July 28, 2019

3141 words 15 mins read

Paper Group ANR 183

Manifold-valued Image Generation with Wasserstein Generative Adversarial Nets. Estimating Mutual Information for Discrete-Continuous Mixtures. Exact Inference for Relational Graphical Models with Interpreted Functions: Lifted Probabilistic Inference Modulo Theories. View Independent Vehicle Make, Model and Color Recognition Using Convolutional Neur …

Manifold-valued Image Generation with Wasserstein Generative Adversarial Nets


Title	Manifold-valued Image Generation with Wasserstein Generative Adversarial Nets
Authors	Zhiwu Huang, Jiqing Wu, Luc Van Gool
Abstract	Generative modeling over natural images is one of the most fundamental machine learning problems. However, few modern generative models, including Wasserstein Generative Adversarial Nets (WGANs), are studied on manifold-valued images that are frequently encountered in real-world applications. To fill the gap, this paper first formulates the problem of generating manifold-valued images and exploits three typical instances: hue-saturation-value (HSV) color image generation, chromaticity-brightness (CB) color image generation, and diffusion-tensor (DT) image generation. For the proposed generative modeling problem, we then introduce a theorem of optimal transport to derive a new Wasserstein distance of data distributions on complete manifolds, enabling us to achieve a tractable objective under the WGAN framework. In addition, we recommend three benchmark datasets that are CIFAR-10 HSV/CB color images, ImageNet HSV/CB color images, UCL DT image datasets. On the three datasets, we experimentally demonstrate the proposed manifold-aware WGAN model can generate more plausible manifold-valued images than its competitors.
Tasks	Image Generation
Published	2017-12-05
URL	http://arxiv.org/abs/1712.01551v2
PDF	http://arxiv.org/pdf/1712.01551v2.pdf
PWC	https://paperswithcode.com/paper/manifold-valued-image-generation-with
Repo
Framework

Estimating Mutual Information for Discrete-Continuous Mixtures


Title	Estimating Mutual Information for Discrete-Continuous Mixtures
Authors	Weihao Gao, Sreeram Kannan, Sewoong Oh, Pramod Viswanath
Abstract	Estimating mutual information from observed samples is a basic primitive, useful in several machine learning tasks including correlation mining, information bottleneck clustering, learning a Chow-Liu tree, and conditional independence testing in (causal) graphical models. While mutual information is a well-defined quantity in general probability spaces, existing estimators can only handle two special cases of purely discrete or purely continuous pairs of random variables. The main challenge is that these methods first estimate the (differential) entropies of X, Y and the pair (X;Y) and add them up with appropriate signs to get an estimate of the mutual information. These 3H-estimators cannot be applied in general mixture spaces, where entropy is not well-defined. In this paper, we design a novel estimator for mutual information of discrete-continuous mixtures. We prove that the proposed estimator is consistent. We provide numerical experiments suggesting superiority of the proposed estimator compared to other heuristics of adding small continuous noise to all the samples and applying standard estimators tailored for purely continuous variables, and quantizing the samples and applying standard estimators tailored for purely discrete variables. This significantly widens the applicability of mutual information estimation in real-world applications, where some variables are discrete, some continuous, and others are a mixture between continuous and discrete components.
Tasks
Published	2017-09-19
URL	http://arxiv.org/abs/1709.06212v3
PDF	http://arxiv.org/pdf/1709.06212v3.pdf
PWC	https://paperswithcode.com/paper/estimating-mutual-information-for-discrete
Repo
Framework

Exact Inference for Relational Graphical Models with Interpreted Functions: Lifted Probabilistic Inference Modulo Theories


Title	Exact Inference for Relational Graphical Models with Interpreted Functions: Lifted Probabilistic Inference Modulo Theories
Authors	Rodrigo de Salvo Braz, Ciaran O’Reilly
Abstract	Probabilistic Inference Modulo Theories (PIMT) is a recent framework that expands exact inference on graphical models to use richer languages that include arithmetic, equalities, and inequalities on both integers and real numbers. In this paper, we expand PIMT to a lifted version that also processes random functions and relations. This enhancement is achieved by adapting Inversion, a method from Lifted First-Order Probabilistic Inference literature, to also be modulo theories. This results in the first algorithm for exact probabilistic inference that efficiently and simultaneously exploits random relations and functions, arithmetic, equalities and inequalities.
Tasks
Published	2017-09-04
URL	http://arxiv.org/abs/1709.01122v1
PDF	http://arxiv.org/pdf/1709.01122v1.pdf
PWC	https://paperswithcode.com/paper/exact-inference-for-relational-graphical
Repo
Framework

View Independent Vehicle Make, Model and Color Recognition Using Convolutional Neural Network


Title	View Independent Vehicle Make, Model and Color Recognition Using Convolutional Neural Network
Authors	Afshin Dehghan, Syed Zain Masood, Guang Shu, Enrique. G. Ortiz
Abstract	This paper describes the details of Sighthound’s fully automated vehicle make, model and color recognition system. The backbone of our system is a deep convolutional neural network that is not only computationally inexpensive, but also provides state-of-the-art results on several competitive benchmarks. Additionally, our deep network is trained on a large dataset of several million images which are labeled through a semi-automated process. Finally we test our system on several public datasets as well as our own internal test dataset. Our results show that we outperform other methods on all benchmarks by significant margins. Our model is available to developers through the Sighthound Cloud API at https://www.sighthound.com/products/cloud
Tasks
Published	2017-02-06
URL	http://arxiv.org/abs/1702.01721v1
PDF	http://arxiv.org/pdf/1702.01721v1.pdf
PWC	https://paperswithcode.com/paper/view-independent-vehicle-make-model-and-color
Repo
Framework

Deep Learning-Guided Image Reconstruction from Incomplete Data


Title	Deep Learning-Guided Image Reconstruction from Incomplete Data
Authors	Brendan Kelly, Thomas P. Matthews, Mark A. Anastasio
Abstract	An approach to incorporate deep learning within an iterative image reconstruction framework to reconstruct images from severely incomplete measurement data is presented. Specifically, we utilize a convolutional neural network (CNN) as a quasi-projection operator within a least squares minimization procedure. The CNN is trained to encode high level information about the class of images being imaged; this information is utilized to mitigate artifacts in intermediate images produced by use of an iterative method. The structure of the method was inspired by the proximal gradient descent method, where the proximal operator is replaced by a deep CNN and the gradient descent step is generalized by use of a linear reconstruction operator. It is demonstrated that this approach improves image quality for several cases of limited-view image reconstruction and that using a CNN in an iterative method increases performance compared to conventional image reconstruction approaches. We test our method on several limited-view image reconstruction problems. Qualitative and quantitative results demonstrate state-of-the-art performance.
Tasks	Image Reconstruction
Published	2017-09-02
URL	http://arxiv.org/abs/1709.00584v1
PDF	http://arxiv.org/pdf/1709.00584v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-guided-image-reconstruction
Repo
Framework

A Meta-Learning Approach to One-Step Active Learning


Title	A Meta-Learning Approach to One-Step Active Learning
Authors	Gabriella Contardo, Ludovic Denoyer, Thierry Artieres
Abstract	We consider the problem of learning when obtaining the training labels is costly, which is usually tackled in the literature using active-learning techniques. These approaches provide strategies to choose the examples to label before or during training. These strategies are usually based on heuristics or even theoretical measures, but are not learned as they are directly used during training. We design a model which aims at \textit{learning active-learning strategies} using a meta-learning setting. More specifically, we consider a pool-based setting, where the system observes all the examples of the dataset of a problem and has to choose the subset of examples to label in a single shot. Experiments show encouraging results.
Tasks	Active Learning, Meta-Learning
Published	2017-06-26
URL	http://arxiv.org/abs/1706.08334v2
PDF	http://arxiv.org/pdf/1706.08334v2.pdf
PWC	https://paperswithcode.com/paper/a-meta-learning-approach-to-one-step-active
Repo
Framework

Tackling Over-pruning in Variational Autoencoders


Title	Tackling Over-pruning in Variational Autoencoders
Authors	Serena Yeung, Anitha Kannan, Yann Dauphin, Li Fei-Fei
Abstract	Variational autoencoders (VAE) are directed generative models that learn factorial latent variables. As noted by Burda et al. (2015), these models exhibit the problem of factor over-pruning where a significant number of stochastic factors fail to learn anything and become inactive. This can limit their modeling power and their ability to learn diverse and meaningful latent representations. In this paper, we evaluate several methods to address this problem and propose a more effective model-based approach called the epitomic variational autoencoder (eVAE). The so-called epitomes of this model are groups of mutually exclusive latent factors that compete to explain the data. This approach helps prevent inactive units since each group is pressured to explain the data. We compare the approaches with qualitative and quantitative results on MNIST and TFD datasets. Our results show that eVAE makes efficient use of model capacity and generalizes better than VAE.
Tasks
Published	2017-06-09
URL	http://arxiv.org/abs/1706.03643v2
PDF	http://arxiv.org/pdf/1706.03643v2.pdf
PWC	https://paperswithcode.com/paper/tackling-over-pruning-in-variational
Repo
Framework

Pixelwise Instance Segmentation with a Dynamically Instantiated Network


Title	Pixelwise Instance Segmentation with a Dynamically Instantiated Network
Authors	Anurag Arnab, Philip H. S Torr
Abstract	Semantic segmentation and object detection research have recently achieved rapid progress. However, the former task has no notion of different instances of the same object, and the latter operates at a coarse, bounding-box level. We propose an Instance Segmentation system that produces a segmentation map where each pixel is assigned an object class and instance identity label. Most approaches adapt object detectors to produce segments instead of boxes. In contrast, our method is based on an initial semantic segmentation module, which feeds into an instance subnetwork. This subnetwork uses the initial category-level segmentation, along with cues from the output of an object detector, within an end-to-end CRF to predict instances. This part of our model is dynamically instantiated to produce a variable number of instances per image. Our end-to-end approach requires no post-processing and considers the image holistically, instead of processing independent proposals. Therefore, unlike some related work, a pixel cannot belong to multiple instances. Furthermore, far more precise segmentations are achieved, as shown by our state-of-the-art results (particularly at high IoU thresholds) on the Pascal VOC and Cityscapes datasets.
Tasks	Instance Segmentation, Object Detection, Panoptic Segmentation, Semantic Segmentation
Published	2017-04-07
URL	http://arxiv.org/abs/1704.02386v1
PDF	http://arxiv.org/pdf/1704.02386v1.pdf
PWC	https://paperswithcode.com/paper/pixelwise-instance-segmentation-with-a
Repo
Framework

Adversarial Generation of Training Examples: Applications to Moving Vehicle License Plate Recognition


Title	Adversarial Generation of Training Examples: Applications to Moving Vehicle License Plate Recognition
Authors	Xinlong Wang, Zhipeng Man, Mingyu You, Chunhua Shen
Abstract	Generative Adversarial Networks (GAN) have attracted much research attention recently, leading to impressive results for natural image generation. However, to date little success was observed in using GAN generated images for improving classification tasks. Here we attempt to explore, in the context of car license plate recognition, whether it is possible to generate synthetic training data using GAN to improve recognition accuracy. With a carefully-designed pipeline, we show that the answer is affirmative. First, a large-scale image set is generated using the generator of GAN, without manual annotation. Then, these images are fed to a deep convolutional neural network (DCNN) followed by a bidirectional recurrent neural network (BRNN) with long short-term memory (LSTM), which performs the feature learning and sequence labelling. Finally, the pre-trained model is fine-tuned on real images. Our experimental results on a few data sets demonstrate the effectiveness of using GAN images: an improvement of 7.5% over a strong baseline with moderate-sized real data being available. We show that the proposed framework achieves competitive recognition accuracy on challenging test datasets. We also leverage the depthwise separate convolution to construct a lightweight convolutional RNN, which is about half size and 2x faster on CPU. Combining this framework and the proposed pipeline, we make progress in performing accurate recognition on mobile and embedded devices.
Tasks	Image Generation, License Plate Recognition
Published	2017-07-11
URL	http://arxiv.org/abs/1707.03124v3
PDF	http://arxiv.org/pdf/1707.03124v3.pdf
PWC	https://paperswithcode.com/paper/adversarial-generation-of-training-examples
Repo
Framework

Image Generation from Sketch Constraint Using Contextual GAN


Title	Image Generation from Sketch Constraint Using Contextual GAN
Authors	Yongyi Lu, Shangzhe Wu, Yu-Wing Tai, Chi-Keung Tang
Abstract	In this paper we investigate image generation guided by hand sketch. When the input sketch is badly drawn, the output of common image-to-image translation follows the input edges due to the hard condition imposed by the translation process. Instead, we propose to use sketch as weak constraint, where the output edges do not necessarily follow the input edges. We address this problem using a novel joint image completion approach, where the sketch provides the image context for completing, or generating the output image. We train a generated adversarial network, i.e, contextual GAN to learn the joint distribution of sketch and the corresponding image by using joint images. Our contextual GAN has several advantages. First, the simple joint image representation allows for simple and effective learning of joint distribution in the same image-sketch space, which avoids complicated issues in cross-domain learning. Second, while the output is related to its input overall, the generated features exhibit more freedom in appearance and do not strictly align with the input features as previous conditional GANs do. Third, from the joint image’s point of view, image and sketch are of no difference, thus exactly the same deep joint image completion network can be used for image-to-sketch generation. Experiments evaluated on three different datasets show that our contextual GAN can generate more realistic images than state-of-the-art conditional GANs on challenging inputs and generalize well on common categories.
Tasks	Image Generation, Image-to-Image Translation
Published	2017-11-24
URL	http://arxiv.org/abs/1711.08972v2
PDF	http://arxiv.org/pdf/1711.08972v2.pdf
PWC	https://paperswithcode.com/paper/image-generation-from-sketch-constraint-using
Repo
Framework

Submodular Function Maximization for Group Elevator Scheduling


Title	Submodular Function Maximization for Group Elevator Scheduling
Authors	Srikumar Ramalingam, Arvind U. Raghunathan, Daniel Nikovski
Abstract	We propose a novel approach for group elevator scheduling by formulating it as the maximization of submodular function under a matroid constraint. In particular, we propose to model the total waiting time of passengers using a quadratic Boolean function. The unary and pairwise terms in the function denote the waiting time for single and pairwise allocation of passengers to elevators, respectively. We show that this objective function is submodular. The matroid constraints ensure that every passenger is allocated to exactly one elevator. We use a greedy algorithm to maximize the submodular objective function, and derive provable guarantees on the optimality of the solution. We tested our algorithm using Elevate 8, a commercial-grade elevator simulator that allows simulation with a wide range of elevator settings. We achieve significant improvement over the existing algorithms.
Tasks
Published	2017-06-28
URL	http://arxiv.org/abs/1707.00617v1
PDF	http://arxiv.org/pdf/1707.00617v1.pdf
PWC	https://paperswithcode.com/paper/submodular-function-maximization-for-group
Repo
Framework

Using Argument-based Features to Predict and Analyse Review Helpfulness


Title	Using Argument-based Features to Predict and Analyse Review Helpfulness
Authors	Haijing Liu, Yang Gao, Pin Lv, Mengxue Li, Shiqiang Geng, Minglan Li, Hao Wang
Abstract	We study the helpful product reviews identification problem in this paper. We observe that the evidence-conclusion discourse relations, also known as arguments, often appear in product reviews, and we hypothesise that some argument-based features, e.g. the percentage of argumentative sentences, the evidences-conclusions ratios, are good indicators of helpful reviews. To validate this hypothesis, we manually annotate arguments in 110 hotel reviews, and investigate the effectiveness of several combinations of argument-based features. Experiments suggest that, when being used together with the argument-based features, the state-of-the-art baseline features can enjoy a performance boost (in terms of F1) of 11.01% in average.
Tasks
Published	2017-07-23
URL	http://arxiv.org/abs/1707.07279v1
PDF	http://arxiv.org/pdf/1707.07279v1.pdf
PWC	https://paperswithcode.com/paper/using-argument-based-features-to-predict-and
Repo
Framework

Greedy Algorithms for Cone Constrained Optimization with Convergence Guarantees


Title	Greedy Algorithms for Cone Constrained Optimization with Convergence Guarantees
Authors	Francesco Locatello, Michael Tschannen, Gunnar Rätsch, Martin Jaggi
Abstract	Greedy optimization methods such as Matching Pursuit (MP) and Frank-Wolfe (FW) algorithms regained popularity in recent years due to their simplicity, effectiveness and theoretical guarantees. MP and FW address optimization over the linear span and the convex hull of a set of atoms, respectively. In this paper, we consider the intermediate case of optimization over the convex cone, parametrized as the conic hull of a generic atom set, leading to the first principled definitions of non-negative MP algorithms for which we give explicit convergence rates and demonstrate excellent empirical performance. In particular, we derive sublinear ($\mathcal{O}(1/t)$) convergence on general smooth and convex objectives, and linear convergence ($\mathcal{O}(e^{-t})$) on strongly convex objectives, in both cases for general sets of atoms. Furthermore, we establish a clear correspondence of our algorithms to known algorithms from the MP and FW literature. Our novel algorithms and analyses target general atom sets and general objective functions, and hence are directly applicable to a large variety of learning settings.
Tasks
Published	2017-05-31
URL	http://arxiv.org/abs/1705.11041v3
PDF	http://arxiv.org/pdf/1705.11041v3.pdf
PWC	https://paperswithcode.com/paper/greedy-algorithms-for-cone-constrained
Repo
Framework

A General Theory of Sample Complexity for Multi-Item Profit Maximization


Title	A General Theory of Sample Complexity for Multi-Item Profit Maximization
Authors	Maria-Florina Balcan, Tuomas Sandholm, Ellen Vitercik
Abstract	The design of profit-maximizing multi-item mechanisms is a notoriously challenging problem with tremendous real-world impact. The mechanism designer’s goal is to field a mechanism with high expected profit on the distribution over buyers’ values. Unfortunately, if the set of mechanisms he optimizes over is complex, a mechanism may have high empirical profit over a small set of samples but low expected profit. This raises the question, how many samples are sufficient to ensure that the empirically optimal mechanism is nearly optimal in expectation? We uncover structure shared by a myriad of pricing, auction, and lottery mechanisms that allows us to prove strong sample complexity bounds: for any set of buyers’ values, profit is a piecewise linear function of the mechanism’s parameters. We prove new bounds for mechanism classes not yet studied in the sample-based mechanism design literature and match or improve over the best known guarantees for many classes. The profit functions we study are significantly different from well-understood functions in machine learning, so our analysis requires a sharp understanding of the interplay between mechanism parameters and buyer values. We strengthen our main results with data-dependent bounds when the distribution over buyers’ values is “well-behaved.” Finally, we investigate a fundamental tradeoff in sample-based mechanism design: complex mechanisms often have higher profit than simple mechanisms, but more samples are required to ensure that empirical and expected profit are close. We provide techniques for optimizing this tradeoff.
Tasks
Published	2017-04-29
URL	http://arxiv.org/abs/1705.00243v4
PDF	http://arxiv.org/pdf/1705.00243v4.pdf
PWC	https://paperswithcode.com/paper/a-general-theory-of-sample-complexity-for
Repo
Framework

N2N Learning: Network to Network Compression via Policy Gradient Reinforcement Learning


Title	N2N Learning: Network to Network Compression via Policy Gradient Reinforcement Learning
Authors	Anubhav Ashok, Nicholas Rhinehart, Fares Beainy, Kris M. Kitani
Abstract	While bigger and deeper neural network architectures continue to advance the state-of-the-art for many computer vision tasks, real-world adoption of these networks is impeded by hardware and speed constraints. Conventional model compression methods attempt to address this problem by modifying the architecture manually or using pre-defined heuristics. Since the space of all reduced architectures is very large, modifying the architecture of a deep neural network in this way is a difficult task. In this paper, we tackle this issue by introducing a principled method for learning reduced network architectures in a data-driven way using reinforcement learning. Our approach takes a larger `teacher' network as input and outputs a compressed` student’ network derived from the `teacher' network. In the first stage of our method, a recurrent policy network aggressively removes layers from the large` teacher’ model. In the second stage, another recurrent policy network carefully reduces the size of each remaining layer. The resulting network is then evaluated to obtain a reward – a score based on the accuracy and compression of the network. Our approach uses this reward signal with policy gradients to train the policies to find a locally optimal student network. Our experiments show that we can achieve compression rates of more than 10x for models such as ResNet-34 while maintaining similar performance to the input `teacher' network. We also present a valuable transfer learning result which shows that policies which are pre-trained on smaller` teacher’ networks can be used to rapidly speed up training on larger `teacher’ networks. \|
Tasks	Model Compression, Transfer Learning
Published	2017-09-18
URL	http://arxiv.org/abs/1709.06030v2
PDF	http://arxiv.org/pdf/1709.06030v2.pdf
PWC	https://paperswithcode.com/paper/n2n-learning-network-to-network-compression
Repo
Framework