July 26, 2019

3235 words 16 mins read

Paper Group ANR 780

Bayes-Optimal Entropy Pursuit for Active Choice-Based Preference Learning. Comparison of Time-Frequency Representations for Environmental Sound Classification using Convolutional Neural Networks. Comparing Neural and Attractiveness-based Visual Features for Artwork Recommendation. Recommendation with k-anonymized Ratings. An Actor-Critic Contextual …

Bayes-Optimal Entropy Pursuit for Active Choice-Based Preference Learning


Title	Bayes-Optimal Entropy Pursuit for Active Choice-Based Preference Learning
Authors	Stephen N. Pallone, Peter I. Frazier, Shane G. Henderson
Abstract	We analyze the problem of learning a single user’s preferences in an active learning setting, sequentially and adaptively querying the user over a finite time horizon. Learning is conducted via choice-based queries, where the user selects her preferred option among a small subset of offered alternatives. These queries have been shown to be a robust and efficient way to learn an individual’s preferences. We take a parametric approach and model the user’s preferences through a linear classifier, using a Bayesian prior to encode our current knowledge of this classifier. The rate at which we learn depends on the alternatives offered at every time epoch. Under certain noise assumptions, we show that the Bayes-optimal policy for maximally reducing entropy of the posterior distribution of this linear classifier is a greedy policy, and that this policy achieves a linear lower bound when alternatives can be constructed from the continuum. Further, we analyze a different metric called misclassification error, proving that the performance of the optimal policy that minimizes misclassification error is bounded below by a linear function of differential entropy. Lastly, we numerically compare the greedy entropy reduction policy with a knowledge gradient policy under a number of scenarios, examining their performance under both differential entropy and misclassification error.
Tasks	Active Learning
Published	2017-02-24
URL	http://arxiv.org/abs/1702.07694v1
PDF	http://arxiv.org/pdf/1702.07694v1.pdf
PWC	https://paperswithcode.com/paper/bayes-optimal-entropy-pursuit-for-active
Repo
Framework

Comparison of Time-Frequency Representations for Environmental Sound Classification using Convolutional Neural Networks


Title	Comparison of Time-Frequency Representations for Environmental Sound Classification using Convolutional Neural Networks
Authors	M. Huzaifah
Abstract	Recent successful applications of convolutional neural networks (CNNs) to audio classification and speech recognition have motivated the search for better input representations for more efficient training. Visual displays of an audio signal, through various time-frequency representations such as spectrograms offer a rich representation of the temporal and spectral structure of the original signal. In this letter, we compare various popular signal processing methods to obtain this representation, such as short-time Fourier transform (STFT) with linear and Mel scales, constant-Q transform (CQT) and continuous Wavelet transform (CWT), and assess their impact on the classification performance of two environmental sound datasets using CNNs. This study supports the hypothesis that time-frequency representations are valuable in learning useful features for sound classification. Moreover, the actual transformation used is shown to impact the classification accuracy, with Mel-scaled STFT outperforming the other discussed methods slightly and baseline MFCC features to a large degree. Additionally, we observe that the optimal window size during transformation is dependent on the characteristics of the audio signal and architecturally, 2D convolution yielded better results in most cases compared to 1D.
Tasks	Audio Classification, Environmental Sound Classification, Speech Recognition
Published	2017-06-22
URL	http://arxiv.org/abs/1706.07156v1
PDF	http://arxiv.org/pdf/1706.07156v1.pdf
PWC	https://paperswithcode.com/paper/comparison-of-time-frequency-representations
Repo
Framework

Comparing Neural and Attractiveness-based Visual Features for Artwork Recommendation


Title	Comparing Neural and Attractiveness-based Visual Features for Artwork Recommendation
Authors	Vicente Dominguez, Pablo Messina, Denis Parra, Domingo Mery, Christoph Trattner, Alvaro Soto
Abstract	Advances in image processing and computer vision in the latest years have brought about the use of visual features in artwork recommendation. Recent works have shown that visual features obtained from pre-trained deep neural networks (DNNs) perform very well for recommending digital art. Other recent works have shown that explicit visual features (EVF) based on attractiveness can perform well in preference prediction tasks, but no previous work has compared DNN features versus specific attractiveness-based visual features (e.g. brightness, texture) in terms of recommendation performance. In this work, we study and compare the performance of DNN and EVF features for the purpose of physical artwork recommendation using transactional data from UGallery, an online store of physical paintings. In addition, we perform an exploratory analysis to understand if DNN embedded features have some relation with certain EVF. Our results show that DNN features outperform EVF, that certain EVF features are more suited for physical artwork recommendation and, finally, we show evidence that certain neurons in the DNN might be partially encoding visual features such as brightness, providing an opportunity for explaining recommendations based on visual neural models.
Tasks
Published	2017-06-22
URL	http://arxiv.org/abs/1706.07515v2
PDF	http://arxiv.org/pdf/1706.07515v2.pdf
PWC	https://paperswithcode.com/paper/comparing-neural-and-attractiveness-based
Repo
Framework

Recommendation with k-anonymized Ratings


Title	Recommendation with k-anonymized Ratings
Authors	Jun Sakuma, Tatsuya Osame
Abstract	Recommender systems are widely used to predict personalized preferences of goods or services using users’ past activities, such as item ratings or purchase histories. If collections of such personal activities were made publicly available, they could be used to personalize a diverse range of services, including targeted advertisement or recommendations. However, there would be an accompanying risk of privacy violations. The pioneering work of Narayanan et al.\ demonstrated that even if the identifiers are eliminated, the public release of user ratings can allow for the identification of users by those who have only a small amount of data on the users’ past ratings. In this paper, we assume the following setting. A collector collects user ratings, then anonymizes and distributes them. A recommender constructs a recommender system based on the anonymized ratings provided by the collector. Based on this setting, we exhaustively list the models of recommender systems that use anonymized ratings. For each model, we then present an item-based collaborative filtering algorithm for making recommendations based on anonymized ratings. Our experimental results show that an item-based collaborative filtering based on anonymized ratings can perform better than collaborative filterings based on 5–10 non-anonymized ratings. This surprising result indicates that, in some settings, privacy protection does not necessarily reduce the usefulness of recommendations. From the experimental analysis of this counterintuitive result, we observed that the sparsity of the ratings can be reduced by anonymization and the variance of the prediction can be reduced if $k$, the anonymization parameter, is appropriately tuned. In this way, the predictive performance of recommendations based on anonymized ratings can be improved in some settings.
Tasks	Recommendation Systems
Published	2017-06-06
URL	http://arxiv.org/abs/1707.03334v1
PDF	http://arxiv.org/pdf/1707.03334v1.pdf
PWC	https://paperswithcode.com/paper/recommendation-with-k-anonymized-ratings
Repo
Framework

An Actor-Critic Contextual Bandit Algorithm for Personalized Mobile Health Interventions


Title	An Actor-Critic Contextual Bandit Algorithm for Personalized Mobile Health Interventions
Authors	Huitian Lei, Ambuj Tewari, Susan A. Murphy
Abstract	Increasing technological sophistication and widespread use of smartphones and wearable devices provide opportunities for innovative and highly personalized health interventions. A Just-In-Time Adaptive Intervention (JITAI) uses real-time data collection and communication capabilities of modern mobile devices to deliver interventions in real-time that are adapted to the in-the-moment needs of the user. The lack of methodological guidance in constructing data-based JITAIs remains a hurdle in advancing JITAI research despite the increasing popularity of JITAIs among clinical scientists. In this article, we make a first attempt to bridge this methodological gap by formulating the task of tailoring interventions in real-time as a contextual bandit problem. Interpretability requirements in the domain of mobile health lead us to formulate the problem differently from existing formulations intended for web applications such as ad or news article placement. Under the assumption of linear reward function, we choose the reward function (the “critic”) parameterization separately from a lower dimensional parameterization of stochastic policies (the “actor”). We provide an online actor-critic algorithm that guides the construction and refinement of a JITAI. Asymptotic properties of the actor-critic algorithm are developed and backed up by numerical experiments. Additional numerical experiments are conducted to test the robustness of the algorithm when idealized assumptions used in the analysis of contextual bandit algorithm are breached.
Tasks
Published	2017-06-28
URL	http://arxiv.org/abs/1706.09090v1
PDF	http://arxiv.org/pdf/1706.09090v1.pdf
PWC	https://paperswithcode.com/paper/an-actor-critic-contextual-bandit-algorithm
Repo
Framework

‘Indifference’ methods for managing agent rewards


Title	‘Indifference’ methods for managing agent rewards
Authors	Stuart Armstrong, Xavier O’Rourke
Abstract	`Indifference’ refers to a class of methods used to control reward based agents. Indifference techniques aim to achieve one or more of three distinct goals: rewards dependent on certain events (without the agent being motivated to manipulate the probability of those events), effective disbelief (where agents behave as if particular events could never happen), and seamless transition from one reward function to another (with the agent acting as if this change is unanticipated). This paper presents several methods for achieving these goals in the POMDP setting, establishing their uses, strengths, and requirements. These methods of control work even when the implications of the agent’s reward are otherwise not fully understood. \|
Tasks
Published	2017-12-18
URL	http://arxiv.org/abs/1712.06365v4
PDF	http://arxiv.org/pdf/1712.06365v4.pdf
PWC	https://paperswithcode.com/paper/indifference-methods-for-managing-agent
Repo
Framework

Tensor Fusion Network for Multimodal Sentiment Analysis


Title	Tensor Fusion Network for Multimodal Sentiment Analysis
Authors	Amir Zadeh, Minghai Chen, Soujanya Poria, Erik Cambria, Louis-Philippe Morency
Abstract	Multimodal sentiment analysis is an increasingly popular research area, which extends the conventional language-based definition of sentiment analysis to a multimodal setup where other relevant modalities accompany language. In this paper, we pose the problem of multimodal sentiment analysis as modeling intra-modality and inter-modality dynamics. We introduce a novel model, termed Tensor Fusion Network, which learns both such dynamics end-to-end. The proposed approach is tailored for the volatile nature of spoken language in online videos as well as accompanying gestures and voice. In the experiments, our model outperforms state-of-the-art approaches for both multimodal and unimodal sentiment analysis.
Tasks	Multimodal Sentiment Analysis, Sentiment Analysis
Published	2017-07-23
URL	http://arxiv.org/abs/1707.07250v1
PDF	http://arxiv.org/pdf/1707.07250v1.pdf
PWC	https://paperswithcode.com/paper/tensor-fusion-network-for-multimodal
Repo
Framework

Pixel-wise object tracking


Title	Pixel-wise object tracking
Authors	Yilin Song, Chenge Li, Yao Wang
Abstract	In this paper, we propose a novel pixel-wise visual object tracking framework that can track any anonymous object in a noisy background. The framework consists of two submodels, a global attention model and a local segmentation model. The global model generates a region of interests (ROI) that the object may lie in the new frame based on the past object segmentation maps, while the local model segments the new image in the ROI. Each model uses a LSTM structure to model the temporal dynamics of the motion and appearance, respectively. To circumvent the dependency of the training data between the two models, we use an iterative update strategy. Once the models are trained, there is no need to refine them to track specific objects, making our method efficient compared to online learning approaches. We demonstrate our real time pixel-wise object tracking framework on a challenging VOT dataset
Tasks	Object Tracking, Semantic Segmentation, Visual Object Tracking
Published	2017-11-20
URL	http://arxiv.org/abs/1711.07377v2
PDF	http://arxiv.org/pdf/1711.07377v2.pdf
PWC	https://paperswithcode.com/paper/pixel-wise-object-tracking
Repo
Framework

Fast Scene Understanding for Autonomous Driving


Title	Fast Scene Understanding for Autonomous Driving
Authors	Davy Neven, Bert De Brabandere, Stamatios Georgoulis, Marc Proesmans, Luc Van Gool
Abstract	Most approaches for instance-aware semantic labeling traditionally focus on accuracy. Other aspects like runtime and memory footprint are arguably as important for real-time applications such as autonomous driving. Motivated by this observation and inspired by recent works that tackle multiple tasks with a single integrated architecture, in this paper we present a real-time efficient implementation based on ENet that solves three autonomous driving related tasks at once: semantic scene segmentation, instance segmentation and monocular depth estimation. Our approach builds upon a branched ENet architecture with a shared encoder but different decoder branches for each of the three tasks. The presented method can run at 21 fps at a resolution of 1024x512 on the Cityscapes dataset without sacrificing accuracy compared to running each task separately.
Tasks	Autonomous Driving, Depth Estimation, Instance Segmentation, Monocular Depth Estimation, Scene Segmentation, Scene Understanding, Semantic Segmentation
Published	2017-08-08
URL	http://arxiv.org/abs/1708.02550v1
PDF	http://arxiv.org/pdf/1708.02550v1.pdf
PWC	https://paperswithcode.com/paper/fast-scene-understanding-for-autonomous
Repo
Framework

Enhanced discrete particle swarm optimization path planning for UAV vision-based surface inspection


Title	Enhanced discrete particle swarm optimization path planning for UAV vision-based surface inspection
Authors	Manh Duong Phung, Cong Hoang Quach, Tran Hiep Dinh, Quang Ha
Abstract	In built infrastructure monitoring, an efficient path planning algorithm is essential for robotic inspection of large surfaces using computer vision. In this work, we first formulate the inspection path planning problem as an extended travelling salesman problem (TSP) in which both the coverage and obstacle avoidance were taken into account. An enhanced discrete particle swarm optimization (DPSO) algorithm is then proposed to solve the TSP, with performance improvement by using deterministic initialization, random mutation, and edge exchange. Finally, we take advantage of parallel computing to implement the DPSO in a GPU-based framework so that the computation time can be significantly reduced while keeping the hardware requirement unchanged. To show the effectiveness of the proposed algorithm, experimental results are included for datasets obtained from UAV inspection of an office building and a bridge.
Tasks
Published	2017-06-14
URL	http://arxiv.org/abs/1706.04399v1
PDF	http://arxiv.org/pdf/1706.04399v1.pdf
PWC	https://paperswithcode.com/paper/enhanced-discrete-particle-swarm-optimization
Repo
Framework

Integrated Deep and Shallow Networks for Salient Object Detection


Title	Integrated Deep and Shallow Networks for Salient Object Detection
Authors	Jing Zhang, Bo Li, Yuchao Dai, Fatih Porikli, Mingyi He
Abstract	Deep convolutional neural network (CNN) based salient object detection methods have achieved state-of-the-art performance and outperform those unsupervised methods with a wide margin. In this paper, we propose to integrate deep and unsupervised saliency for salient object detection under a unified framework. Specifically, our method takes results of unsupervised saliency (Robust Background Detection, RBD) and normalized color images as inputs, and directly learns an end-to-end mapping between inputs and the corresponding saliency maps. The color images are fed into a Fully Convolutional Neural Networks (FCNN) adapted from semantic segmentation to exploit high-level semantic cues for salient object detection. Then the results from deep FCNN and RBD are concatenated to feed into a shallow network to map the concatenated feature maps to saliency maps. Finally, to obtain a spatially consistent saliency map with sharp object boundaries, we fuse superpixel level saliency map at multi-scale. Extensive experimental results on 8 benchmark datasets demonstrate that the proposed method outperforms the state-of-the-art approaches with a margin.
Tasks	Object Detection, Salient Object Detection, Semantic Segmentation
Published	2017-06-02
URL	http://arxiv.org/abs/1706.00530v1
PDF	http://arxiv.org/pdf/1706.00530v1.pdf
PWC	https://paperswithcode.com/paper/integrated-deep-and-shallow-networks-for
Repo
Framework

AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline


Title	AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline
Authors	Hui Bu, Jiayu Du, Xingyu Na, Bengu Wu, Hao Zheng
Abstract	An open-source Mandarin speech corpus called AISHELL-1 is released. It is by far the largest corpus which is suitable for conducting the speech recognition research and building speech recognition systems for Mandarin. The recording procedure, including audio capturing devices and environments are presented in details. The preparation of the related resources, including transcriptions and lexicon are described. The corpus is released with a Kaldi recipe. Experimental results implies that the quality of audio recordings and transcriptions are promising.
Tasks	Speech Recognition
Published	2017-09-16
URL	http://arxiv.org/abs/1709.05522v1
PDF	http://arxiv.org/pdf/1709.05522v1.pdf
PWC	https://paperswithcode.com/paper/aishell-1-an-open-source-mandarin-speech
Repo
Framework

Learning Non-local Image Diffusion for Image Denoising


Title	Learning Non-local Image Diffusion for Image Denoising
Authors	Peng Qiao, Yong Dou, Wensen Feng, Yunjin Chen
Abstract	Image diffusion plays a fundamental role for the task of image denoising. Recently proposed trainable nonlinear reaction diffusion (TNRD) model defines a simple but very effective framework for image denoising. However, as the TNRD model is a local model, the diffusion behavior of which is purely controlled by information of local patches, it is prone to create artifacts in the homogenous regions and over-smooth highly textured regions, especially in the case of strong noise levels. Meanwhile, it is widely known that the non-local self-similarity (NSS) prior stands as an effective image prior for image denoising, which has been widely exploited in many non-local methods. In this work, we are highly motivated to embed the NSS prior into the TNRD model to tackle its weaknesses. In order to preserve the expected property that end-to-end training is available, we exploit the NSS prior by a set of non-local filters, and derive our proposed trainable non-local reaction diffusion (TNLRD) model for image denoising. Together with the local filters and influence functions, the non-local filters are learned by employing loss-specific training. The experimental results show that the trained TNLRD model produces visually plausible recovered images with more textures and less artifacts, compared to its local versions. Moreover, the trained TNLRD model can achieve strongly competitive performance to recent state-of-the-art image denoising methods in terms of peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM).
Tasks	Denoising, Image Denoising
Published	2017-02-24
URL	http://arxiv.org/abs/1702.07472v1
PDF	http://arxiv.org/pdf/1702.07472v1.pdf
PWC	https://paperswithcode.com/paper/learning-non-local-image-diffusion-for-image
Repo
Framework

ForestHash: Semantic Hashing With Shallow Random Forests and Tiny Convolutional Networks


Title	ForestHash: Semantic Hashing With Shallow Random Forests and Tiny Convolutional Networks
Authors	Qiang Qiu, Jose Lezama, Alex Bronstein, Guillermo Sapiro
Abstract	Hash codes are efficient data representations for coping with the ever growing amounts of data. In this paper, we introduce a random forest semantic hashing scheme that embeds tiny convolutional neural networks (CNN) into shallow random forests, with near-optimal information-theoretic code aggregation among trees. We start with a simple hashing scheme, where random trees in a forest act as hashing functions by setting `1' for the visited tree leaf, and` 0’ for the rest. We show that traditional random forests fail to generate hashes that preserve the underlying similarity between the trees, rendering the random forests approach to hashing challenging. To address this, we propose to first randomly group arriving classes at each tree split node into two groups, obtaining a significantly simplified two-class classification problem, which can be handled using a light-weight CNN weak learner. Such random class grouping scheme enables code uniqueness by enforcing each class to share its code with different classes in different trees. A non-conventional low-rank loss is further adopted for the CNN weak learners to encourage code consistency by minimizing intra-class variations and maximizing inter-class distance for the two random class groups. Finally, we introduce an information-theoretic approach for aggregating codes of individual trees into a single hash code, producing a near-optimal unique hash for each class. The proposed approach significantly outperforms state-of-the-art hashing methods for image retrieval tasks on large-scale public datasets, while performing at the level of other state-of-the-art image classification techniques while utilizing a more compact and efficient scalable representation. This work proposes a principled and robust procedure to train and deploy in parallel an ensemble of light-weight CNNs, instead of simply going deeper.
Tasks	Image Classification, Image Retrieval
Published	2017-11-22
URL	http://arxiv.org/abs/1711.08364v2
PDF	http://arxiv.org/pdf/1711.08364v2.pdf
PWC	https://paperswithcode.com/paper/foresthash-semantic-hashing-with-shallow
Repo
Framework

Machine Learned Learning Machines


Title	Machine Learned Learning Machines
Authors	Leigh Sheneman, Arend Hintze
Abstract	There are two common approaches for optimizing the performance of a machine: genetic algorithms and machine learning. A genetic algorithm is applied over many generations whereas machine learning works by applying feedback until the system meets a performance threshold. Though these are methods that typically operate separately, we combine evolutionary adaptation and machine learning into one approach. Our focus is on machines that can learn during their lifetime, but instead of equipping them with a machine learning algorithm we aim to let them evolve their ability to learn by themselves. We use evolvable networks of probabilistic and deterministic logic gates, known as Markov Brains, as our computational model organism. The ability of Markov Brains to learn is augmented by a novel adaptive component that can change its computational behavior based on feedback. We show that Markov Brains can indeed evolve to incorporate these feedback gates to improve their adaptability to variable environments. By combining these two methods, we now also implemented a computational model that can be used to study the evolution of learning.
Tasks
Published	2017-05-29
URL	http://arxiv.org/abs/1705.10201v2
PDF	http://arxiv.org/pdf/1705.10201v2.pdf
PWC	https://paperswithcode.com/paper/machine-learned-learning-machines
Repo
Framework