January 25, 2020

3320 words 16 mins read

Paper Group ANR 1673

DeGAN : Data-Enriching GAN for Retrieving Representative Samples from a Trained Classifier. Accurate and Fast Retrieval for Complex Non-metric Data via Neighborhood Graphs. Estimating Forces of Robotic Pouring Using a LSTM RNN. Domain Adaptation Regularization for Spectral Pruning. Mixture Modeling of Global Shape Priors and Autoencoding Local Inte …

DeGAN : Data-Enriching GAN for Retrieving Representative Samples from a Trained Classifier


Title	DeGAN : Data-Enriching GAN for Retrieving Representative Samples from a Trained Classifier
Authors	Sravanti Addepalli, Gaurav Kumar Nayak, Anirban Chakraborty, R. Venkatesh Babu
Abstract	In this era of digital information explosion, an abundance of data from numerous modalities is being generated as well as archived everyday. However, most problems associated with training Deep Neural Networks still revolve around lack of data that is rich enough for a given task. Data is required not only for training an initial model, but also for future learning tasks such as Model Compression and Incremental Learning. A diverse dataset may be used for training an initial model, but it may not be feasible to store it throughout the product life cycle due to data privacy issues or memory constraints. We propose to bridge the gap between the abundance of available data and lack of relevant data, for the future learning tasks of a given trained network. We use the available data, that may be an imbalanced subset of the original training dataset, or a related domain dataset, to retrieve representative samples from a trained classifier, using a novel Data-enriching GAN (DeGAN) framework. We demonstrate that data from a related domain can be leveraged to achieve state-of-the-art performance for the tasks of Data-free Knowledge Distillation and Incremental Learning on benchmark datasets. We further demonstrate that our proposed framework can enrich any data, even from unrelated domains, to make it more useful for the future learning tasks of a given network.
Tasks	Model Compression
Published	2019-12-27
URL	https://arxiv.org/abs/1912.11960v1
PDF	https://arxiv.org/pdf/1912.11960v1.pdf
PWC	https://paperswithcode.com/paper/degan-data-enriching-gan-for-retrieving
Repo
Framework

Accurate and Fast Retrieval for Complex Non-metric Data via Neighborhood Graphs


Title	Accurate and Fast Retrieval for Complex Non-metric Data via Neighborhood Graphs
Authors	Leonid Boytsov, Eric Nyberg
Abstract	We demonstrate that a graph-based search algorithm-relying on the construction of an approximate neighborhood graph-can directly work with challenging non-metric and/or non-symmetric distances without resorting to metric-space mapping and/or distance symmetrization, which, in turn, lead to substantial performance degradation. Although the straightforward metrization and symmetrization is usually ineffective, we find that constructing an index using a modified, e.g., symmetrized, distance can improve performance. This observation paves a way to a new line of research of designing index-specific graph-construction distance functions.
Tasks	graph construction
Published	2019-10-08
URL	https://arxiv.org/abs/1910.03534v1
PDF	https://arxiv.org/pdf/1910.03534v1.pdf
PWC	https://paperswithcode.com/paper/accurate-and-fast-retrieval-for-complex-non
Repo
Framework

Estimating Forces of Robotic Pouring Using a LSTM RNN


Title	Estimating Forces of Robotic Pouring Using a LSTM RNN
Authors	Kyle Mott
Abstract	In machine learning, it is very important for a robot to be able to estimate dynamics from sequences of input data. This problem can be solved using a recurrent neural network. In this paper, we will discuss the preprocessing of 10 states of the dataset, then the use of a LSTM recurrent neural network to estimate one output state (dynamics) from the other 9 input states. We will discuss the architecture of the recurrent neural network, the data collection and preprocessing, the loss function, the results of the test data, and the discussion of changes that could improve the network. The results of this paper will be used for artificial intelligence research and identify the capabilities of a LSTM recurrent neural network architecture to estimate dynamics of a system.
Tasks
Published	2019-04-21
URL	http://arxiv.org/abs/1904.09980v2
PDF	http://arxiv.org/pdf/1904.09980v2.pdf
PWC	https://paperswithcode.com/paper/estimating-forces-of-robotic-pouring-using-a
Repo
Framework

Domain Adaptation Regularization for Spectral Pruning


Title	Domain Adaptation Regularization for Spectral Pruning
Authors	Laurent Dillard, Yosuke Shinya, Taiji Suzuki
Abstract	Deep Neural Networks (DNNs) have recently been achieving state-of-the-art performance on a variety of computer vision related tasks. However, their computational cost limits their ability to be implemented in embedded systems with restricted resources or strict latency constraints. Model compression has therefore been an active field of research to overcome this issue. On the other hand, DNNs typically require massive amounts of labeled data to be trained. This represents a second limitation to their deployment. Domain Adaptation (DA) addresses this issue by allowing to transfer knowledge learned on one labeled source distribution to a target distribution, possibly unlabeled. In this paper, we investigate on possible improvements of compression methods in DA setting. We focus on a compression method that was previously developed in the context of a single data distribution and show that, with a careful choice of data to use during compression and additional regularization terms directly related to DA objectives, it is possible to improve compression results. We also show that our method outperforms an existing compression method studied in the DA setting by a large margin for high compression rates. Although our work is based on one specific compression method, we also outline some general guidelines for improving compression in DA setting.
Tasks	Domain Adaptation, Model Compression
Published	2019-12-26
URL	https://arxiv.org/abs/1912.11853v2
PDF	https://arxiv.org/pdf/1912.11853v2.pdf
PWC	https://paperswithcode.com/paper/domain-adaptation-regularization-for-spectral
Repo
Framework

Mixture Modeling of Global Shape Priors and Autoencoding Local Intensity Priors for Left Atrium Segmentation


Title	Mixture Modeling of Global Shape Priors and Autoencoding Local Intensity Priors for Left Atrium Segmentation
Authors	Tim Sodergren, Riddhish Bhalodia, Ross Whitaker, Joshua Cates, Nassir Marrouche, Shireen Elhabian
Abstract	Difficult image segmentation problems, for instance left atrium MRI, can be addressed by incorporating shape priors to find solutions that are consistent with known objects. Nonetheless, a single multivariate Gaussian is not an adequate model in cases with significant nonlinear shape variation or where the prior distribution is multimodal. Nonparametric density estimation is more general, but has a ravenous appetite for training samples and poses serious challenges in optimization, especially in high dimensional spaces. Here, we propose a maximum-a-posteriori formulation that relies on a generative image model by incorporating both local intensity and global shape priors. We use deep autoencoders to capture the complex intensity distribution while avoiding the careful selection of hand-crafted features. We formulate the shape prior as a mixture of Gaussians and learn the corresponding parameters in a high-dimensional shape space rather than pre-projecting onto a low-dimensional subspace. In segmentation, we treat the identity of the mixture component as a latent variable and marginalize it within a generalized expectation-maximization framework. We present a conditional maximization-based scheme that alternates between a closed-form solution for component-specific shape parameters that provides a global update-based optimization strategy, and an intensity-based energy minimization that translates the global notion of a nonlinear shape prior into a set of local penalties. We demonstrate our approach on the left atrial segmentation from gadolinium-enhanced MRI, which is useful in quantifying the atrial geometry in patients with atrial fibrillation.
Tasks	Density Estimation, Semantic Segmentation
Published	2019-03-06
URL	http://arxiv.org/abs/1903.06260v1
PDF	http://arxiv.org/pdf/1903.06260v1.pdf
PWC	https://paperswithcode.com/paper/mixture-modeling-of-global-shape-priors-and
Repo
Framework

FisheyeMODNet: Moving Object detection on Surround-view Cameras for Autonomous Driving


Title	FisheyeMODNet: Moving Object detection on Surround-view Cameras for Autonomous Driving
Authors	Marie Yahiaoui, Hazem Rashed, Letizia Mariotti, Ganesh Sistu, Ian Clancy, Lucie Yahiaoui, Varun Ravi Kumar, Senthil Yogamani
Abstract	Moving Object Detection (MOD) is an important task for achieving robust autonomous driving. An autonomous vehicle has to estimate collision risk with other interacting objects in the environment and calculate an optional trajectory. Collision risk is typically higher for moving objects than static ones due to the need to estimate the future states and poses of the objects for decision making. This is particularly important for near-range objects around the vehicle which are typically detected by a fisheye surround-view system that captures a 360{\deg} view of the scene. In this work, we propose a CNN architecture for moving object detection using fisheye images that were captured in autonomous driving environment. As motion geometry is highly non-linear and unique for fisheye cameras, we will make an improved version of the current dataset public to encourage further research. To target embedded deployment, we design a lightweight encoder sharing weights across sequential images. The proposed network runs at 15 fps on a 1 teraflops automotive embedded system at accuracy of 40% IoU and 69.5% mIoU.
Tasks	Autonomous Driving, Decision Making, Object Detection
Published	2019-08-30
URL	https://arxiv.org/abs/1908.11789v1
PDF	https://arxiv.org/pdf/1908.11789v1.pdf
PWC	https://paperswithcode.com/paper/fisheyemodnet-moving-object-detection-on
Repo
Framework

Improving Generalization via Attribute Selection on Out-of-the-box Data


Title	Improving Generalization via Attribute Selection on Out-of-the-box Data
Authors	Xiaofeng Xu, Ivor W. Tsang, Chuancai Liu
Abstract	Zero-shot learning (ZSL) aims to recognize unseen objects (test classes) given some other seen objects (training classes), by sharing information of attributes between different objects. Attributes are artificially annotated for objects and treated equally in recent ZSL tasks. However, some inferior attributes with poor predictability or poor discriminability may have negative impacts on the ZSL system performance. This paper first derives a generalization error bound for ZSL tasks. Our theoretical analysis verifies that selecting the subset of key attributes can improve the generalization performance of the original ZSL model, which utilizes all the attributes. Unfortunately, previous attribute selection methods are conducted based on the seen data, and their selected attributes have poor generalization capability to the unseen data, which is unavailable in the training stage of ZSL tasks. Inspired by learning from pseudo relevance feedback, this paper introduces the out-of-the-box data, which is pseudo data generated by an attribute-guided generative model, to mimic the unseen data. After that, we present an iterative attribute selection (IAS) strategy which iteratively selects key attributes based on the out-of-the-box data. Since the distribution of the generated out-of-the-box data is similar to the test data, the key attributes selected by IAS can be effectively generalized to test data. Extensive experiments demonstrate that IAS can significantly improve existing attribute-based ZSL methods and achieve state-of-the-art performance.
Tasks	Zero-Shot Learning
Published	2019-07-26
URL	https://arxiv.org/abs/1907.11397v2
PDF	https://arxiv.org/pdf/1907.11397v2.pdf
PWC	https://paperswithcode.com/paper/improving-generalization-via-attribute
Repo
Framework

FaSTExt: Fast and Small Text Extractor


Title	FaSTExt: Fast and Small Text Extractor
Authors	Alexander Filonenko, Konstantin Gudkov, Aleksei Lebedev, Nikita Orlov, Ivan Zagaynov
Abstract	Text detection in natural images is a challenging but necessary task for many applications. Existing approaches utilize large deep convolutional neural networks making it difficult to use them in real-world tasks. We propose a small yet relatively precise text extraction method. The basic component of it is a convolutional neural network which works in a fully-convolutional manner and produces results at multiple scales. Each scale output predicts whether a pixel is a part of some word, its geometry, and its relation to neighbors at the same scale and between scales. The key factor of reducing the complexity of the model was the utilization of depthwise separable convolution, linear bottlenecks, and inverted residuals. Experiments on public datasets show that the proposed network can effectively detect text while keeping the number of parameters in the range of 1.58 to 10.59 million in different configurations.
Tasks
Published	2019-08-14
URL	https://arxiv.org/abs/1908.08994v1
PDF	https://arxiv.org/pdf/1908.08994v1.pdf
PWC	https://paperswithcode.com/paper/fastext-fast-and-small-text-extractor
Repo
Framework

Predicting Student Performance in an Educational Game Using a Hidden Markov Model


Title	Predicting Student Performance in an Educational Game Using a Hidden Markov Model
Authors	Manie Tadayon, Greg Pottie
Abstract	Contributions: Prior studies on education have mostly followed the model of the cross sectional study, namely, examining the pretest and the posttest scores. This paper shows that students’ knowledge throughout the intervention can be estimated by time series analysis using a hidden Markov model. Background: Analyzing time series and the interaction between the students and the game data can result in valuable information that cannot be gained by only cross sectional studies of the exams. Research Questions: Can a hidden Markov model be used to analyze the educational games? Can a hidden Markov model be used to make a prediction of the students’ performance? Methodology: The study was conducted on (N=854) students who played the Save Patch game. Students were divided into class 1 and class 2. Class 1 students are those who scored lower in the test than class 2 students. The analysis is done by choosing various features of the game as the observations. Findings: The state trajectories can predict the students’ performance accurately for both class 1 and class 2.
Tasks	Time Series, Time Series Analysis
Published	2019-04-24
URL	http://arxiv.org/abs/1904.11857v1
PDF	http://arxiv.org/pdf/1904.11857v1.pdf
PWC	https://paperswithcode.com/paper/predicting-student-performance-in-an
Repo
Framework

Photonic architecture for reinforcement learning


Title	Photonic architecture for reinforcement learning
Authors	Fulvio Flamini, Arne Hamann, Sofiène Jerbi, Lea M. Trenkwalder, Hendrik Poulsen Nautrup, Hans J. Briegel
Abstract	The last decade has seen an unprecedented growth in artificial intelligence and photonic technologies, both of which drive the limits of modern-day computing devices. In line with these recent developments, this work brings together the state of the art of both fields within the framework of reinforcement learning. We present the blueprint for a photonic implementation of an active learning machine incorporating contemporary algorithms such as SARSA, Q-learning, and projective simulation. We numerically investigate its performance within typical reinforcement learning environments, showing that realistic levels of experimental noise can be tolerated or even be beneficial for the learning process. Remarkably, the architecture itself enables mechanisms of abstraction and generalization, two features which are often considered key ingredients for artificial intelligence. The proposed architecture, based on single-photon evolution on a mesh of tunable beamsplitters, is simple, scalable, and a first integration in portable systems appears to be within the reach of near-term technology.
Tasks	Active Learning, Q-Learning
Published	2019-07-17
URL	https://arxiv.org/abs/1907.07503v1
PDF	https://arxiv.org/pdf/1907.07503v1.pdf
PWC	https://paperswithcode.com/paper/photonic-architecture-for-reinforcement
Repo
Framework

Iterative Least Trimmed Squares for Mixed Linear Regression


Title	Iterative Least Trimmed Squares for Mixed Linear Regression
Authors	Yanyao Shen, Sujay Sanghavi
Abstract	Given a linear regression setting, Iterative Least Trimmed Squares (ILTS) involves alternating between (a) selecting the subset of samples with lowest current loss, and (b) re-fitting the linear model only on that subset. Both steps are very fast and simple. In this paper we analyze ILTS in the setting of mixed linear regression with corruptions (MLR-C). We first establish deterministic conditions (on the features etc.) under which the ILTS iterate converges linearly to the closest mixture component. We also provide a global algorithm that uses ILTS as a subroutine, to fully solve mixed linear regressions with corruptions. We then evaluate it for the widely studied setting of isotropic Gaussian features, and establish that we match or better existing results in terms of sample complexity. Finally, we provide an ODE analysis for a gradient-descent variant of ILTS that has optimal time complexity. Our results provide initial theoretical evidence that iteratively fitting to the best subset of samples – a potentially widely applicable idea – can provably provide state of the art performance in bad training data settings.
Tasks
Published	2019-02-10
URL	https://arxiv.org/abs/1902.03653v2
PDF	https://arxiv.org/pdf/1902.03653v2.pdf
PWC	https://paperswithcode.com/paper/iterative-least-trimmed-squares-for-mixed
Repo
Framework

Deep Coupled-Representation Learning for Sparse Linear Inverse Problems with Side Information


Title	Deep Coupled-Representation Learning for Sparse Linear Inverse Problems with Side Information
Authors	Evaggelia Tsiligianni, Nikos Deligiannis
Abstract	In linear inverse problems, the goal is to recover a target signal from undersampled, incomplete or noisy linear measurements. Typically, the recovery relies on complex numerical optimization methods; recent approaches perform an unfolding of a numerical algorithm into a neural network form, resulting in a substantial reduction of the computational complexity. In this paper, we consider the recovery of a target signal with the aid of a correlated signal, the so-called side information (SI), and propose a deep unfolding model that incorporates SI. The proposed model is used to learn coupled representations of correlated signals from different modalities, enabling the recovery of multimodal data at a low computational cost. As such, our work introduces the first deep unfolding method with SI, which actually comes from a different modality. We apply our model to reconstruct near-infrared images from undersampled measurements given RGB images as SI. Experimental results demonstrate the superior performance of the proposed framework against single-modal deep learning methods that do not use SI, multimodal deep learning designs, and optimization algorithms.
Tasks	Representation Learning
Published	2019-07-04
URL	https://arxiv.org/abs/1907.02511v1
PDF	https://arxiv.org/pdf/1907.02511v1.pdf
PWC	https://paperswithcode.com/paper/deep-coupled-representation-learning-for
Repo
Framework

Decision-Focused Learning of Adversary Behavior in Security Games


Title	Decision-Focused Learning of Adversary Behavior in Security Games
Authors	Andrew Perrault, Bryan Wilder, Eric Ewing, Aditya Mate, Bistra Dilkina, Milind Tambe
Abstract	Stackelberg security games are a critical tool for maximizing the utility of limited defense resources to protect important targets from an intelligent adversary. Motivated by green security, where the defender may only observe an adversary’s response to defense on a limited set of targets, we study the problem of defending against the same adversary on a larger set of targets from the same distribution. We give a theoretical justification for why standard two-stage learning approaches, where a model of the adversary is trained for predictive accuracy and then optimized against, may fail to maximize the defender’s expected utility in this setting. We develop a decision-focused learning approach, where the adversary behavior model is optimized for decision quality, and show empirically that it achieves higher defender expected utility than the two-stage approach when there is limited training data and a large number of target features.
Tasks
Published	2019-03-03
URL	http://arxiv.org/abs/1903.00958v1
PDF	http://arxiv.org/pdf/1903.00958v1.pdf
PWC	https://paperswithcode.com/paper/decision-focused-learning-of-adversary
Repo
Framework

Model-free Control of Chaos with Continuous Deep Q-learning


Title	Model-free Control of Chaos with Continuous Deep Q-learning
Authors	Junya Ikemoto, Toshimitsu Ushio
Abstract	The OGY method is one of control methods for a chaotic system. In the method, we have to calculate a stabilizing periodic orbit embedded in its chaotic attractor. Thus, we cannot use this method in the case where a precise mathematical model of the chaotic system cannot be identified. In this case, the delayed feedback control proposed by Pyragas is useful. However, even in the delayed feedback control, we need the mathematical model to determine a feedback gain that stabilizes the periodic orbit. To overcome this problem, we propose a model-free reinforcement learning algorithm to the design of a controller for the chaotic system. In recent years, model-free reinforcement learning algorithms with deep neural networks have been paid much attention to. Those algorithms make it possible to control complex systems. However, it is known that model-free reinforcement learning algorithms are not efficient because learners must explore their control policies over the entire state space. Moreover, model-free reinforcement learning algorithms with deep neural networks have the disadvantage in taking much time to learn their control optimal policies. Thus, we propose a data-based control policy consisting of two steps, where we determine a region including the stabilizing periodic orbit first, and make the controller learn an optimal control policy for its stabilization. In the proposed method, the controller efficiently explores its control policy only in the region.
Tasks	Q-Learning
Published	2019-07-16
URL	https://arxiv.org/abs/1907.07775v3
PDF	https://arxiv.org/pdf/1907.07775v3.pdf
PWC	https://paperswithcode.com/paper/model-free-control-of-chaos-with-continuous
Repo
Framework

VideoDP: A Universal Platform for Video Analytics with Differential Privacy


Title	VideoDP: A Universal Platform for Video Analytics with Differential Privacy
Authors	Han Wang, Shangyu Xie, Yuan Hong
Abstract	Massive amounts of video data are ubiquitously generated in personal devices and dedicated video recording facilities. Analyzing such data would be extremely beneficial in real world (e.g., urban traffic analysis, pedestrian behavior analysis, video surveillance). However, videos contain considerable sensitive information, such as human faces, identities and activities. Most of the existing video sanitization techniques simply obfuscate the video by detecting and blurring the region of interests (e.g., faces, vehicle plates, locations and timestamps) without quantifying and bounding the privacy leakage in the sanitization. In this paper, to the best of our knowledge, we propose the first differentially private video analytics platform (VideoDP) which flexibly supports different video analyses with rigorous privacy guarantee. Different from traditional noise-injection based differentially private mechanisms, given the input video, VideoDP randomly generates a utility-driven private video in which adding or removing any sensitive visual element (e.g., human, object) does not significantly affect the output video. Then, different video analyses requested by untrusted video analysts can be flexibly performed over the utility-driven video while ensuring differential privacy. Finally, we conduct experiments on real videos, and the experimental results demonstrate that our VideoDP effectively functions video analytics with good utility.
Tasks
Published	2019-09-18
URL	https://arxiv.org/abs/1909.08729v2
PDF	https://arxiv.org/pdf/1909.08729v2.pdf
PWC	https://paperswithcode.com/paper/videodp-a-universal-platform-for-video
Repo
Framework