January 30, 2020

3206 words 16 mins read

Paper Group ANR 199

Weakly Labeling the Antarctic: The Penguin Colony Case. Unseen Object Segmentation in Videos via Transferable Representations. Machine Learning for Geometrically-Consistent Angular Spread Function Estimation in Massive MIMO. L2P: An Algorithm for Estimating Heavy-tailed Outcomes. LYRICS: a General Interface Layer to Integrate Logic Inference and De …

Weakly Labeling the Antarctic: The Penguin Colony Case


Title	Weakly Labeling the Antarctic: The Penguin Colony Case
Authors	Hieu Le, Bento Gonçalves, Dimitris Samaras, Heather Lynch
Abstract	Antarctic penguins are important ecological indicators – especially in the face of climate change. In this work, we present a deep learning based model for semantic segmentation of Ad'elie penguin colonies in high-resolution satellite imagery. To train our segmentation models, we take advantage of the Penguin Colony Dataset: a unique dataset with 2044 georeferenced cropped images from 193 Ad'elie penguin colonies in Antarctica. In the face of a scarcity of pixel-level annotation masks, we propose a weakly-supervised framework to effectively learn a segmentation model from weak labels. We use a classification network to filter out data unsuitable for the segmentation network. This segmentation network is trained with a specific loss function, based on the average activation, to effectively learn from the data with the weakly-annotated labels. Our experiments show that adding weakly-annotated training examples significantly improves segmentation performance, increasing the mean Intersection-over-Union from 42.3 to 60.0% on the Penguin Colony Dataset.
Tasks	Semantic Segmentation
Published	2019-05-08
URL	https://arxiv.org/abs/1905.03313v2
PDF	https://arxiv.org/pdf/1905.03313v2.pdf
PWC	https://paperswithcode.com/paper/190503313
Repo
Framework

Unseen Object Segmentation in Videos via Transferable Representations


Title	Unseen Object Segmentation in Videos via Transferable Representations
Authors	Yi-Wen Chen, Yi-Hsuan Tsai, Chu-Ya Yang, Yen-Yu Lin, Ming-Hsuan Yang
Abstract	In order to learn object segmentation models in videos, conventional methods require a large amount of pixel-wise ground truth annotations. However, collecting such supervised data is time-consuming and labor-intensive. In this paper, we exploit existing annotations in source images and transfer such visual information to segment videos with unseen object categories. Without using any annotations in the target video, we propose a method to jointly mine useful segments and learn feature representations that better adapt to the target frames. The entire process is decomposed into two tasks: 1) solving a submodular function for selecting object-like segments, and 2) learning a CNN model with a transferable module for adapting seen categories in the source domain to the unseen target video. We present an iterative update scheme between two tasks to self-learn the final solution for object segmentation. Experimental results on numerous benchmark datasets show that the proposed method performs favorably against the state-of-the-art algorithms.
Tasks	Semantic Segmentation
Published	2019-01-08
URL	http://arxiv.org/abs/1901.02444v1
PDF	http://arxiv.org/pdf/1901.02444v1.pdf
PWC	https://paperswithcode.com/paper/unseen-object-segmentation-in-videos-via
Repo
Framework

Machine Learning for Geometrically-Consistent Angular Spread Function Estimation in Massive MIMO


Title	Machine Learning for Geometrically-Consistent Angular Spread Function Estimation in Massive MIMO
Authors	Yi Song, Mahdi Barzegar Khalilsarai, Saeid Haghighatshoar, Giuseppe Caire
Abstract	In the spatial channel models used in multi-antenna wireless communications, the propagation from a single-antenna transmitter (e.g., a user) to an M-antenna receiver (e.g., a Base Station) occurs through scattering clusters located in the far field of the receiving antenna array. The Angular Spread Function (ASF) of the corresponding M-dim channel vector describes the angular density of the received signal power at the array. The modern literature on massive MIMO has recognized that the knowledge of covariance matrix of user channel vectors is very useful for various applications such as hybrid digital analog beamforming, pilot decontamination, etc. Therefore, most literature has focused on the estimation of such channel covariance matrices. However, in some applications such as uplink-downlink covariance transformation (for FDD massive MIMO precoding) and channel sounding some form of ASF estimation is required either implicitly or explicitly. It turns out that while covariance estimation is well-known and well-conditioned, the ASF estimation is a much harder problem and is in general ill-posed. In this paper, we show that under additional geometrically-consistent group-sparsity structure on the ASF, which is prevalent in almost all wireless propagation scenarios, one is able to estimate ASF properly. We propose sparse dictionary-based algorithms that promote this group-sparsity structure via suitable regularizations. Since generally it is difficult to capture the notion of group-sparsity through proper regularization, we propose another algorithm based on Deep Neural Networks (DNNs) that learns this structure. We provide numerical simulations to assess the performance of our proposed algorithms. We also compare the results with that of other methods in the literature, where we re-frame those methods in the context of ASF estimation in massive MIMO.
Tasks
Published	2019-10-30
URL	https://arxiv.org/abs/1910.13795v1
PDF	https://arxiv.org/pdf/1910.13795v1.pdf
PWC	https://paperswithcode.com/paper/machine-learning-for-geometrically-consistent
Repo
Framework

L2P: An Algorithm for Estimating Heavy-tailed Outcomes


Title	L2P: An Algorithm for Estimating Heavy-tailed Outcomes
Authors	Xindi Wang, Onur Varol, Tina Eliassi-Rad
Abstract	Many real-world prediction tasks have outcome (a.k.a.~target or response) variables that have characteristic heavy-tail distributions. Examples include copies of books sold, auction prices of art pieces, etc. By learning heavy-tailed distributions, ``big and rare’’ instances (e.g., the best-sellers) will have accurate predictions. Most existing approaches are not dedicated to learning heavy-tailed distribution; thus, they heavily under-predict such instances. To tackle this problem, we introduce \emph{Learning to Place} (\texttt{L2P}), which exploits the pairwise relationships between instances to learn from a proportionally higher number of rare instances. \texttt{L2P} consists of two stages. In Stage 1, \texttt{L2P} learns a pairwise preference classifier: \textit{is instance A $>$ instance B?}. In Stage 2, \texttt{L2P} learns to place a new instance into an ordinal ranking of known instances. Based on its placement, the new instance is then assigned a value for its outcome variable. Experiments on real data show that \texttt{L2P} outperforms competing approaches in terms of accuracy and capability to reproduce heavy-tailed outcome distribution. In addition, \texttt{L2P} can provide an interpretable model with explainable outcomes by placing each predicted instance in context with its comparable neighbors. \|
Tasks
Published	2019-08-13
URL	https://arxiv.org/abs/1908.04628v1
PDF	https://arxiv.org/pdf/1908.04628v1.pdf
PWC	https://paperswithcode.com/paper/l2p-an-algorithm-for-estimating-heavy-tailed
Repo
Framework

LYRICS: a General Interface Layer to Integrate Logic Inference and Deep Learning


Title	LYRICS: a General Interface Layer to Integrate Logic Inference and Deep Learning
Authors	Giuseppe Marra, Francesco Giannini, Michelangelo Diligenti, Marco Gori
Abstract	In spite of the amazing results obtained by deep learning in many applications, a real intelligent behavior of an agent acting in a complex environment is likely to require some kind of higher-level symbolic inference. Therefore, there is a clear need for the definition of a general and tight integration between low-level tasks, processing sensorial data that can be effectively elaborated using deep learning techniques, and the logic reasoning that allows humans to take decisions in complex environments. This paper presents LYRICS, a generic interface layer for AI, which is implemented in TersorFlow (TF). LYRICS provides an input language that allows to define arbitrary First Order Logic (FOL) background knowledge. The predicates and functions of the FOL knowledge can be bound to any TF computational graph, and the formulas are converted into a set of real-valued constraints, which participate to the overall optimization problem. This allows to learn the weights of the learners, under the constraints imposed by the prior knowledge. The framework is extremely general as it imposes no restrictions in terms of which models or knowledge can be integrated. In this paper, we show the generality of the approach showing some use cases of the presented language, including model checking, supervised learning and collective classification.
Tasks
Published	2019-03-18
URL	https://arxiv.org/abs/1903.07534v2
PDF	https://arxiv.org/pdf/1903.07534v2.pdf
PWC	https://paperswithcode.com/paper/lyrics-a-general-interface-layer-to-integrate
Repo
Framework

Operationalizing Individual Fairness with Pairwise Fair Representations


Title	Operationalizing Individual Fairness with Pairwise Fair Representations
Authors	Preethi Lahoti, Krishna P. Gummadi, Gerhard Weikum
Abstract	We revisit the notion of individual fairness proposed by Dwork et al. A central challenge in operationalizing their approach is the difficulty in eliciting a human specification of a similarity metric. In this paper, we propose an operationalization of individual fairness that does not rely on a human specification of a distance metric. Instead, we propose novel approaches to elicit and leverage side-information on equally deserving individuals to counter subordination between social groups. We model this knowledge as a fairness graph, and learn a unified Pairwise Fair Representation (PFR) of the data that captures both data-driven similarity between individuals and the pairwise side-information in fairness graph. We elicit fairness judgments from a variety of sources, including human judgments for two real-world datasets on recidivism prediction (COMPAS) and violent neighborhood prediction (Crime & Communities). Our experiments show that the PFR model for operationalizing individual fairness is practically viable.
Tasks
Published	2019-07-02
URL	https://arxiv.org/abs/1907.01439v2
PDF	https://arxiv.org/pdf/1907.01439v2.pdf
PWC	https://paperswithcode.com/paper/operationalizing-individual-fairness-with
Repo
Framework

A New Tensioning Method using Deep Reinforcement Learning for Surgical Pattern Cutting


Title	A New Tensioning Method using Deep Reinforcement Learning for Surgical Pattern Cutting
Authors	Thanh Thi Nguyen, Ngoc Duy Nguyen, Fernando Bello, Saeid Nahavandi
Abstract	Surgeons normally need surgical scissors and tissue grippers to cut through a deformable surgical tissue. The cutting accuracy depends on the skills to manipulate these two tools. Such skills are part of basic surgical skills training as in the Fundamentals of Laparoscopic Surgery. The gripper is used to pinch a point on the surgical sheet and pull the tissue to a certain direction to maintain the tension while the scissors cut through a trajectory. As the surgical materials are deformable, it requires a comprehensive tensioning policy to yield appropriate tensioning direction at each step of the cutting process. Automating a tensioning policy for a given cutting trajectory will support not only the human surgeons but also the surgical robots to improve the cutting accuracy and reliability. This paper presents a multiple pinch point approach to modelling an autonomous tensioning planner based on a deep reinforcement learning algorithm. Experiments on a simulator show that the proposed method is superior to existing methods in terms of both performance and robustness.
Tasks
Published	2019-01-10
URL	http://arxiv.org/abs/1901.03327v1
PDF	http://arxiv.org/pdf/1901.03327v1.pdf
PWC	https://paperswithcode.com/paper/a-new-tensioning-method-using-deep
Repo
Framework

Ignorance-Aware Approaches and Algorithms for Prototype Selection in Machine Learning


Title	Ignorance-Aware Approaches and Algorithms for Prototype Selection in Machine Learning
Authors	Vagan Terziyan, Anton Nikulin
Abstract	Operating with ignorance is an important concern of the Machine Learning research, especially when the objective is to discover knowledge from the imperfect data. Data mining (driven by appropriate knowledge discovery tools) is about processing available (observed, known and understood) samples of data aiming to build a model (e.g., a classifier) to handle data samples, which are not yet observed, known or understood. These tools traditionally take samples of the available data (known facts) as an input for learning. We want to challenge the indispensability of this approach and we suggest considering the things the other way around. What if the task would be as follows: how to learn a model based on our ignorance, i.e. by processing the shape of ‘voids’ within the available data space? Can we improve traditional classification by modeling also the ignorance? In this paper, we provide some algorithms for the discovery and visualizing of the ignorance zones in two-dimensional data spaces and design two ignorance-aware smart prototype selection techniques (incremental and adversarial) to improve the performance of the nearest neighbor classifiers. We present experiments with artificial and real datasets to test the concept of the usefulness of ignorance discovery in machine learning.
Tasks
Published	2019-05-15
URL	https://arxiv.org/abs/1905.06054v1
PDF	https://arxiv.org/pdf/1905.06054v1.pdf
PWC	https://paperswithcode.com/paper/ignorance-aware-approaches-and-algorithms-for
Repo
Framework

RelEmb: A relevance-based application embedding for Mobile App retrieval and categorization


Title	RelEmb: A relevance-based application embedding for Mobile App retrieval and categorization
Authors	Ahsaas Bajaj, Shubham Krishna, Mukund Rungta, Hemant Tiwari, Vanraj Vala
Abstract	Information Retrieval Systems have revolutionized the organization and extraction of Information. In recent years, mobile applications (apps) have become primary tools of collecting and disseminating information. However, limited research is available on how to retrieve and organize mobile apps on users’ devices. In this paper, authors propose a novel method to estimate app-embeddings which are then applied to tasks like app clustering, classification, and retrieval. Usage of app-embedding for query expansion, nearest neighbor analysis enables unique and interesting use cases to enhance end-user experience with mobile apps.
Tasks	Information Retrieval
Published	2019-04-14
URL	http://arxiv.org/abs/1904.06672v1
PDF	http://arxiv.org/pdf/1904.06672v1.pdf
PWC	https://paperswithcode.com/paper/relemb-a-relevance-based-application
Repo
Framework

Accelerated Motion-Aware MR Imaging via Motion Prediction from K-Space Center


Title	Accelerated Motion-Aware MR Imaging via Motion Prediction from K-Space Center
Authors	Christoph Jud, Damien Nguyen, Alina Giger, Robin Sandkühler, Miriam Krieger, Tony Lomax, Rares Salomir, Oliver Bieri, Philippe C. Cattin
Abstract	Motion has been a challenge for magnetic resonance (MR) imaging ever since the MR has been invented. Especially in volumetric imaging of thoracic and abdominal organs, motion-awareness is essential for reducing motion artifacts in the final image. A recently proposed MR imaging approach copes with motion by observing the motion patterns during the acquisition. Repetitive scanning of the k-space center region enables the extraction of the patient motion while acquiring the remaining part of the k-space. Due to highly redundant measurements of the center, the required scanning time of over 11 min and the reconstruction time of 2 h exceed clinical applicability though. We propose an accelerated motion-aware MR imaging method where the motion is inferred from small-sized k-space center patches and an initial training phase during which the characteristic movements are modeled. Thereby, acquisition times are reduced by a factor of almost 2 and reconstruction times by two orders of magnitude. Moreover, we improve the existing motion-aware approach with a systematic temporal shift correction to achieve a sharper image reconstruction. We tested our method on 12 volunteers and scanned their lungs and abdomen under free breathing. We achieved equivalent to higher reconstruction quality using the motion-prediction compared to the slower existing approach.
Tasks	Image Reconstruction, motion prediction
Published	2019-08-26
URL	https://arxiv.org/abs/1908.09560v1
PDF	https://arxiv.org/pdf/1908.09560v1.pdf
PWC	https://paperswithcode.com/paper/accelerated-motion-aware-mr-imaging-via
Repo
Framework

Inundation Modeling in Data Scarce Regions


Title	Inundation Modeling in Data Scarce Regions
Authors	Zvika Ben-Haim, Vladimir Anisimov, Aaron Yonas, Varun Gulshan, Yusef Shafi, Stephan Hoyer, Sella Nevo
Abstract	Flood forecasts are crucial for effective individual and governmental protective action. The vast majority of flood-related casualties occur in developing countries, where providing spatially accurate forecasts is a challenge due to scarcity of data and lack of funding. This paper describes an operational system providing flood extent forecast maps covering several flood-prone regions in India, with the goal of being sufficiently scalable and cost-efficient to facilitate the establishment of effective flood forecasting systems globally.
Tasks
Published	2019-10-11
URL	https://arxiv.org/abs/1910.05006v2
PDF	https://arxiv.org/pdf/1910.05006v2.pdf
PWC	https://paperswithcode.com/paper/inundation-modeling-in-data-scarce-regions
Repo
Framework

Understanding Limitation of Two Symmetrized Orders by Worst-case Complexity


Title	Understanding Limitation of Two Symmetrized Orders by Worst-case Complexity
Authors	Peijun Xiao, Zhisheng Xiao, Ruoyu SUn
Abstract	It was recently found that the standard version of multi-block cyclic ADMM diverges. Interestingly, Gaussian Back Substitution ADMM (GBS-ADMM) and symmetric Gauss-Seidel ADMM (sGS-ADMM) do not have the divergence issue. Therefore, it seems that symmetrization can improve the performance of the classical cyclic order. In another recent work, cyclic CD (Coordinate Descent) was shown to be $\mathcal{O}(n^2)$ times slower than randomized versions in the worst-case. A natural question arises: can the symmetrized orders achieve a faster convergence rate than the cyclic order, or even getting close to randomized versions? In this paper, we give a negative answer to this question. We show that both Gaussian Back Substitution and symmetric Gauss-Seidel order suffer from the same slow convergence issue as the cyclic order in the worst case. In particular, we prove that for unconstrained problems, they can be $\mathcal{O}(n^2)$ times slower than R-CD. For linearly constrained problems with quadratic objective, we empirically show the convergence speed of GBS-ADMM and sGS-ADMM can be roughly $\mathcal{O}(n^2)$ times slower than randomly permuted ADMM.
Tasks
Published	2019-10-10
URL	https://arxiv.org/abs/1910.04366v1
PDF	https://arxiv.org/pdf/1910.04366v1.pdf
PWC	https://paperswithcode.com/paper/understanding-limitation-of-two-symmetrized
Repo
Framework

GlidarCo: gait recognition by 3D skeleton estimation and biometric feature correction of flash lidar data


Title	GlidarCo: gait recognition by 3D skeleton estimation and biometric feature correction of flash lidar data
Authors	Nasrin Sadeghzadehyazdi, Tamal Batabyal, Nibir K. Dhar, B. O. Familoni, K. M. Iftekharuddin, Scott T. Acton
Abstract	Gait recognition using noninvasively acquired data has been attracting an increasing interest in the last decade. Among various modalities of data sources, it is experimentally found that the data involving skeletal representation are amenable for reliable feature compaction and fast processing. Model-based gait recognition methods that exploit features from a fitted model, like skeleton, are recognized for their view and scale-invariant properties. We propose a model-based gait recognition method, using sequences recorded by a single flash lidar. Existing state-of-the-art model-based approaches that exploit features from high quality skeletal data collected by Kinect and Mocap are limited to controlled laboratory environments. The performance of conventional research efforts is negatively affected by poor data quality. We address the problem of gait recognition under challenging scenarios, such as lower quality and noisy imaging process of lidar, that degrades the performance of state-of-the-art skeleton-based systems. We present GlidarCo to attain high accuracy on gait recognition under the described conditions. A filtering mechanism corrects faulty skeleton joint measurements, and robust statistics are integrated to conventional feature moments to encode the dynamic of the motion. As a comparison, length-based and vector-based features extracted from the noisy skeletons are investigated for outlier removal. Experimental results illustrate the efficacy of the proposed methodology in improving gait recognition given noisy low resolution lidar data.
Tasks	Gait Recognition
Published	2019-05-16
URL	https://arxiv.org/abs/1905.07058v2
PDF	https://arxiv.org/pdf/1905.07058v2.pdf
PWC	https://paperswithcode.com/paper/glidarco-gait-recognition-by-3d-skeleton
Repo
Framework

Zero-shot Domain Adaptation Based on Attribute Information


Title	Zero-shot Domain Adaptation Based on Attribute Information
Authors	Masato Ishii, Takashi Takenouchi, Masashi Sugiyama
Abstract	In this paper, we propose a novel domain adaptation method that can be applied without target data. We consider the situation where domain shift is caused by a prior change of a specific factor and assume that we know how the prior changes between source and target domains. We call this factor an attribute, and reformulate the domain adaptation problem to utilize the attribute prior instead of target data. In our method, the source data are reweighted with the sample-wise weight estimated by the attribute prior and the data themselves so that they are useful in the target domain. We theoretically reveal that our method provides more precise estimation of sample-wise transferability than a straightforward attribute-based reweighting approach. Experimental results with both toy datasets and benchmark datasets show that our method can perform well, though it does not use any target data.
Tasks	Domain Adaptation
Published	2019-03-13
URL	http://arxiv.org/abs/1903.05312v1
PDF	http://arxiv.org/pdf/1903.05312v1.pdf
PWC	https://paperswithcode.com/paper/zero-shot-domain-adaptation-based-on
Repo
Framework

Complex Cepstrum-based Decomposition of Speech for Glottal Source Estimation


Title	Complex Cepstrum-based Decomposition of Speech for Glottal Source Estimation
Authors	Thomas Drugman, Baris Bozkurt, Thierry Dutoit
Abstract	Homomorphic analysis is a well-known method for the separation of non-linearly combined signals. More particularly, the use of complex cepstrum for source-tract deconvolution has been discussed in various articles. However there exists no study which proposes a glottal flow estimation methodology based on cepstrum and reports effective results. In this paper, we show that complex cepstrum can be effectively used for glottal flow estimation by separating the causal and anticausal components of a windowed speech signal as done by the Zeros of the Z-Transform (ZZT) decomposition. Based on exactly the same principles presented for ZZT decomposition, windowing should be applied such that the windowed speech signals exhibit mixed-phase characteristics which conform the speech production model that the anticausal component is mainly due to the glottal flow open phase. The advantage of the complex cepstrum-based approach compared to the ZZT decomposition is its much higher speed.
Tasks
Published	2019-12-29
URL	https://arxiv.org/abs/1912.12602v1
PDF	https://arxiv.org/pdf/1912.12602v1.pdf
PWC	https://paperswithcode.com/paper/complex-cepstrum-based-decomposition-of
Repo
Framework