Paper Group ANR 1432
Recovering Faces from Portraits with Auxiliary Facial Attributes. Cost-Sensitive Feature Selection by Optimizing F-Measures. A Test for Shared Patterns in Cross-modal Brain Activation Analysis. Evolving Gaussian Process kernels from elementary mathematical expressions. Current Trends in the Use of Eye Tracking in Mathematics Education Research: A P …
Recovering Faces from Portraits with Auxiliary Facial Attributes
| Title | Recovering Faces from Portraits with Auxiliary Facial Attributes |
| Authors | Fatemeh Shiri, Xin Yu, Fatih Porikli, Richard Hartley, Piotr Koniusz |
| Abstract | Recovering a photorealistic face from an artistic portrait is a challenging task since crucial facial details are often distorted or completely lost in artistic compositions. To handle this loss, we propose an Attribute-guided Face Recovery from Portraits (AFRP) that utilizes a Face Recovery Network (FRN) and a Discriminative Network (DN). FRN consists of an autoencoder with residual block-embedded skip-connections and incorporates facial attribute vectors into the feature maps of input portraits at the bottleneck of the autoencoder. DN has multiple convolutional and fully-connected layers, and its role is to enforce FRN to generate authentic face images with corresponding facial attributes dictated by the input attribute vectors. %Leveraging on the spatial transformer networks, FRN automatically compensates for misalignments of portraits. % and generates aligned face images. For the preservation of identities, we impose the recovered and ground-truth faces to share similar visual features. Specifically, DN determines whether the recovered image looks like a real face and checks if the facial attributes extracted from the recovered image are consistent with given attributes. %Our method can recover high-quality photorealistic faces from unaligned portraits while preserving the identity of the face images as well as it can reconstruct a photorealistic face image with a desired set of attributes. Our method can recover photorealistic identity-preserving faces with desired attributes from unseen stylized portraits, artistic paintings, and hand-drawn sketches. On large-scale synthesized and sketch datasets, we demonstrate that our face recovery method achieves state-of-the-art results. |
| Tasks | |
| Published | 2019-04-07 |
| URL | http://arxiv.org/abs/1904.03612v1 |
| http://arxiv.org/pdf/1904.03612v1.pdf | |
| PWC | https://paperswithcode.com/paper/recovering-faces-from-portraits-with |
| Repo | |
| Framework | |
Cost-Sensitive Feature Selection by Optimizing F-Measures
| Title | Cost-Sensitive Feature Selection by Optimizing F-Measures |
| Authors | Meng Liu, Chang Xu, Yong Luo, Chao Xu, Yonggang Wen, Dacheng Tao |
| Abstract | Feature selection is beneficial for improving the performance of general machine learning tasks by extracting an informative subset from the high-dimensional features. Conventional feature selection methods usually ignore the class imbalance problem, thus the selected features will be biased towards the majority class. Considering that F-measure is a more reasonable performance measure than accuracy for imbalanced data, this paper presents an effective feature selection algorithm that explores the class imbalance issue by optimizing F-measures. Since F-measure optimization can be decomposed into a series of cost-sensitive classification problems, we investigate the cost-sensitive feature selection by generating and assigning different costs to each class with rigorous theory guidance. After solving a series of cost-sensitive feature selection problems, features corresponding to the best F-measure will be selected. In this way, the selected features will fully represent the properties of all classes. Experimental results on popular benchmarks and challenging real-world data sets demonstrate the significance of cost-sensitive feature selection for the imbalanced data setting and validate the effectiveness of the proposed method. |
| Tasks | Feature Selection |
| Published | 2019-04-04 |
| URL | http://arxiv.org/abs/1904.02301v1 |
| http://arxiv.org/pdf/1904.02301v1.pdf | |
| PWC | https://paperswithcode.com/paper/cost-sensitive-feature-selection-by |
| Repo | |
| Framework | |
A Test for Shared Patterns in Cross-modal Brain Activation Analysis
| Title | A Test for Shared Patterns in Cross-modal Brain Activation Analysis |
| Authors | Elena Kalinina, Fabian Pedregosa, Vittorio Iacovella, Emanuele Olivetti, Paolo Avesani |
| Abstract | Determining the extent to which different cognitive modalities (understood here as the set of cognitive processes underlying the elaboration of a stimulus by the brain) rely on overlapping neural representations is a fundamental issue in cognitive neuroscience. In the last decade, the identification of shared activity patterns has been mostly framed as a supervised learning problem. For instance, a classifier is trained to discriminate categories (e.g. faces vs. houses) in modality I (e.g. perception) and tested on the same categories in modality II (e.g. imagery). This type of analysis is often referred to as cross-modal decoding. In this paper we take a different approach and instead formulate the problem of assessing shared patterns across modalities within the framework of statistical hypothesis testing. We propose both an appropriate test statistic and a scheme based on permutation testing to compute the significance of this test while making only minimal distributional assumption. We denote this test cross-modal permutation test (CMPT). We also provide empirical evidence on synthetic datasets that our approach has greater statistical power than the cross-modal decoding method while maintaining low Type I errors (rejecting a true null hypothesis). We compare both approaches on an fMRI dataset with three different cognitive modalities (perception, imagery, visual search). Finally, we show how CMPT can be combined with Searchlight analysis to explore spatial distribution of shared activity patterns. |
| Tasks | |
| Published | 2019-10-08 |
| URL | https://arxiv.org/abs/1910.05271v1 |
| https://arxiv.org/pdf/1910.05271v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-test-for-shared-patterns-in-cross-modal |
| Repo | |
| Framework | |
Evolving Gaussian Process kernels from elementary mathematical expressions
| Title | Evolving Gaussian Process kernels from elementary mathematical expressions |
| Authors | Ibai Roman, Roberto Santana, Alexander Mendiburu, Jose A. Lozano |
| Abstract | Choosing the most adequate kernel is crucial in many Machine Learning applications. Gaussian Process is a state-of-the-art technique for regression and classification that heavily relies on a kernel function. However, in the Gaussian Process literature, kernels have usually been either ad hoc designed, selected from a predefined set, or searched for in a space of compositions of kernels which have been defined a priori. In this paper, we propose a Genetic-Programming algorithm that represents a kernel function as a tree of elementary mathematical expressions. By means of this representation, a wider set of kernels can be modeled, where potentially better solutions can be found, although new challenges also arise. The proposed algorithm is able to overcome these difficulties and find kernels that accurately model the characteristics of the data. This method has been tested in several real-world time-series extrapolation problems, improving the state-of-the-art results while reducing the complexity of the kernels. |
| Tasks | Time Series |
| Published | 2019-10-11 |
| URL | https://arxiv.org/abs/1910.05173v2 |
| https://arxiv.org/pdf/1910.05173v2.pdf | |
| PWC | https://paperswithcode.com/paper/evolving-gaussian-process-kernels-from |
| Repo | |
| Framework | |
Current Trends in the Use of Eye Tracking in Mathematics Education Research: A PME Survey
| Title | Current Trends in the Use of Eye Tracking in Mathematics Education Research: A PME Survey |
| Authors | Achim J. Lilienthal, Maike Schindler |
| Abstract | Eye tracking (ET) is a research method that receives growing interest in mathematics education research (MER). This paper aims to give a literature overview, specifically focusing on the evolution of interest in this technology, ET equipment, and analysis methods used in mathematics education. To capture the current state, we focus on papers published in the proceedings of PME, one of the primary conferences dedicated to MER, of the last ten years. We identify trends in interest, methodology, and methods of analysis that are used in the community, and discuss possible future developments. |
| Tasks | Eye Tracking |
| Published | 2019-04-26 |
| URL | https://arxiv.org/abs/1904.12581v2 |
| https://arxiv.org/pdf/1904.12581v2.pdf | |
| PWC | https://paperswithcode.com/paper/current-trends-in-eye-tracking-research-in |
| Repo | |
| Framework | |
3D Human Pose Estimation from Deep Multi-View 2D Pose
| Title | 3D Human Pose Estimation from Deep Multi-View 2D Pose |
| Authors | Steven Schwarcz, Thomas Pollard |
| Abstract | Human pose estimation - the process of recognizing a human’s limb positions and orientations in a video - has many important applications including surveillance, diagnosis of movement disorders, and computer animation. While deep learning has lead to great advances in 2D and 3D pose estimation from single video sources, the problem of estimating 3D human pose from multiple video sensors with overlapping fields of view has received less attention. When the application allows use of multiple cameras, 3D human pose estimates may be greatly improved through fusion of multi-view pose estimates and observation of limbs that are fully or partially occluded in some views. Past approaches to multi-view 3D pose estimation have used probabilistic graphical models to reason over constraints, including per-image pose estimates, temporal smoothness, and limb length. In this paper, we present a pipeline for multi-view 3D pose estimation of multiple individuals which combines a state-of-art 2D pose detector with a factor graph of 3D limb constraints optimized with belief propagation. We evaluate our results on the TUM-Campus and Shelf datasets for multi-person 3D pose estimation and show that our system significantly out-performs the previous state-of-the-art with a simpler model of limb dependency. |
| Tasks | 3D Human Pose Estimation, 3D Pose Estimation, Pose Estimation |
| Published | 2019-02-07 |
| URL | http://arxiv.org/abs/1902.02841v1 |
| http://arxiv.org/pdf/1902.02841v1.pdf | |
| PWC | https://paperswithcode.com/paper/3d-human-pose-estimation-from-deep-multi-view |
| Repo | |
| Framework | |
Controlling Utterance Length in NMT-based Word Segmentation with Attention
| Title | Controlling Utterance Length in NMT-based Word Segmentation with Attention |
| Authors | Pierre Godard, Laurent Besacier, Francois Yvon |
| Abstract | One of the basic tasks of computational language documentation (CLD) is to identify word boundaries in an unsegmented phonemic stream. While several unsupervised monolingual word segmentation algorithms exist in the literature, they are challenged in real-world CLD settings by the small amount of available data. A possible remedy is to take advantage of glosses or translation in a foreign, well-resourced, language, which often exist for such data. In this paper, we explore and compare ways to exploit neural machine translation models to perform unsupervised boundary detection with bilingual information, notably introducing a new loss function for jointly learning alignment and segmentation. We experiment with an actual under-resourced language, Mboshi, and show that these techniques can effectively control the output segmentation length. |
| Tasks | Boundary Detection, Machine Translation |
| Published | 2019-10-18 |
| URL | https://arxiv.org/abs/1910.08418v1 |
| https://arxiv.org/pdf/1910.08418v1.pdf | |
| PWC | https://paperswithcode.com/paper/controlling-utterance-length-in-nmt-based |
| Repo | |
| Framework | |
Enhancing Certifiable Robustness via a Deep Model Ensemble
| Title | Enhancing Certifiable Robustness via a Deep Model Ensemble |
| Authors | Huan Zhang, Minhao Cheng, Cho-Jui Hsieh |
| Abstract | We propose an algorithm to enhance certified robustness of a deep model ensemble by optimally weighting each base model. Unlike previous works on using ensembles to empirically improve robustness, our algorithm is based on optimizing a guaranteed robustness certificate of neural networks. Our proposed ensemble framework with certified robustness, RobBoost, formulates the optimal model selection and weighting task as an optimization problem on a lower bound of classification margin, which can be efficiently solved using coordinate descent. Experiments show that our algorithm can form a more robust ensemble than naively averaging all available models using robustly trained MNIST or CIFAR base models. Additionally, our ensemble typically has better accuracy on clean (unperturbed) data. RobBoost allows us to further improve certified robustness and clean accuracy by creating an ensemble of already certified models. |
| Tasks | Model Selection |
| Published | 2019-10-31 |
| URL | https://arxiv.org/abs/1910.14655v1 |
| https://arxiv.org/pdf/1910.14655v1.pdf | |
| PWC | https://paperswithcode.com/paper/enhancing-certifiable-robustness-via-a-deep |
| Repo | |
| Framework | |
Higher-Order Accelerated Methods for Faster Non-Smooth Optimization
| Title | Higher-Order Accelerated Methods for Faster Non-Smooth Optimization |
| Authors | Brian Bullins, Richard Peng |
| Abstract | We provide improved convergence rates for various \emph{non-smooth} optimization problems via higher-order accelerated methods. In the case of $\ell_\infty$ regression, we achieves an $O(\epsilon^{-4/5})$ iteration complexity, breaking the $O(\epsilon^{-1})$ barrier so far present for previous methods. We arrive at a similar rate for the problem of $\ell_1$-SVM, going beyond what is attainable by first-order methods with prox-oracle access for non-smooth non-strongly convex problems. We further show how to achieve even faster rates by introducing higher-order regularization. Our results rely on recent advances in near-optimal accelerated methods for higher-order smooth convex optimization. In particular, we extend Nesterov’s smoothing technique to show that the standard softmax approximation is not only smooth in the usual sense, but also \emph{higher-order} smooth. With this observation in hand, we provide the first example of higher-order acceleration techniques yielding faster rates for \emph{non-smooth} optimization, to the best of our knowledge. |
| Tasks | |
| Published | 2019-06-04 |
| URL | https://arxiv.org/abs/1906.01621v1 |
| https://arxiv.org/pdf/1906.01621v1.pdf | |
| PWC | https://paperswithcode.com/paper/higher-order-accelerated-methods-for-faster |
| Repo | |
| Framework | |
Learning a Neural Solver for Multiple Object Tracking
| Title | Learning a Neural Solver for Multiple Object Tracking |
| Authors | Guillem Brasó, Laura Leal-Taixé |
| Abstract | Graphs offer a natural way to formulate Multiple Object Tracking (MOT) within the tracking-by-detection paradigm. However, they also introduce a major challenge for learning methods, as defining a model that can operate on such a structured domain is not trivial. As a consequence, most learning-based work has been devoted to learning better features for MOT, and then using these with well-established optimization frameworks. In this work, we exploit the classical network flow formulation of MOT to define a fully differentiable framework based on Message Passing Networks (MPNs). By operating directly on the graph domain, our method can reason globally over an entire set of detections and predict final solutions. Hence, we show that learning in MOT does not need to be restricted to feature extraction, but it can also be applied to the data association step. We show a significant improvement in both MOTA and IDF1 on three publicly available benchmarks. |
| Tasks | Multiple Object Tracking, Object Tracking |
| Published | 2019-12-16 |
| URL | https://arxiv.org/abs/1912.07515v1 |
| https://arxiv.org/pdf/1912.07515v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-a-neural-solver-for-multiple-object |
| Repo | |
| Framework | |
Reducing Selection Bias in Counterfactual Reasoning for Individual Treatment Effects Estimation
| Title | Reducing Selection Bias in Counterfactual Reasoning for Individual Treatment Effects Estimation |
| Authors | Zichen Zhang, Qingfeng Lan, Lei Ding, Yue Wang, Negar Hassanpour, Russell Greiner |
| Abstract | Counterfactual reasoning is an important paradigm applicable in many fields, such as healthcare, economics, and education. In this work, we propose a novel method to address the issue of \textit{selection bias}. We learn two groups of latent random variables, where one group corresponds to variables that only cause selection bias, and the other group is relevant for outcome prediction. They are learned by an auto-encoder where an additional regularized loss based on Pearson Correlation Coefficient (PCC) encourages the de-correlation between the two groups of random variables. This allows for explicitly alleviating selection bias by only keeping the latent variables that are relevant for estimating individual treatment effects. Experimental results on a synthetic toy dataset and a benchmark dataset show that our algorithm is able to achieve state-of-the-art performance and improve the result of its counterpart that does not explicitly model the selection bias. |
| Tasks | |
| Published | 2019-12-19 |
| URL | https://arxiv.org/abs/1912.09040v1 |
| https://arxiv.org/pdf/1912.09040v1.pdf | |
| PWC | https://paperswithcode.com/paper/reducing-selection-bias-in-counterfactual |
| Repo | |
| Framework | |
Achieving Fairness in Stochastic Multi-armed Bandit Problem
| Title | Achieving Fairness in Stochastic Multi-armed Bandit Problem |
| Authors | Vishakha Patil, Ganesh Ghalme, Vineet Nair, Y. Narahari |
| Abstract | We study an interesting variant of the stochastic multi-armed bandit problem, called the Fair-SMAB problem, where each arm is required to be pulled for at least a given fraction of the total available rounds. We investigate the interplay between learning and fairness in terms of a pre-specified vector denoting the fractions of guaranteed pulls. We define a fairness-aware regret, called r-Regret, that takes into account the above fairness constraints and naturally extends the conventional notion of regret. Our primary contribution is characterizing a class of Fair-SMAB algorithms by two parameters: the unfairness tolerance and learning algorithm used as a black-box. We provide a fairness guarantee for this class that holds uniformly over time irrespective of the choice of the learning algorithm. In particular, when the learning algorithm is UCB1, we show that our algorithm achieves O(log(T)) r-Regret. Finally, we evaluate the cost of fairness in terms of the conventional notion of regret. |
| Tasks | Multi-Armed Bandits |
| Published | 2019-05-27 |
| URL | https://arxiv.org/abs/1905.11260v3 |
| https://arxiv.org/pdf/1905.11260v3.pdf | |
| PWC | https://paperswithcode.com/paper/stochastic-multi-armed-bandits-with-arm |
| Repo | |
| Framework | |
Enforcing Perceptual Consistency on Generative Adversarial Networks by Using the Normalised Laplacian Pyramid Distance
| Title | Enforcing Perceptual Consistency on Generative Adversarial Networks by Using the Normalised Laplacian Pyramid Distance |
| Authors | Alexander Hepburn, Valero Laparra, Ryan McConville, Raul Santos-Rodriguez |
| Abstract | In recent years there has been a growing interest in image generation through deep learning. While an important part of the evaluation of the generated images usually involves visual inspection, the inclusion of human perception as a factor in the training process is often overlooked. In this paper we propose an alternative perceptual regulariser for image-to-image translation using conditional generative adversarial networks (cGANs). To do so automatically (avoiding visual inspection), we use the Normalised Laplacian Pyramid Distance (NLPD) to measure the perceptual similarity between the generated image and the original image. The NLPD is based on the principle of normalising the value of coefficients with respect to a local estimate of mean energy at different scales and has already been successfully tested in different experiments involving human perception. We compare this regulariser with the originally proposed L1 distance and note that when using NLPD the generated images contain more realistic values for both local and global contrast. We found that using NLPD as a regulariser improves image segmentation accuracy on generated images as well as improving two no-reference image quality metrics. |
| Tasks | Image Generation, Image-to-Image Translation, Semantic Segmentation |
| Published | 2019-08-09 |
| URL | https://arxiv.org/abs/1908.04347v1 |
| https://arxiv.org/pdf/1908.04347v1.pdf | |
| PWC | https://paperswithcode.com/paper/enforcing-perceptual-consistency-on |
| Repo | |
| Framework | |
Fine-Tuning Models Comparisons on Garbage Classification for Recyclability
| Title | Fine-Tuning Models Comparisons on Garbage Classification for Recyclability |
| Authors | Umut Ozkaya, Levent Seyfi |
| Abstract | In this study, it is aimed to develop a deep learning application which detects types of garbage into trash in order to provide recyclability with vision system. Training and testing will be performed with image data consisting of several classes on different garbage types. The data set used during training and testing will be generated from original frames taken from garbage images. The data set used for deep learning structures has a total of 2527 images with 6 different classes. Half of these images in the data set were used for training process and remaining part were used for testing procedure. Also, transfer learning was used to obtain shorter training and test procedures with and higher accuracy. As fine-tuned models, Alexnet, VGG16, Googlenet and Resnet structures were carried. In order to test performance of classifiers, two different classifiers are used as Softmax and Support Vector Machines. 6 different type of trash images were correctly classified the highest accuracy with GoogleNet+SVM as 97.86%. |
| Tasks | Transfer Learning |
| Published | 2019-08-07 |
| URL | https://arxiv.org/abs/1908.04393v1 |
| https://arxiv.org/pdf/1908.04393v1.pdf | |
| PWC | https://paperswithcode.com/paper/fine-tuning-models-comparisons-on-garbage |
| Repo | |
| Framework | |
Best Practices for Convolutional Neural Networks Applied to Object Recognition in Images
| Title | Best Practices for Convolutional Neural Networks Applied to Object Recognition in Images |
| Authors | Anderson de Andrade |
| Abstract | This research project studies the impact of convolutional neural networks (CNN) in image classification tasks. We explore different architectures and training configurations with the use of ReLUs, Nesterov’s accelerated gradient, dropout and maxout networks. We work with the CIFAR-10 dataset as part of a Kaggle competition to identify objects in images. Initial results show that CNNs outperform our baseline by acting as invariant feature detectors. Comparisons between different preprocessing procedures show better results for global contrast normalization and ZCA whitening. ReLUs are much faster than tanh units and outperform sigmoids. We provide extensive details about our training hyperparameters, providing intuition for their selection that could help enhance learning in similar situations. We design 4 models of convolutional neural networks that explore characteristics such as depth, number of feature maps, size and overlap of kernels, pooling regions, and different subsampling techniques. Results favor models of moderate depth that use an extensive number of parameters in both convolutional and dense layers. Maxout networks are able to outperform rectifiers on some models but introduce too much noise as the complexity of the fully-connected layers increases. The final discussion explains our results and provides additional techniques that could improve performance. |
| Tasks | Image Classification, Object Recognition |
| Published | 2019-10-29 |
| URL | https://arxiv.org/abs/1910.13029v1 |
| https://arxiv.org/pdf/1910.13029v1.pdf | |
| PWC | https://paperswithcode.com/paper/best-practices-for-convolutional-neural |
| Repo | |
| Framework | |
