previously.
Tasks
Published	2018-10-11
URL	http://arxiv.org/abs/1810.04954v1
PDF	http://arxiv.org/pdf/1810.04954v1.pdf
PWC	https://paperswithcode.com/paper/globally-continuous-and-non-markovian
Repo
Framework