Paper Group ANR 342
Iterate averaging as regularization for stochastic gradient descent. Interest Point Detection based on Adaptive Ternary Coding. Hole Filling with Multiple Reference Views in DIBR View Synthesis. On the Implicit Bias of Dropout. An Investigation of Environmental Influence on the Benefits of Adaptation Mechanisms in Evolutionary Swarm Robotics. Sound …
Iterate averaging as regularization for stochastic gradient descent
Title | Iterate averaging as regularization for stochastic gradient descent |
Authors | Gergely Neu, Lorenzo Rosasco |
Abstract | We propose and analyze a variant of the classic Polyak-Ruppert averaging scheme, broadly used in stochastic gradient methods. Rather than a uniform average of the iterates, we consider a weighted average, with weights decaying in a geometric fashion. In the context of linear least squares regression, we show that this averaging scheme has a the same regularizing effect, and indeed is asymptotically equivalent, to ridge regression. In particular, we derive finite-sample bounds for the proposed approach that match the best known results for regularized stochastic gradient methods. |
Tasks | |
Published | 2018-02-22 |
URL | http://arxiv.org/abs/1802.08009v1 |
http://arxiv.org/pdf/1802.08009v1.pdf | |
PWC | https://paperswithcode.com/paper/iterate-averaging-as-regularization-for |
Repo | |
Framework | |
Interest Point Detection based on Adaptive Ternary Coding
Title | Interest Point Detection based on Adaptive Ternary Coding |
Authors | Zhenwei Miao, Kim-Hui Yap, Xudong Jiang |
Abstract | In this paper, an adaptive pixel ternary coding mechanism is proposed and a contrast invariant and noise resistant interest point detector is developed on the basis of this mechanism. Every pixel in a local region is adaptively encoded into one of the three statuses: bright, uncertain and dark. The blob significance of the local region is measured by the spatial distribution of the bright and dark pixels. Interest points are extracted from this blob significance measurement. By labeling the statuses of ternary bright, uncertain, and dark, the proposed detector shows more robustness to image noise and quantization errors. Moreover, the adaptive strategy for the ternary cording, which relies on two thresholds that automatically converge to the median of the local region in measurement, enables this coding to be insensitive to the image local contrast. As a result, the proposed detector is invariant to illumination changes. The state-of-the-art results are achieved on the standard datasets, and also in the face recognition application. |
Tasks | Face Recognition, Interest Point Detection, Quantization |
Published | 2018-12-31 |
URL | http://arxiv.org/abs/1901.00031v1 |
http://arxiv.org/pdf/1901.00031v1.pdf | |
PWC | https://paperswithcode.com/paper/interest-point-detection-based-on-adaptive |
Repo | |
Framework | |
Hole Filling with Multiple Reference Views in DIBR View Synthesis
Title | Hole Filling with Multiple Reference Views in DIBR View Synthesis |
Authors | Shuai Li, Ce Zhu, Ming-Ting Sun |
Abstract | Depth-image-based rendering (DIBR) oriented view synthesis has been widely employed in the current depth-based 3D video systems by synthesizing a virtual view from an arbitrary viewpoint. However, holes may appear in the synthesized view due to disocclusion, thus significantly degrading the quality. Consequently, efforts have been made on developing effective and efficient hole filling algorithms. Current hole filling techniques generally extrapolate/interpolate the hole regions with the neighboring information based on an assumption that the texture pattern in the holes is similar to that of the neighboring background information. However, in many scenarios especially of complex texture, the assumption may not hold. In other words, hole filling techniques can only provide an estimation for a hole which may not be good enough or may even be erroneous considering a wide variety of complex scene of images. In this paper, we first examine the view interpolation with multiple reference views, demonstrating that the problem of emerging holes in a target virtual view can be greatly alleviated by making good use of other neighboring complementary views in addition to its two (commonly used) most neighboring primary views. The effects of using multiple views for view extrapolation in reducing holes are also investigated in this paper. In view of the 3D Video and ongoing free-viewpoint TV standardization, we propose a new view synthesis framework which employs multiple views to synthesize output virtual views. Furthermore, a scheme of selective warping of complementary views is developed by efficiently locating a small number of useful pixels in the complementary views for hole reduction, to avoid a full warping of additional complementary views thus lowering greatly the warping complexity. |
Tasks | |
Published | 2018-02-08 |
URL | http://arxiv.org/abs/1802.03079v1 |
http://arxiv.org/pdf/1802.03079v1.pdf | |
PWC | https://paperswithcode.com/paper/hole-filling-with-multiple-reference-views-in |
Repo | |
Framework | |
On the Implicit Bias of Dropout
Title | On the Implicit Bias of Dropout |
Authors | Poorya Mianjy, Raman Arora, Rene Vidal |
Abstract | Algorithmic approaches endow deep learning systems with implicit bias that helps them generalize even in over-parametrized settings. In this paper, we focus on understanding such a bias induced in learning through dropout, a popular technique to avoid overfitting in deep learning. For single hidden-layer linear neural networks, we show that dropout tends to make the norm of incoming/outgoing weight vectors of all the hidden nodes equal. In addition, we provide a complete characterization of the optimization landscape induced by dropout. |
Tasks | |
Published | 2018-06-26 |
URL | http://arxiv.org/abs/1806.09777v1 |
http://arxiv.org/pdf/1806.09777v1.pdf | |
PWC | https://paperswithcode.com/paper/on-the-implicit-bias-of-dropout |
Repo | |
Framework | |
An Investigation of Environmental Influence on the Benefits of Adaptation Mechanisms in Evolutionary Swarm Robotics
Title | An Investigation of Environmental Influence on the Benefits of Adaptation Mechanisms in Evolutionary Swarm Robotics |
Authors | Andreas Steyven, Emma Hart, Ben Paechter |
Abstract | A robotic swarm that is required to operate for long periods in a potentially unknown environment can use both evolution and individual learning methods in order to adapt. However, the role played by the environment in influencing the effectiveness of each type of learning is not well understood. In this paper, we address this question by analysing the performance of a swarm in a range of simulated, dynamic environments where a distributed evolutionary algorithm for evolving a controller is augmented with a number of different individual learning mechanisms. The learning mechanisms themselves are defined by parameters which can be either fixed or inherited. We conduct experiments in a range of dynamic environments whose characteristics are varied so as to present different opportunities for learning. Results enable us to map environmental characteristics to the most effective learning algorithm. |
Tasks | |
Published | 2018-04-20 |
URL | http://arxiv.org/abs/1804.07663v1 |
http://arxiv.org/pdf/1804.07663v1.pdf | |
PWC | https://paperswithcode.com/paper/an-investigation-of-environmental-influence |
Repo | |
Framework | |
Sounderfeit: Cloning a Physical Model using a Conditional Adversarial Autoencoder
Title | Sounderfeit: Cloning a Physical Model using a Conditional Adversarial Autoencoder |
Authors | Stephen Sinclair |
Abstract | An adversarial autoencoder conditioned on known parameters of a physical modeling bowed string synthesizer is evaluated for use in parameter estimation and resynthesis tasks. Latent dimensions are provided to capture variance not explained by the conditional parameters. Results are compared with and without the adversarial training, and a system capable of “copying” a given parameter-signal bidirectional relationship is examined. A real-time synthesis system built on a generative, conditioned and regularized neural network is presented, allowing to construct engaging sound synthesizers based purely on recorded data. |
Tasks | |
Published | 2018-06-25 |
URL | http://arxiv.org/abs/1806.09617v1 |
http://arxiv.org/pdf/1806.09617v1.pdf | |
PWC | https://paperswithcode.com/paper/sounderfeit-cloning-a-physical-model-using-a |
Repo | |
Framework | |
Deep Laplacian Pyramid Network for Text Images Super-Resolution
Title | Deep Laplacian Pyramid Network for Text Images Super-Resolution |
Authors | Hanh T. M. Tran, Tien Ho-Phuoc |
Abstract | Convolutional neural networks have recently demonstrated interesting results for single image super-resolution. However, these networks were trained to deal with super-resolution problem on natural images. In this paper, we adapt a deep network, which was proposed for natural images superresolution, to single text image super-resolution. To evaluate the network, we present our database for single text image super-resolution. Moreover, we propose to combine Gradient Difference Loss (GDL) with L1/L2 loss to enhance edges in super-resolution image. Quantitative and qualitative evaluations on our dataset show that adding the GDL improves the super-resolution results. |
Tasks | Image Super-Resolution, Super-Resolution |
Published | 2018-11-26 |
URL | http://arxiv.org/abs/1811.10449v1 |
http://arxiv.org/pdf/1811.10449v1.pdf | |
PWC | https://paperswithcode.com/paper/deep-laplacian-pyramid-network-for-text |
Repo | |
Framework | |
High-Dimensional Robust Mean Estimation in Nearly-Linear Time
Title | High-Dimensional Robust Mean Estimation in Nearly-Linear Time |
Authors | Yu Cheng, Ilias Diakonikolas, Rong Ge |
Abstract | We study the fundamental problem of high-dimensional mean estimation in a robust model where a constant fraction of the samples are adversarially corrupted. Recent work gave the first polynomial time algorithms for this problem with dimension-independent error guarantees for several families of structured distributions. In this work, we give the first nearly-linear time algorithms for high-dimensional robust mean estimation. Specifically, we focus on distributions with (i) known covariance and sub-gaussian tails, and (ii) unknown bounded covariance. Given $N$ samples on $\mathbb{R}^d$, an $\epsilon$-fraction of which may be arbitrarily corrupted, our algorithms run in time $\tilde{O}(Nd) / \mathrm{poly}(\epsilon)$ and approximate the true mean within the information-theoretically optimal error, up to constant factors. Previous robust algorithms with comparable error guarantees have running times $\tilde{\Omega}(N d^2)$, for $\epsilon = \Omega(1)$. Our algorithms rely on a natural family of SDPs parameterized by our current guess $\nu$ for the unknown mean $\mu^\star$. We give a win-win analysis establishing the following: either a near-optimal solution to the primal SDP yields a good candidate for $\mu^\star$ – independent of our current guess $\nu$ – or the dual SDP yields a new guess $\nu'$ whose distance from $\mu^\star$ is smaller by a constant factor. We exploit the special structure of the corresponding SDPs to show that they are approximately solvable in nearly-linear time. Our approach is quite general, and we believe it can also be applied to obtain nearly-linear time algorithms for other high-dimensional robust learning problems. |
Tasks | |
Published | 2018-11-23 |
URL | http://arxiv.org/abs/1811.09380v1 |
http://arxiv.org/pdf/1811.09380v1.pdf | |
PWC | https://paperswithcode.com/paper/high-dimensional-robust-mean-estimation-in |
Repo | |
Framework | |
Future Segmentation Using 3D Structure
Title | Future Segmentation Using 3D Structure |
Authors | Suhani Vora, Reza Mahjourian, Soeren Pirk, Anelia Angelova |
Abstract | Predicting the future to anticipate the outcome of events and actions is a critical attribute of autonomous agents; particularly for agents which must rely heavily on real time visual data for decision making. Working towards this capability, we address the task of predicting future frame segmentation from a stream of monocular video by leveraging the 3D structure of the scene. Our framework is based on learnable sub-modules capable of predicting pixel-wise scene semantic labels, depth, and camera ego-motion of adjacent frames. We further propose a recurrent neural network based model capable of predicting future ego-motion trajectory as a function of a series of past ego-motion steps. Ultimately, we observe that leveraging 3D structure in the model facilitates successful prediction, achieving state of the art accuracy in future semantic segmentation. |
Tasks | Decision Making, Semantic Segmentation |
Published | 2018-11-28 |
URL | http://arxiv.org/abs/1811.11358v1 |
http://arxiv.org/pdf/1811.11358v1.pdf | |
PWC | https://paperswithcode.com/paper/future-segmentation-using-3d-structure |
Repo | |
Framework | |
JuncNet: A Deep Neural Network for Road Junction Disambiguation for Autonomous Vehicles
Title | JuncNet: A Deep Neural Network for Road Junction Disambiguation for Autonomous Vehicles |
Authors | Saumya Kumaar, Navaneethkrishnan B, Sumedh Mannar, S N Omkar |
Abstract | With a great amount of research going on in the field of autonomous vehicles or self-driving cars, there has been considerable progress in road detection and tracking algorithms. Most of these algorithms use GPS to handle road junctions and its subsequent decisions. However, there are places in the urban environment where it becomes difficult to get GPS fixes which render the junction decision handling erroneous or possibly risky. Vision-based junction detection, however, does not have such problems. This paper proposes a novel deep convolutional neural network architecture for disambiguation of junctions from roads with a high degree of accuracy. This network is benchmarked against other well known classifying network architectures like AlexNet and VGGnet. Further, we discuss a potential road navigation methodology which uses the proposed network model. We conclude by performing an experimental validation of the trained network and the navigational method on the roads of the Indian Institute of Science (IISc). |
Tasks | Autonomous Vehicles, Self-Driving Cars |
Published | 2018-08-31 |
URL | http://arxiv.org/abs/1809.01011v1 |
http://arxiv.org/pdf/1809.01011v1.pdf | |
PWC | https://paperswithcode.com/paper/juncnet-a-deep-neural-network-for-road |
Repo | |
Framework | |
Predicting Musical Sophistication from Music Listening Behaviors: A Preliminary Study
Title | Predicting Musical Sophistication from Music Listening Behaviors: A Preliminary Study |
Authors | Bruce Ferwerda, Mark Graus |
Abstract | Psychological models are increasingly being used to explain online behavioral traces. Aside from the commonly used personality traits as a general user model, more domain dependent models are gaining attention. The use of domain dependent psychological models allows for more fine-grained identification of behaviors and provide a deeper understanding behind the occurrence of those behaviors. Understanding behaviors based on psychological models can provide an advantage over data-driven approaches. For example, relying on psychological models allow for ways to personalize when data is scarce. In this preliminary work we look at the relation between users’ musical sophistication and their online music listening behaviors and to what extent we can successfully predict musical sophistication. An analysis of data from a study with 61 participants shows that listening behaviors can successfully be used to infer users’ musical sophistication. |
Tasks | |
Published | 2018-08-22 |
URL | http://arxiv.org/abs/1808.07314v1 |
http://arxiv.org/pdf/1808.07314v1.pdf | |
PWC | https://paperswithcode.com/paper/predicting-musical-sophistication-from-music |
Repo | |
Framework | |
Self-learning Local Supervision Encoding Framework to Constrict and Disperse Feature Distribution for Clustering
Title | Self-learning Local Supervision Encoding Framework to Constrict and Disperse Feature Distribution for Clustering |
Authors | Jielei Chu, Tianrui Li, Hongjun Wang, Jing Liu, Meng Hua |
Abstract | To obtain suitable feature distribution is a difficult task in machine learning, especially for unsupervised learning. In this paper, we propose a novel self-learning local supervision encoding framework based on RBMs, in which the self-learning local supervisions from visible layer are integrated into the contrastive divergence (CD) learning of RBMs to constrict and disperse the distribution of the hidden layer features for clustering tasks. In the framework, we use sigmoid transformation to obtain hidden layer and reconstructed hidden layer features from visible layer and reconstructed visible layer units during sampling procedure. The self-learning local supervisions contain local credible clusters which stem from different unsupervised learning and unanimous voting strategy. They are fused into hidden layer features and reconstructed hidden layer features. For the same local clusters, the hidden features and reconstructed hidden layer features of the framework tend to constrict together. Furthermore, the hidden layer features of different local clusters tend to disperse in the encoding process. Under such framework, we present two instantiation models with the reconstruction of two different visible layers. One is self-learning local supervision GRBM (slsGRBM) model with Gaussian linear visible units and binary hidden units using linear transformation for visible layer reconstruction. The other is self-learning local supervision RBM (slsRBM) model with binary visible and hidden units using sigmoid transformation for visible layer reconstruction. |
Tasks | |
Published | 2018-12-05 |
URL | http://arxiv.org/abs/1812.01967v1 |
http://arxiv.org/pdf/1812.01967v1.pdf | |
PWC | https://paperswithcode.com/paper/self-learning-local-supervision-encoding |
Repo | |
Framework | |
False Discovery Rate Control via Debiased Lasso
Title | False Discovery Rate Control via Debiased Lasso |
Authors | Adel Javanmard, Hamid Javadi |
Abstract | We consider the problem of variable selection in high-dimensional statistical models where the goal is to report a set of variables, out of many predictors $X_1, \dotsc, X_p$, that are relevant to a response of interest. For linear high-dimensional model, where the number of parameters exceeds the number of samples $(p>n)$, we propose a procedure for variables selection and prove that it controls the “directional” false discovery rate (FDR) below a pre-assigned significance level $q\in [0,1]$. We further analyze the statistical power of our framework and show that for designs with subgaussian rows and a common precision matrix $\Omega\in\mathbb{R}^{p\times p}$, if the minimum nonzero parameter $\theta_{\min}$ satisfies $$\sqrt{n} \theta_{\min} - \sigma \sqrt{2(\max_{i\in [p]}\Omega_{ii})\log\left(\frac{2p}{qs_0}\right)} \to \infty,,$$ then this procedure achieves asymptotic power one. Our framework is built upon the debiasing approach and assumes the standard condition $s_0 = o(\sqrt{n}/(\log p)^2)$, where $s_0$ indicates the number of true positives among the $p$ features. Notably, this framework achieves exact directional FDR control without any assumption on the amplitude of unknown regression parameters, and does not require any knowledge of the distribution of covariates or the noise level. We test our method in synthetic and real data experiments to assess its performance and to corroborate our theoretical results. |
Tasks | |
Published | 2018-03-12 |
URL | http://arxiv.org/abs/1803.04464v2 |
http://arxiv.org/pdf/1803.04464v2.pdf | |
PWC | https://paperswithcode.com/paper/false-discovery-rate-control-via-debiased |
Repo | |
Framework | |
Subpixel-Precise Tracking of Rigid Objects in Real-time
Title | Subpixel-Precise Tracking of Rigid Objects in Real-time |
Authors | Tobias Böttger, Markus Ulrich, Carsten Steger |
Abstract | We present a novel object tracking scheme that can track rigid objects in real time. The approach uses subpixel-precise image edges to track objects with high accuracy. It can determine the object position, scale, and rotation with subpixel-precision at around 80fps. The tracker returns a reliable score for each frame and is capable of self diagnosing a tracking failure. Furthermore, the choice of the similarity measure makes the approach inherently robust against occlusion, clutter, and nonlinear illumination changes. We evaluate the method on sequences from rigid objects from the OTB-2015 and VOT2016 dataset and discuss its performance. The evaluation shows that the tracker is more accurate than state-of-the-art real-time trackers while being equally robust. |
Tasks | Object Tracking |
Published | 2018-07-05 |
URL | http://arxiv.org/abs/1807.01952v1 |
http://arxiv.org/pdf/1807.01952v1.pdf | |
PWC | https://paperswithcode.com/paper/subpixel-precise-tracking-of-rigid-objects-in |
Repo | |
Framework | |
TransRev: Modeling Reviews as Translations from Users to Items
Title | TransRev: Modeling Reviews as Translations from Users to Items |
Authors | Alberto Garcia-Duran, Roberto Gonzalez, Daniel Onoro-Rubio, Mathias Niepert, Hui Li |
Abstract | The text of a review expresses the sentiment a customer has towards a particular product. This is exploited in sentiment analysis where machine learning models are used to predict the review score from the text of the review. Furthermore, the products costumers have purchased in the past are indicative of the products they will purchase in the future. This is what recommender systems exploit by learning models from purchase information to predict the items a customer might be interested in. We propose TransRev, an approach to the product recommendation problem that integrates ideas from recommender systems, sentiment analysis, and multi-relational learning into a joint learning objective. TransRev learns vector representations for users, items, and reviews. The embedding of a review is learned such that (a) it performs well as input feature of a regression model for sentiment prediction; and (b) it always translates the reviewer embedding to the embedding of the reviewed items. This allows TransRev to approximate a review embedding at test time as the difference of the embedding of each item and the user embedding. The approximated review embedding is then used with the regression model to predict the review score for each item. TransRev outperforms state of the art recommender systems on a large number of benchmark data sets. Moreover, it is able to retrieve, for each user and item, the review text from the training set whose embedding is most similar to the approximated review embedding. |
Tasks | Product Recommendation, Recommendation Systems, Relational Reasoning, Sentiment Analysis |
Published | 2018-01-30 |
URL | http://arxiv.org/abs/1801.10095v2 |
http://arxiv.org/pdf/1801.10095v2.pdf | |
PWC | https://paperswithcode.com/paper/transrev-modeling-reviews-as-translations |
Repo | |
Framework | |