October 17, 2019

2837 words 14 mins read

Paper Group ANR 860

Successful Nash Equilibrium Agent for a 3-Player Imperfect-Information Game. Modelling tourism demand to Spain with machine learning techniques. The impact of forecast horizon on model selection. Semantic See-Through Rendering on Light Fields. Non-local RoIs for Instance Segmentation. Nonlinear Collaborative Scheme for Deep Neural Networks. Design …

Successful Nash Equilibrium Agent for a 3-Player Imperfect-Information Game


Title	Successful Nash Equilibrium Agent for a 3-Player Imperfect-Information Game
Authors	Sam Ganzfried, Austin Nowak, Joannier Pinales
Abstract	Creating strong agents for games with more than two players is a major open problem in AI. Common approaches are based on approximating game-theoretic solution concepts such as Nash equilibrium, which have strong theoretical guarantees in two-player zero-sum games, but no guarantees in non-zero-sum games or in games with more than two players. We describe an agent that is able to defeat a variety of realistic opponents using an exact Nash equilibrium strategy in a 3-player imperfect-information game. This shows that, despite a lack of theoretical guarantees, agents based on Nash equilibrium strategies can be successful in multiplayer games after all.
Tasks
Published	2018-04-13
URL	http://arxiv.org/abs/1804.04789v1
PDF	http://arxiv.org/pdf/1804.04789v1.pdf
PWC	https://paperswithcode.com/paper/successful-nash-equilibrium-agent-for-a-3
Repo
Framework

Modelling tourism demand to Spain with machine learning techniques. The impact of forecast horizon on model selection


Title	Modelling tourism demand to Spain with machine learning techniques. The impact of forecast horizon on model selection
Authors	Oscar Claveria, Enric Monte, Salvador Torra
Abstract	This study assesses the influence of the forecast horizon on the forecasting performance of several machine learning techniques. We compare the fo recast accuracy of Support Vector Regression (SVR) to Neural Network (NN) models, using a linear model as a benchmark. We focus on international tourism demand to all seventeen regions of Spain. The SVR with a Gaussian radial basis function kernel outperforms the rest of the models for the longest forecast horizons. We also find that machine learning methods improve their forecasting accuracy with respect to linear models as forecast horizons increase. This result shows the suitability of SVR for medium and long term forecasting.
Tasks	Model Selection
Published	2018-05-02
URL	http://arxiv.org/abs/1805.00878v1
PDF	http://arxiv.org/pdf/1805.00878v1.pdf
PWC	https://paperswithcode.com/paper/modelling-tourism-demand-to-spain-with
Repo
Framework

Semantic See-Through Rendering on Light Fields


Title	Semantic See-Through Rendering on Light Fields
Authors	Huangjie Yu, Guli Zhang, Yuanxi Ma, Yingliang Zhang, Jingyi Yu
Abstract	We present a novel semantic light field (LF) refocusing technique that can achieve unprecedented see-through quality. Different from prior art, our semantic see-through (SST) differentiates rays in their semantic meaning and depth. Specifically, we combine deep learning and stereo matching to provide each ray a semantic label. We then design tailored weighting schemes for blending the rays. Although simple, our solution can effectively remove foreground residues when focusing on the background. At the same time, SST maintains smooth transitions in varying focal depths. Comprehensive experiments on synthetic and new real indoor and outdoor datasets demonstrate the effectiveness and usefulness of our technique.
Tasks	Stereo Matching, Stereo Matching Hand
Published	2018-03-26
URL	http://arxiv.org/abs/1803.09474v1
PDF	http://arxiv.org/pdf/1803.09474v1.pdf
PWC	https://paperswithcode.com/paper/semantic-see-through-rendering-on-light
Repo
Framework

Non-local RoIs for Instance Segmentation


Title	Non-local RoIs for Instance Segmentation
Authors	Shou-Yao Roy Tseng, Hwann-Tzong Chen, Shao-Heng Tai, Tyng-Luh Liu
Abstract	We introduce the concept of Non-Local RoI (NL-RoI) Block as a generic and flexible module that can be seamlessly adapted into different Mask R-CNN heads for various tasks. Mask R-CNN treats RoIs (Regions of Interest) independently and performs the prediction based on individual object bounding boxes. However, the correlation between objects may provide useful information for detection and segmentation. The proposed NL-RoI Block enables each RoI to refer to all other RoIs’ information, and results in a simple, low-cost but effective module. Our experimental results show that generalizations with NL-RoI Blocks can improve the performance of Mask R-CNN for instance segmentation on the Robust Vision Challenge benchmarks.
Tasks	Instance Segmentation, Semantic Segmentation
Published	2018-07-14
URL	http://arxiv.org/abs/1807.05361v1
PDF	http://arxiv.org/pdf/1807.05361v1.pdf
PWC	https://paperswithcode.com/paper/non-local-rois-for-instance-segmentation
Repo
Framework

Nonlinear Collaborative Scheme for Deep Neural Networks


Title	Nonlinear Collaborative Scheme for Deep Neural Networks
Authors	Hui-Ling Zhen, Xi Lin, Alan Z. Tang, Zhenhua Li, Qingfu Zhang, Sam Kwong
Abstract	Conventional research attributes the improvements of generalization ability of deep neural networks either to powerful optimizers or the new network design. Different from them, in this paper, we aim to link the generalization ability of a deep network to optimizing a new objective function. To this end, we propose a \textit{nonlinear collaborative scheme} for deep network training, with the key technique as combining different loss functions in a nonlinear manner. We find that after adaptively tuning the weights of different loss functions, the proposed objective function can efficiently guide the optimization process. What is more, we demonstrate that, from the mathematical perspective, the nonlinear collaborative scheme can lead to (i) smaller KL divergence with respect to optimal solutions; (ii) data-driven stochastic gradient descent; (iii) tighter PAC-Bayes bound. We also prove that its advantage can be strengthened by nonlinearity increasing. To some extent, we bridge the gap between learning (i.e., minimizing the new objective function) and generalization (i.e., minimizing a PAC-Bayes bound) in the new scheme. We also interpret our findings through the experiments on Residual Networks and DenseNet, showing that our new scheme performs superior to single-loss and multi-loss schemes no matter with randomization or not.
Tasks
Published	2018-11-04
URL	http://arxiv.org/abs/1811.01316v1
PDF	http://arxiv.org/pdf/1811.01316v1.pdf
PWC	https://paperswithcode.com/paper/nonlinear-collaborative-scheme-for-deep
Repo
Framework

Design Rule Violation Hotspot Prediction Based on Neural Network Ensembles


Title	Design Rule Violation Hotspot Prediction Based on Neural Network Ensembles
Authors	Wei Zeng, Azadeh Davoodi, Yu Hen Hu
Abstract	Design rule check is a critical step in the physical design of integrated circuits to ensure manufacturability. However, it can be done only after a time-consuming detailed routing procedure, which adds drastically to the time of design iterations. With advanced technology nodes, the outcomes of global routing and detailed routing become less correlated, which adds to the difficulty of predicting design rule violations from earlier stages. In this paper, a framework based on neural network ensembles is proposed to predict design rule violation hotspots using information from placement and global routing. A soft voting structure and a PCA-based subset selection scheme are developed on top of a baseline neural network from a recent work. Experimental results show that the proposed architecture achieves significant improvement in model performance compared to the baseline case. For half of test cases, the performance is even better than random forest, a commonly-used ensemble learning model.
Tasks
Published	2018-11-09
URL	http://arxiv.org/abs/1811.04151v1
PDF	http://arxiv.org/pdf/1811.04151v1.pdf
PWC	https://paperswithcode.com/paper/design-rule-violation-hotspot-prediction
Repo
Framework

From Nodes to Networks: Evolving Recurrent Neural Networks


Title	From Nodes to Networks: Evolving Recurrent Neural Networks
Authors	Aditya Rawal, Risto Miikkulainen
Abstract	Gated recurrent networks such as those composed of Long Short-Term Memory (LSTM) nodes have recently been used to improve state of the art in many sequential processing tasks such as speech recognition and machine translation. However, the basic structure of the LSTM node is essentially the same as when it was first conceived 25 years ago. Recently, evolutionary and reinforcement learning mechanisms have been employed to create new variations of this structure. This paper proposes a new method, evolution of a tree-based encoding of the gated memory nodes, and shows that it makes it possible to explore new variations more effectively than other methods. The method discovers nodes with multiple recurrent paths and multiple memory cells, which lead to significant improvement in the standard language modeling benchmark task. The paper also shows how the search process can be speeded up by training an LSTM network to estimate performance of candidate structures, and by encouraging exploration of novel solutions. Thus, evolutionary design of complex neural network structures promises to improve performance of deep learning architectures beyond human ability to do so.
Tasks	Language Modelling, Machine Translation, Speech Recognition
Published	2018-03-12
URL	http://arxiv.org/abs/1803.04439v2
PDF	http://arxiv.org/pdf/1803.04439v2.pdf
PWC	https://paperswithcode.com/paper/from-nodes-to-networks-evolving-recurrent
Repo
Framework

tau-FPL: Tolerance-Constrained Learning in Linear Time


Title	tau-FPL: Tolerance-Constrained Learning in Linear Time
Authors	Ao Zhang, Nan Li, Jian Pu, Jun Wang, Junchi Yan, Hongyuan Zha
Abstract	Learning a classifier with control on the false-positive rate plays a critical role in many machine learning applications. Existing approaches either introduce prior knowledge dependent label cost or tune parameters based on traditional classifiers, which lack consistency in methodology because they do not strictly adhere to the false-positive rate constraint. In this paper, we propose a novel scoring-thresholding approach, tau-False Positive Learning (tau-FPL) to address this problem. We show the scoring problem which takes the false-positive rate tolerance into accounts can be efficiently solved in linear time, also an out-of-bootstrap thresholding method can transform the learned ranking function into a low false-positive classifier. Both theoretical analysis and experimental results show superior performance of the proposed tau-FPL over existing approaches.
Tasks
Published	2018-01-15
URL	http://arxiv.org/abs/1801.04701v1
PDF	http://arxiv.org/pdf/1801.04701v1.pdf
PWC	https://paperswithcode.com/paper/tau-fpl-tolerance-constrained-learning-in
Repo
Framework

Monolingual and Cross-lingual Zero-shot Style Transfer


Title	Monolingual and Cross-lingual Zero-shot Style Transfer
Authors	Elizaveta Korotkova, Maksym Del, Mark Fishel
Abstract	We introduce the task of zero-shot style transfer between different languages. Our training data includes multilingual parallel corpora, but does not contain any parallel sentences between styles, similarly to the recent previous work. We propose a unified multilingual multi-style machine translation system design, that allows to perform zero-shot style conversions during inference; moreover, it does so both monolingually and cross-lingually. Our model allows to increase the presence of dissimilar styles in corpus by up to 3 times, easily learns to operate with various contractions, and provides reasonable lexicon swaps as we see from manual evaluation.
Tasks	Machine Translation, Style Transfer
Published	2018-08-01
URL	http://arxiv.org/abs/1808.00179v1
PDF	http://arxiv.org/pdf/1808.00179v1.pdf
PWC	https://paperswithcode.com/paper/monolingual-and-cross-lingual-zero-shot-style
Repo
Framework

Temporal Saliency Adaptation in Egocentric Videos


Title	Temporal Saliency Adaptation in Egocentric Videos
Authors	Panagiotis Linardos, Eva Mohedano, Monica Cherto, Cathal Gurrin, Xavier Giro-i-Nieto
Abstract	This work adapts a deep neural model for image saliency prediction to the temporal domain of egocentric video. We compute the saliency map for each video frame, firstly with an off-the-shelf model trained from static images, secondly by adding a a convolutional or conv-LSTM layers trained with a dataset for video saliency prediction. We study each configuration on EgoMon, a new dataset made of seven egocentric videos recorded by three subjects in both free-viewing and task-driven set ups. Our results indicate that the temporal adaptation is beneficial when the viewer is not moving and observing the scene from a narrow field of view. Encouraged by this observation, we compute and publish the saliency maps for the EPIC Kitchens dataset, in which viewers are cooking. Source code and models available at https://imatge-upc.github.io/saliency-2018-videosalgan/
Tasks	Saliency Prediction
Published	2018-08-28
URL	http://arxiv.org/abs/1808.09559v2
PDF	http://arxiv.org/pdf/1808.09559v2.pdf
PWC	https://paperswithcode.com/paper/temporal-saliency-adaptation-in-egocentric
Repo
Framework

Efficient CNN Implementation for Eye-Gaze Estimation on Low-Power/Low-Quality Consumer Imaging Systems


Title	Efficient CNN Implementation for Eye-Gaze Estimation on Low-Power/Low-Quality Consumer Imaging Systems
Authors	Joseph Lemley, Anuradha Kar, Alexandru Drimbarean, Peter Corcoran
Abstract	Accurate and efficient eye gaze estimation is important for emerging consumer electronic systems such as driver monitoring systems and novel user interfaces. Such systems are required to operate reliably in difficult, unconstrained environments with low power consumption and at minimal cost. In this paper a new hardware friendly, convolutional neural network model with minimal computational requirements is introduced and assessed for efficient appearance-based gaze estimation. The model is tested and compared against existing appearance based CNN approaches, achieving better eye gaze accuracy with significantly fewer computational requirements. A brief updated literature review is also provided.
Tasks	Gaze Estimation
Published	2018-06-28
URL	http://arxiv.org/abs/1806.10890v1
PDF	http://arxiv.org/pdf/1806.10890v1.pdf
PWC	https://paperswithcode.com/paper/efficient-cnn-implementation-for-eye-gaze
Repo
Framework

Coarse-to-Fine Salient Object Detection with Low-Rank Matrix Recovery


Title	Coarse-to-Fine Salient Object Detection with Low-Rank Matrix Recovery
Authors	Qi Zheng, Shujian Yu, Xinge You, Qinmu Peng
Abstract	Low-Rank Matrix Recovery (LRMR) has recently been applied to saliency detection by decomposing image features into a low-rank component associated with background and a sparse component associated with visual salient regions. Despite its great potential, existing LRMR-based saliency detection methods seldom consider the inter-relationship among elements within these two components, thus are prone to generating scattered or incomplete saliency maps. In this paper, we introduce a novel and efficient LRMR-based saliency detection model under a coarse-to-fine framework to circumvent this limitation. First, we roughly measure the saliency of image regions with a baseline LRMR model that integrates a $\ell_1$-norm sparsity constraint and a Laplacian regularization smooth term. Given samples from the coarse saliency map, we then learn a projection that maps image features to refined saliency values, to significantly sharpen the object boundaries and to preserve the object entirety. We evaluate our framework against existing LRMR-based methods on three benchmark datasets. Experimental results validate the superiority of our method as well as the effectiveness of our suggested coarse-to-fine framework, especially for images containing multiple objects.
Tasks	Object Detection, Saliency Detection, Salient Object Detection
Published	2018-05-21
URL	https://arxiv.org/abs/1805.07936v4
PDF	https://arxiv.org/pdf/1805.07936v4.pdf
PWC	https://paperswithcode.com/paper/coarse-to-fine-salient-object-detection-with
Repo
Framework

On the Local Minima of the Empirical Risk


Title	On the Local Minima of the Empirical Risk
Authors	Chi Jin, Lydia T. Liu, Rong Ge, Michael I. Jordan
Abstract	Population risk is always of primary interest in machine learning; however, learning algorithms only have access to the empirical risk. Even for applications with nonconvex nonsmooth losses (such as modern deep networks), the population risk is generally significantly more well-behaved from an optimization point of view than the empirical risk. In particular, sampling can create many spurious local minima. We consider a general framework which aims to optimize a smooth nonconvex function $F$ (population risk) given only access to an approximation $f$ (empirical risk) that is pointwise close to $F$ (i.e., $\F-f_{\infty} \le \nu$). Our objective is to find the $\epsilon$-approximate local minima of the underlying function $F$ while avoiding the shallow local minima—arising because of the tolerance $\nu$—which exist only in $f$. We propose a simple algorithm based on stochastic gradient descent (SGD) on a smoothed version of $f$ that is guaranteed to achieve our goal as long as $\nu \le O(\epsilon^{1.5}/d)$. We also provide an almost matching lower bound showing that our algorithm achieves optimal error tolerance $\nu$ among all algorithms making a polynomial number of queries of $f$. As a concrete example, we show that our results can be directly used to give sample complexities for learning a ReLU unit.
Tasks
Published	2018-03-25
URL	http://arxiv.org/abs/1803.09357v2
PDF	http://arxiv.org/pdf/1803.09357v2.pdf
PWC	https://paperswithcode.com/paper/on-the-local-minima-of-the-empirical-risk
Repo
Framework

Necessary and Sufficient Null Space Condition for Nuclear Norm Minimization in Low-Rank Matrix Recovery


Title	Necessary and Sufficient Null Space Condition for Nuclear Norm Minimization in Low-Rank Matrix Recovery
Authors	Jirong Yi, Weiyu Xu
Abstract	Low-rank matrix recovery has found many applications in science and engineering such as machine learning, signal processing, collaborative filtering, system identification, and Euclidean embedding. But the low-rank matrix recovery problem is an NP hard problem and thus challenging. A commonly used heuristic approach is the nuclear norm minimization. In [12,14,15], the authors established the necessary and sufficient null space conditions for nuclear norm minimization to recover every possible low-rank matrix with rank at most r (the strong null space condition). In addition, in [12], Oymak et al. established a null space condition for successful recovery of a given low-rank matrix (the weak null space condition) using nuclear norm minimization, and derived the phase transition for the nuclear norm minimization. In this paper, we show that the weak null space condition in [12] is only a sufficient condition for successful matrix recovery using nuclear norm minimization, and is not a necessary condition as claimed in [12]. In this paper, we further give a weak null space condition for low-rank matrix recovery, which is both necessary and sufficient for the success of nuclear norm minimization. At the core of our derivation are an inequality for characterizing the nuclear norms of block matrices, and the conditions for equality to hold in that inequality.
Tasks
Published	2018-02-14
URL	http://arxiv.org/abs/1802.05234v1
PDF	http://arxiv.org/pdf/1802.05234v1.pdf
PWC	https://paperswithcode.com/paper/necessary-and-sufficient-null-space-condition
Repo
Framework

Task-specific Deep LDA pruning of neural networks


Title	Task-specific Deep LDA pruning of neural networks
Authors	Qing Tian, Tal Arbel, James J. Clark
Abstract	With deep learning’s success, a limited number of popular deep nets have been widely adopted for various vision tasks. However, this usually results in unnecessarily high complexities and possibly many features of low task utility. In this paper, we address this problem by introducing a task-dependent deep pruning framework based on Fisher’s Linear Discriminant Analysis (LDA). The approach can be applied to convolutional, fully-connected, and module-based deep network structures, in all cases leveraging the high decorrelation of neuron motifs found in the pre-decision layer and cross-layer deconv dependency. Moreover, we examine our approach’s potential in network architecture search for specific tasks and analyze the influence of our pruning on model robustness to noises and adversarial attacks. Experimental results on datasets of generic objects, as well as domain specific tasks (CIFAR100, Adience, and LFWA) illustrate our framework’s superior performance over state-of-the-art pruning approaches and fixed compact nets (e.g. SqueezeNet, MobileNet). The proposed method successfully maintains comparable accuracies even after discarding most parameters (98%-99% for VGG16, up to 82% for the already compact InceptionNet) and with significant FLOP reductions (83% for VGG16, up to 64% for InceptionNet). Through pruning, we can also derive smaller, but more accurate and more robust models suitable for the task.
Tasks
Published	2018-03-21
URL	https://arxiv.org/abs/1803.08134v5
PDF	https://arxiv.org/pdf/1803.08134v5.pdf
PWC	https://paperswithcode.com/paper/fisher-pruning-of-deep-nets-for-facial-trait
Repo
Framework