October 16, 2019

3275 words 16 mins read

Paper Group ANR 1151

Bandit learning in concave $N$-person games. Dialogue Natural Language Inference. An Aggregated Multicolumn Dilated Convolution Network for Perspective-Free Counting. Few-Shot Goal Inference for Visuomotor Learning and Planning. Make (Nearly) Every Neural Network Better: Generating Neural Network Ensembles by Weight Parameter Resampling. Video-base …

Bandit learning in concave $N$-person games


Title	Bandit learning in concave $N$-person games
Authors	Mario Bravo, David S. Leslie, Panayotis Mertikopoulos
Abstract	This paper examines the long-run behavior of learning with bandit feedback in non-cooperative concave games. The bandit framework accounts for extremely low-information environments where the agents may not even know they are playing a game; as such, the agents’ most sensible choice in this setting would be to employ a no-regret learning algorithm. In general, this does not mean that the players’ behavior stabilizes in the long run: no-regret learning may lead to cycles, even with perfect gradient information. However, if a standard monotonicity condition is satisfied, our analysis shows that no-regret learning based on mirror descent with bandit feedback converges to Nash equilibrium with probability $1$. We also derive an upper bound for the convergence rate of the process that nearly matches the best attainable rate for single-agent bandit stochastic optimization.
Tasks	Stochastic Optimization
Published	2018-10-03
URL	http://arxiv.org/abs/1810.01925v1
PDF	http://arxiv.org/pdf/1810.01925v1.pdf
PWC	https://paperswithcode.com/paper/bandit-learning-in-concave-n-person-games
Repo
Framework

Dialogue Natural Language Inference


Title	Dialogue Natural Language Inference
Authors	Sean Welleck, Jason Weston, Arthur Szlam, Kyunghyun Cho
Abstract	Consistency is a long standing issue faced by dialogue models. In this paper, we frame the consistency of dialogue agents as natural language inference (NLI) and create a new natural language inference dataset called Dialogue NLI. We propose a method which demonstrates that a model trained on Dialogue NLI can be used to improve the consistency of a dialogue model, and evaluate the method with human evaluation and with automatic metrics on a suite of evaluation sets designed to measure a dialogue model’s consistency.
Tasks	Natural Language Inference
Published	2018-11-01
URL	http://arxiv.org/abs/1811.00671v2
PDF	http://arxiv.org/pdf/1811.00671v2.pdf
PWC	https://paperswithcode.com/paper/dialogue-natural-language-inference
Repo
Framework

An Aggregated Multicolumn Dilated Convolution Network for Perspective-Free Counting


Title	An Aggregated Multicolumn Dilated Convolution Network for Perspective-Free Counting
Authors	Diptodip Deb, Jonathan Ventura
Abstract	We propose the use of dilated filters to construct an aggregation module in a multicolumn convolutional neural network for perspective-free counting. Counting is a common problem in computer vision (e.g. traffic on the street or pedestrians in a crowd). Modern approaches to the counting problem involve the production of a density map via regression whose integral is equal to the number of objects in the image. However, objects in the image can occur at different scales (e.g. due to perspective effects) which can make it difficult for a learning agent to learn the proper density map. While the use of multiple columns to extract multiscale information from images has been shown before, our approach aggregates the multiscale information gathered by the multicolumn convolutional neural network to improve performance. Our experiments show that our proposed network outperforms the state-of-the-art on many benchmark datasets, and also that using our aggregation module in combination with a higher number of columns is beneficial for multiscale counting.
Tasks
Published	2018-04-20
URL	http://arxiv.org/abs/1804.07821v1
PDF	http://arxiv.org/pdf/1804.07821v1.pdf
PWC	https://paperswithcode.com/paper/an-aggregated-multicolumn-dilated-convolution
Repo
Framework

Few-Shot Goal Inference for Visuomotor Learning and Planning


Title	Few-Shot Goal Inference for Visuomotor Learning and Planning
Authors	Annie Xie, Avi Singh, Sergey Levine, Chelsea Finn
Abstract	Reinforcement learning and planning methods require an objective or reward function that encodes the desired behavior. Yet, in practice, there is a wide range of scenarios where an objective is difficult to provide programmatically, such as tasks with visual observations involving unknown object positions or deformable objects. In these cases, prior methods use engineered problem-specific solutions, e.g., by instrumenting the environment with additional sensors to measure a proxy for the objective. Such solutions require a significant engineering effort on a per-task basis, and make it impractical for robots to continuously learn complex skills outside of laboratory settings. We aim to find a more general and scalable solution for specifying goals for robot learning in unconstrained environments. To that end, we formulate the few-shot objective learning problem, where the goal is to learn a task objective from only a few example images of successful end states for that task. We propose a simple solution to this problem: meta-learn a classifier that can recognize new goals from a few examples. We show how this approach can be used with both model-free reinforcement learning and visual model-based planning and show results in three domains: rope manipulation from images in simulation, visual navigation in a simulated 3D environment, and object arrangement into user-specified configurations on a real robot.
Tasks	Visual Navigation
Published	2018-09-30
URL	http://arxiv.org/abs/1810.00482v1
PDF	http://arxiv.org/pdf/1810.00482v1.pdf
PWC	https://paperswithcode.com/paper/few-shot-goal-inference-for-visuomotor
Repo
Framework

Make (Nearly) Every Neural Network Better: Generating Neural Network Ensembles by Weight Parameter Resampling


Title	Make (Nearly) Every Neural Network Better: Generating Neural Network Ensembles by Weight Parameter Resampling
Authors	Jiayi Liu, Samarth Tripathi, Unmesh Kurup, Mohak Shah
Abstract	Deep Neural Networks (DNNs) have become increasingly popular in computer vision, natural language processing, and other areas. However, training and fine-tuning a deep learning model is computationally intensive and time-consuming. We propose a new method to improve the performance of nearly every model including pre-trained models. The proposed method uses an ensemble approach where the networks in the ensemble are constructed by reassigning model parameter values based on the probabilistic distribution of these parameters, calculated towards the end of the training process. For pre-trained models, this approach results in an additional training step (usually less than one epoch). We perform a variety of analysis using the MNIST dataset and validate the approach with a number of DNN models using pre-trained models on the ImageNet dataset.
Tasks
Published	2018-07-02
URL	http://arxiv.org/abs/1807.00847v1
PDF	http://arxiv.org/pdf/1807.00847v1.pdf
PWC	https://paperswithcode.com/paper/make-nearly-every-neural-network-better
Repo
Framework

Video-based computer aided arthroscopy for patient specific reconstruction of the Anterior Cruciate Ligament


Title	Video-based computer aided arthroscopy for patient specific reconstruction of the Anterior Cruciate Ligament
Authors	Carolina Raposo, Cristovao Sousa, Luis Ribeiro, Rui Melo, Joao P. Barreto, Joao Oliveira, Pedro Marques, Fernando Fonseca
Abstract	The Anterior Cruciate Ligament (ACL) tear is a common medical condition that is treated using arthroscopy by pulling a tissue graft through a tunnel opened with a drill. The correct anatomical position and orientation of this tunnel is crucial for knee stability, and drilling an adequate bone tunnel is the most technically challenging part of the procedure. This paper presents, for the first time, a guidance system based solely on intra-operative video for guiding the drilling of the tunnel. Our solution uses small, easily recognizable visual markers that are attached to the bone and tools for estimating their relative pose. A recent registration algorithm is employed for aligning a pre-operative image of the patient’s anatomy with a set of contours reconstructed by touching the bone surface with an instrumented tool. Experimental validation using ex-vivo data shows that the method enables the accurate registration of the pre-operative model with the bone, providing useful information for guiding the surgeon during the medical procedure.
Tasks
Published	2018-07-25
URL	http://arxiv.org/abs/1807.09627v1
PDF	http://arxiv.org/pdf/1807.09627v1.pdf
PWC	https://paperswithcode.com/paper/video-based-computer-aided-arthroscopy-for
Repo
Framework

Fast Mitochondria Segmentation for Connectomics


Title	Fast Mitochondria Segmentation for Connectomics
Authors	Vincent Casser, Kai Kang, Hanspeter Pfister, Daniel Haehn
Abstract	In connectomics, scientists create the wiring diagram of a mammalian brain by identifying synaptic connections between neurons in nano-scale electron microscopy images. This allows for the identification of dysfunctional mitochondria which are linked to a variety of diseases such as autism or bipolar. However, manual analysis is not feasible since connectomics datasets can be petabytes in size. To process such large data, we present a fully automatic mitochondria detector based on a modified U-Net architecture that yields high accuracy and fast processing times. We evaluate our method on multiple real-world connectomics datasets, including an improved version of the EPFL Hippocampus mitochondria detection benchmark. Our results show a Jaccard index of up to 0.90 with inference speeds lower than 16ms for a 512x512 image tile. This speed is faster than the acquisition time of modern electron microscopes, allowing mitochondria detection in real-time. Compared to previous work, our detector ranks first among real-time methods and third overall. Our data, results, and code are freely available.
Tasks
Published	2018-12-14
URL	http://arxiv.org/abs/1812.06024v1
PDF	http://arxiv.org/pdf/1812.06024v1.pdf
PWC	https://paperswithcode.com/paper/fast-mitochondria-segmentation-for
Repo
Framework

Probabilistic supervised learning


Title	Probabilistic supervised learning
Authors	Frithjof Gressmann, Franz J. Király, Bilal Mateen, Harald Oberhauser
Abstract	Predictive modelling and supervised learning are central to modern data science. With predictions from an ever-expanding number of supervised black-box strategies - e.g., kernel methods, random forests, deep learning aka neural networks - being employed as a basis for decision making processes, it is crucial to understand the statistical uncertainty associated with these predictions. As a general means to approach the issue, we present an overarching framework for black-box prediction strategies that not only predict the target but also their own predictions’ uncertainty. Moreover, the framework allows for fair assessment and comparison of disparate prediction strategies. For this, we formally consider strategies capable of predicting full distributions from feature variables, so-called probabilistic supervised learning strategies. Our work draws from prior work including Bayesian statistics, information theory, and modern supervised machine learning, and in a novel synthesis leads to (a) new theoretical insights such as a probabilistic bias-variance decomposition and an entropic formulation of prediction, as well as to (b) new algorithms and meta-algorithms, such as composite prediction strategies, probabilistic boosting and bagging, and a probabilistic predictive independence test. Our black-box formulation also leads (c) to a new modular interface view on probabilistic supervised learning and a modelling workflow API design, which we have implemented in the newly released skpro machine learning toolbox, extending the familiar modelling interface and meta-modelling functionality of sklearn. The skpro package provides interfaces for construction, composition, and tuning of probabilistic supervised learning strategies, together with orchestration features for validation and comparison of any such strategy - be it frequentist, Bayesian, or other.
Tasks	Decision Making
Published	2018-01-02
URL	https://arxiv.org/abs/1801.00753v3
PDF	https://arxiv.org/pdf/1801.00753v3.pdf
PWC	https://paperswithcode.com/paper/probabilistic-supervised-learning
Repo
Framework

Learning the Hierarchical Parts of Objects by Deep Non-Smooth Nonnegative Matrix Factorization


Title	Learning the Hierarchical Parts of Objects by Deep Non-Smooth Nonnegative Matrix Factorization
Authors	Jinshi Yu, Guoxu Zhou, Andrzej Cichocki, Shengli Xie
Abstract	Nonsmooth Nonnegative Matrix Factorization (nsNMF) is capable of producing more localized, less overlapped feature representations than other variants of NMF while keeping satisfactory fit to data. However, nsNMF as well as other existing NMF methods is incompetent to learn hierarchical features of complex data due to its shallow structure. To fill this gap, we propose a deep nsNMF method coined by the fact that it possesses a deeper architecture compared with standard nsNMF. The deep nsNMF not only gives parts-based features due to the nonnegativity constraints, but also creates higher-level, more abstract features by combing lower-level ones. The in-depth description of how deep architecture can help to efficiently discover abstract features in dnsNMF is presented. And we also show that the deep nsNMF has close relationship with the deep autoencoder, suggesting that the proposed model inherits the major advantages from both deep learning and NMF. Extensive experiments demonstrate the standout performance of the proposed method in clustering analysis.
Tasks
Published	2018-03-20
URL	http://arxiv.org/abs/1803.07226v1
PDF	http://arxiv.org/pdf/1803.07226v1.pdf
PWC	https://paperswithcode.com/paper/learning-the-hierarchical-parts-of-objects-by
Repo
Framework

Distortion Robust Image Classification using Deep Convolutional Neural Network with Discrete Cosine Transform


Title	Distortion Robust Image Classification using Deep Convolutional Neural Network with Discrete Cosine Transform
Authors	Md Tahmid Hossain, Shyh Wei Teng, Dengsheng Zhang, Suryani Lim, Guojun Lu
Abstract	Convolutional Neural Network is good at image classification. However, it is found to be vulnerable to image quality degradation. Even a small amount of distortion such as noise or blur can severely hamper the performance of these CNN architectures. Most of the work in the literature strives to mitigate this problem simply by fine-tuning a pre-trained CNN on mutually exclusive or a union set of distorted training data. This iterative fine-tuning process with all known types of distortion is exhaustive and the network struggles to handle unseen distortions. In this work, we propose distortion robust DCT-Net, a Discrete Cosine Transform based module integrated into a deep network which is built on top of VGG16. Unlike other works in the literature, DCT-Net is “blind” to the distortion type and level in an image both during training and testing. As a part of the training process, the proposed DCT module discards input information which mostly represents the contribution of high frequencies. The DCT-Net is trained “blindly” only once and applied in generic situation without further retraining. We also extend the idea of traditional dropout and present a training adaptive version of the same. We evaluate our proposed method against Gaussian blur, motion blur, salt and pepper noise, Gaussian noise and speckle noise added to CIFAR-10/100 and ImageNet test sets. Experimental results demonstrate that once trained, DCT-Net not only generalizes well to a variety of unseen image distortions but also outperforms other methods in the literature.
Tasks	Image Classification
Published	2018-11-14
URL	http://arxiv.org/abs/1811.05819v2
PDF	http://arxiv.org/pdf/1811.05819v2.pdf
PWC	https://paperswithcode.com/paper/distortion-robust-image-classification-using
Repo
Framework

An Augmented Linear Mixing Model to Address Spectral Variability for Hyperspectral Unmixing


Title	An Augmented Linear Mixing Model to Address Spectral Variability for Hyperspectral Unmixing
Authors	Danfeng Hong, Naoto Yokoya, Jocelyn Chanussot, Xiao Xiang Zhu
Abstract	Hyperspectral imagery collected from airborne or satellite sources inevitably suffers from spectral variability, making it difficult for spectral unmixing to accurately estimate abundance maps. The classical unmixing model, the linear mixing model (LMM), generally fails to handle this sticky issue effectively. To this end, we propose a novel spectral mixture model, called the augmented linear mixing model (ALMM), to address spectral variability by applying a data-driven learning strategy in inverse problems of hyperspectral unmixing. The proposed approach models the main spectral variability (i.e., scaling factors) generated by variations in illumination or typography separately by means of the endmember dictionary. It then models other spectral variabilities caused by environmental conditions (e.g., local temperature and humidity, atmospheric effects) and instrumental configurations (e.g., sensor noise), as well as material nonlinear mixing effects, by introducing a spectral variability dictionary. To effectively run the data-driven learning strategy, we also propose a reasonable prior knowledge for the spectral variability dictionary, whose atoms are assumed to be low-coherent with spectral signatures of endmembers, which leads to a well-known low coherence dictionary learning problem. Thus, a dictionary learning technique is embedded in the framework of spectral unmixing so that the algorithm can learn the spectral variability dictionary and estimate the abundance maps simultaneously. Extensive experiments on synthetic and real datasets are performed to demonstrate the superiority and effectiveness of the proposed method in comparison with previous state-of-the-art methods.
Tasks	Dictionary Learning, Hyperspectral Unmixing
Published	2018-10-29
URL	http://arxiv.org/abs/1810.12000v1
PDF	http://arxiv.org/pdf/1810.12000v1.pdf
PWC	https://paperswithcode.com/paper/an-augmented-linear-mixing-model-to-address
Repo
Framework

A Low-rank Tensor Regularization Strategy for Hyperspectral Unmixing


Title	A Low-rank Tensor Regularization Strategy for Hyperspectral Unmixing
Authors	Tales Imbiriba, Ricardo Augusto Borsoi, José Carlos Moreira Bermudez
Abstract	Tensor-based methods have recently emerged as a more natural and effective formulation to address many problems in hyperspectral imaging. In hyperspectral unmixing (HU), low-rank constraints on the abundance maps have been shown to act as a regularization which adequately accounts for the multidimensional structure of the underlying signal. However, imposing a strict low-rank constraint for the abundance maps does not seem to be adequate, as important information that may be required to represent fine scale abundance behavior may be discarded. This paper introduces a new low-rank tensor regularization that adequately captures the low-rank structure underlying the abundance maps without hindering the flexibility of the solution. Simulation results with synthetic and real data show that the the extra flexibility introduced by the proposed regularization significantly improves the unmixing results.
Tasks	Hyperspectral Unmixing
Published	2018-03-16
URL	http://arxiv.org/abs/1803.06355v1
PDF	http://arxiv.org/pdf/1803.06355v1.pdf
PWC	https://paperswithcode.com/paper/a-low-rank-tensor-regularization-strategy-for
Repo
Framework

Towards Adversarial Configurations for Software Product Lines


Title	Towards Adversarial Configurations for Software Product Lines
Authors	Paul Temple, Mathieu Acher, Battista Biggio, Jean-Marc Jézéquel, Fabio Roli
Abstract	Ensuring that all supposedly valid configurations of a software product line (SPL) lead to well-formed and acceptable products is challenging since it is most of the time impractical to enumerate and test all individual products of an SPL. Machine learning classifiers have been recently used to predict the acceptability of products associated with unseen configurations. For some configurations, a tiny change in their feature values can make them pass from acceptable to non-acceptable regarding users’ requirements and vice-versa. In this paper, we introduce the idea of leveraging these specific configurations and their positions in the feature space to improve the classifier and therefore the engineering of an SPL. Starting from a variability model, we propose to use Adversarial Machine Learning techniques to create new, adversarial configurations out of already known configurations by modifying their feature values. Using an industrial video generator we show how adversarial configurations can improve not only the classifier, but also the variability model, the variability implementation, and the testing oracle.
Tasks
Published	2018-05-30
URL	http://arxiv.org/abs/1805.12021v1
PDF	http://arxiv.org/pdf/1805.12021v1.pdf
PWC	https://paperswithcode.com/paper/towards-adversarial-configurations-for
Repo
Framework

ORACLE: Optimized Radio clAssification through Convolutional neuraL nEtworks


Title	ORACLE: Optimized Radio clAssification through Convolutional neuraL nEtworks
Authors	Kunal Sankhe, Mauro Belgiovine, Fan Zhou, Shamnaz Riyaz, Stratis Ioannidis, Kaushik Chowdhury
Abstract	This paper describes the architecture and performance of ORACLE, an approach for detecting a unique radio from a large pool of bit-similar devices (same hardware, protocol, physical address, MAC ID) using only IQ samples at the physical layer. ORACLE trains a convolutional neural network (CNN) that balances computational time and accuracy, showing 99% classification accuracy for a 16-node USRP X310 SDR testbed and an external database of $>$100 COTS WiFi devices. Our work makes the following contributions: (i) it studies the hardware-centric features within the transmitter chain that causes IQ sample variations; (ii) for an idealized static channel environment, it proposes a CNN architecture requiring only raw IQ samples accessible at the front-end, without channel estimation or prior knowledge of the communication protocol; (iii) for dynamic channels, it demonstrates a principled method of feedback-driven transmitter-side modifications that uses channel estimation at the receiver to increase differentiability for the CNN classifier. The key innovation here is to intentionally introduce controlled imperfections on the transmitter side through software directives, while minimizing the change in bit error rate. Unlike previous work that imposes constant environmental conditions, ORACLE adopts the `train once deploy anywhere’ paradigm with near-perfect device classification accuracy. \|
Tasks
Published	2018-12-03
URL	http://arxiv.org/abs/1812.01124v1
PDF	http://arxiv.org/pdf/1812.01124v1.pdf
PWC	https://paperswithcode.com/paper/oracle-optimized-radio-classification-through
Repo
Framework

Relocalization, Global Optimization and Map Merging for Monocular Visual-Inertial SLAM


Title	Relocalization, Global Optimization and Map Merging for Monocular Visual-Inertial SLAM
Authors	Tong Qin, Perliang Li, Shaojie Shen
Abstract	The monocular visual-inertial system (VINS), which consists one camera and one low-cost inertial measurement unit (IMU), is a popular approach to achieve accurate 6-DOF state estimation. However, such locally accurate visual-inertial odometry is prone to drift and cannot provide absolute pose estimation. Leveraging history information to relocalize and correct drift has become a hot topic. In this paper, we propose a monocular visual-inertial SLAM system, which can relocalize camera and get the absolute pose in a previous-built map. Then 4-DOF pose graph optimization is performed to correct drifts and achieve global consistent. The 4-DOF contains x, y, z, and yaw angle, which is the actual drifted direction in the visual-inertial system. Furthermore, the proposed system can reuse a map by saving and loading it in an efficient way. Current map and previous map can be merged together by the global pose graph optimization. We validate the accuracy of our system on public datasets and compare against other state-of-the-art algorithms. We also evaluate the map merging ability of our system in the large-scale outdoor environment. The source code of map reuse is integrated into our public code, VINS-Mono.
Tasks	Pose Estimation
Published	2018-03-05
URL	http://arxiv.org/abs/1803.01549v1
PDF	http://arxiv.org/pdf/1803.01549v1.pdf
PWC	https://paperswithcode.com/paper/relocalization-global-optimization-and-map
Repo
Framework