Paper Group ANR 465
A Survey on Periocular Biometrics Research. Independent Component Analysis via Energy-based and Kernel-based Mutual Dependence Measures. Contextual Audio-Visual Switching For Speech Enhancement in Real-World Environments. Expression Recognition Using the Periocular Region: A Feasibility Study. Unsupervised Learning of Shape Concepts - From Real-Wor …
A Survey on Periocular Biometrics Research
| Title | A Survey on Periocular Biometrics Research |
| Authors | Fernando Alonso-Fernandez, Josef Bigun |
| Abstract | Periocular refers to the facial region in the vicinity of the eye, including eyelids, lashes and eyebrows. While face and irises have been extensively studied, the periocular region has emerged as a promising trait for unconstrained biometrics, following demands for increased robustness of face or iris systems. With a surprisingly high discrimination ability, this region can be easily obtained with existing setups for face and iris, and the requirement of user cooperation can be relaxed, thus facilitating the interaction with biometric systems. It is also available over a wide range of distances even when the iris texture cannot be reliably obtained (low resolution) or under partial face occlusion (close distances). Here, we review the state of the art in periocular biometrics research. A number of aspects are described, including: i) existing databases, ii) algorithms for periocular detection and/or segmentation, iii) features employed for recognition, iv) identification of the most discriminative regions of the periocular area, v) comparison with iris and face modalities, vi) soft-biometrics (gender/ethnicity classification), and vii) impact of gender transformation and plastic surgery on the recognition accuracy. This work is expected to provide an insight of the most relevant issues in periocular biometrics, giving a comprehensive coverage of the existing literature and current state of the art. |
| Tasks | |
| Published | 2018-10-08 |
| URL | http://arxiv.org/abs/1810.03360v1 |
| http://arxiv.org/pdf/1810.03360v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-survey-on-periocular-biometrics-research |
| Repo | |
| Framework | |
Independent Component Analysis via Energy-based and Kernel-based Mutual Dependence Measures
| Title | Independent Component Analysis via Energy-based and Kernel-based Mutual Dependence Measures |
| Authors | Ze Jin, David S. Matteson |
| Abstract | We apply both distance-based (Jin and Matteson, 2017) and kernel-based (Pfister et al., 2016) mutual dependence measures to independent component analysis (ICA), and generalize dCovICA (Matteson and Tsay, 2017) to MDMICA, minimizing empirical dependence measures as an objective function in both deflation and parallel manners. Solving this minimization problem, we introduce Latin hypercube sampling (LHS) (McKay et al., 2000), and a global optimization method, Bayesian optimization (BO) (Mockus, 1994) to improve the initialization of the Newton-type local optimization method. The performance of MDMICA is evaluated in various simulation studies and an image data example. When the ICA model is correct, MDMICA achieves competitive results compared to existing approaches. When the ICA model is misspecified, the estimated independent components are less mutually dependent than the observed components using MDMICA, while they are prone to be even more mutually dependent than the observed components using other approaches. |
| Tasks | |
| Published | 2018-05-17 |
| URL | http://arxiv.org/abs/1805.06639v1 |
| http://arxiv.org/pdf/1805.06639v1.pdf | |
| PWC | https://paperswithcode.com/paper/independent-component-analysis-via-energy |
| Repo | |
| Framework | |
Contextual Audio-Visual Switching For Speech Enhancement in Real-World Environments
| Title | Contextual Audio-Visual Switching For Speech Enhancement in Real-World Environments |
| Authors | Ahsan Adeel, Mandar Gogate, Amir Hussain |
| Abstract | Human speech processing is inherently multimodal, where visual cues (lip movements) help to better understand the speech in noise. Lip-reading driven speech enhancement significantly outperforms benchmark audio-only approaches at low signal-to-noise ratios (SNRs). However, at high SNRs or low levels of background noise, visual cues become fairly less effective for speech enhancement. Therefore, a more optimal, context-aware audio-visual (AV) system is required, that contextually utilises both visual and noisy audio features and effectively accounts for different noisy conditions. In this paper, we introduce a novel contextual AV switching component that contextually exploits AV cues with respect to different operating conditions to estimate clean audio, without requiring any SNR estimation. The switching module switches between visual-only (V-only), audio-only (A-only), and both AV cues at low, high and moderate SNR levels, respectively. The contextual AV switching component is developed by integrating a convolutional neural network and long-short-term memory network. For testing, the estimated clean audio features are utilised by the developed novel enhanced visually derived Wiener filter for clean audio power spectrum estimation. The contextual AV speech enhancement method is evaluated under real-world scenarios using benchmark Grid and ChiME3 corpora. For objective testing, perceptual evaluation of speech quality is used to evaluate the quality of the restored speech. For subjective testing, the standard mean-opinion-score method is used. The critical analysis and comparative study demonstrate the outperformance of proposed contextual AV approach, over A-only, V-only, spectral subtraction, and log-minimum mean square error based speech enhancement methods at both low and high SNRs, revealing its capability to tackle spectro-temporal variation in any real-world noisy condition. |
| Tasks | Speech Enhancement |
| Published | 2018-08-28 |
| URL | http://arxiv.org/abs/1808.09825v1 |
| http://arxiv.org/pdf/1808.09825v1.pdf | |
| PWC | https://paperswithcode.com/paper/contextual-audio-visual-switching-for-speech |
| Repo | |
| Framework | |
Expression Recognition Using the Periocular Region: A Feasibility Study
| Title | Expression Recognition Using the Periocular Region: A Feasibility Study |
| Authors | Fernando Alonso-Fernandez, Josef Bigun, Cristofer Englund |
| Abstract | This paper investigates the feasibility of using the periocular region for expression recognition. Most works have tried to solve this by analyzing the whole face. Periocular is the facial region in the immediate vicinity of the eye. It has the advantage of being available over a wide range of distances and under partial face occlusion, thus making it suitable for unconstrained or uncooperative scenarios. We evaluate five different image descriptors on a dataset of 1,574 images from 118 subjects. The experimental results show an average/overall accuracy of 67.0%/78.0% by fusion of several descriptors. While this accuracy is still behind that attained with full-face methods, it is noteworthy to mention that our initial approach employs only one frame to predict the expression, in contraposition to state of the art, exploiting several order more data comprising spatial-temporal data which is often not available. |
| Tasks | |
| Published | 2018-10-23 |
| URL | http://arxiv.org/abs/1810.09798v1 |
| http://arxiv.org/pdf/1810.09798v1.pdf | |
| PWC | https://paperswithcode.com/paper/expression-recognition-using-the-periocular |
| Repo | |
| Framework | |
Unsupervised Learning of Shape Concepts - From Real-World Objects to Mental Simulation
| Title | Unsupervised Learning of Shape Concepts - From Real-World Objects to Mental Simulation |
| Authors | Christian A. Mueller, Andreas Birk |
| Abstract | An unsupervised shape analysis is proposed to learn concepts reflecting shape commonalities. Our approach is two-fold: i) a spatial topology analysis of point cloud segment constellations within objects is used in which constellations are decomposed and described in a hierarchical and symbolic manner. ii) A topology analysis of the description space is used in which segment decompositions are exposed in. Inspired by Persistent Homology, groups of shape commonality are revealed. Experiments show that extracted persistent commonality groups can feature semantically meaningful shape concepts; the generalization of the proposed approach is evaluated by different real-world datasets. We extend this by not only learning shape concepts using real-world data, but by also using mental simulation of artificial abstract objects for training purposes. This extended approach is unsupervised in two respects: label-agnostic (no label information is used) and instance-agnostic (no instances preselected by human supervision are used for training). Experiments show that concepts generated with mental simulation, generalize and discriminate real object observations. Consequently, a robot may train and learn its own internal representation of concepts regarding shape appearance in a self-driven and machine-centric manner while omitting the tedious process of supervised dataset generation including the ambiguity in instance labeling and selection. |
| Tasks | |
| Published | 2018-11-20 |
| URL | http://arxiv.org/abs/1811.08165v1 |
| http://arxiv.org/pdf/1811.08165v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-learning-of-shape-concepts-from |
| Repo | |
| Framework | |
Derivative free optimization via repeated classification
| Title | Derivative free optimization via repeated classification |
| Authors | Tatsunori B. Hashimoto, Steve Yadlowsky, John C. Duchi |
| Abstract | We develop an algorithm for minimizing a function using $n$ batched function value measurements at each of $T$ rounds by using classifiers to identify a function’s sublevel set. We show that sufficiently accurate classifiers can achieve linear convergence rates, and show that the convergence rate is tied to the difficulty of active learning sublevel sets. Further, we show that the bootstrap is a computationally efficient approximation to the necessary classification scheme. The end result is a computationally efficient derivative-free algorithm requiring no tuning that consistently outperforms other approaches on simulations, standard benchmarks, real-world DNA binding optimization, and airfoil design problems whenever batched function queries are natural. |
| Tasks | Active Learning |
| Published | 2018-04-11 |
| URL | http://arxiv.org/abs/1804.03761v1 |
| http://arxiv.org/pdf/1804.03761v1.pdf | |
| PWC | https://paperswithcode.com/paper/derivative-free-optimization-via-repeated |
| Repo | |
| Framework | |
Data-Driven Impulse Response Regularization via Deep Learning
| Title | Data-Driven Impulse Response Regularization via Deep Learning |
| Authors | Carl Andersson, Niklas Wahlström, Thomas B. Schön |
| Abstract | We consider the problem of impulse response estimation of stable linear single-input single-output systems. It is a well-studied problem where flexible non-parametric models recently offered a leap in performance compared to the classical finite-dimensional model structures. Inspired by this development and the success of deep learning we propose a new flexible data-driven model. Our experiments indicate that the new model is capable of exploiting even more of the hidden patterns that are present in the input-output data as compared to the non-parametric models. |
| Tasks | |
| Published | 2018-01-25 |
| URL | http://arxiv.org/abs/1801.08383v2 |
| http://arxiv.org/pdf/1801.08383v2.pdf | |
| PWC | https://paperswithcode.com/paper/data-driven-impulse-response-regularization |
| Repo | |
| Framework | |
Shape-only Features for Plant Leaf Identification
| Title | Shape-only Features for Plant Leaf Identification |
| Authors | Charlie Hewitt, Marwa Mahmoud |
| Abstract | This paper presents a novel feature set for shape-only leaf identification motivated by real-world, mobile deployment. The feature set includes basic shape features, as well as signal features extracted from local area integral invariants (LAIIs), similar to curvature maps, at multiple scales. The proposed methodology is evaluated on a number of publicly available leaf datasets with comparable results to existing methods which make use of colour and texture features in addition to shape. Over 90% classification accuracy is achieved on most datasets, with top-four accuracy for these datasets reaching over 98%. Rotation and scale invariance of the proposed features are demonstrated, along with an evaluation of the generalisability of the approach for generic shape matching. |
| Tasks | |
| Published | 2018-11-20 |
| URL | http://arxiv.org/abs/1811.08398v1 |
| http://arxiv.org/pdf/1811.08398v1.pdf | |
| PWC | https://paperswithcode.com/paper/shape-only-features-for-plant-leaf |
| Repo | |
| Framework | |
Non-monotonic Reasoning in Deductive Argumentation
| Title | Non-monotonic Reasoning in Deductive Argumentation |
| Authors | Anthony Hunter |
| Abstract | Argumentation is a non-monotonic process. This reflects the fact that argumentation involves uncertain information, and so new information can cause a change in the conclusions drawn. However, the base logic does not need to be non-monotonic. Indeed, most proposals for structured argumentation use a monotonic base logic (e.g. some form of modus ponens with a rule-based language, or classical logic). Nonetheless, there are issues in capturing defeasible reasoning in argumentation including choice of base logic and modelling of defeasible knowledge. And there are insights and tools to be harnessed for research in non-monontonic logics. We consider some of these issues in this paper. |
| Tasks | |
| Published | 2018-09-04 |
| URL | http://arxiv.org/abs/1809.00858v1 |
| http://arxiv.org/pdf/1809.00858v1.pdf | |
| PWC | https://paperswithcode.com/paper/non-monotonic-reasoning-in-deductive |
| Repo | |
| Framework | |
Study of Residual Networks for Image Recognition
| Title | Study of Residual Networks for Image Recognition |
| Authors | Mohammad Sadegh Ebrahimi, Hossein Karkeh Abadi |
| Abstract | Deep neural networks demonstrate to have a high performance on image classification tasks while being more difficult to train. Due to the complexity and vanishing gradient problem, it normally takes a lot of time and more computational power to train deeper neural networks. Deep residual networks (ResNets) can make the training process faster and attain more accuracy compared to their equivalent neural networks. ResNets achieve this improvement by adding a simple skip connection parallel to the layers of convolutional neural networks. In this project we first design a ResNet model that can perform the image classification task on the Tiny ImageNet dataset with a high accuracy, then we compare the performance of this ResNet model with its equivalent Convolutional Network (ConvNet). Our findings illustrate that ResNets are more prone to overfitting despite their higher accuracy. Several methods to prevent overfitting such as adding dropout layers and stochastic augmentation of the training dataset has been studied in this work. |
| Tasks | Image Classification |
| Published | 2018-04-21 |
| URL | http://arxiv.org/abs/1805.00325v1 |
| http://arxiv.org/pdf/1805.00325v1.pdf | |
| PWC | https://paperswithcode.com/paper/study-of-residual-networks-for-image |
| Repo | |
| Framework | |
Human peripheral blur is optimal for object recognition
| Title | Human peripheral blur is optimal for object recognition |
| Authors | R. T. Pramod, Harish Katti, S. P. Arun |
| Abstract | Our vision is sharpest at the center of our gaze and becomes progressively blurry into the periphery. It is widely believed that this high foveal resolution evolved at the expense of peripheral acuity. But what if this sampling scheme is actually optimal for object recognition? To test this hypothesis, we trained deep neural networks on ‘foveated’ images with high resolution near objects and increasingly sparse sampling into the periphery. Neural networks trained using a blur profile matching the human eye yielded the best performance compared to shallower and steeper blur profiles. Even in humans, categorization accuracy deteriorated only for steeper blur profiles. Thus, our blurry peripheral vision may have evolved to optimize object recognition rather than merely due to wiring constraints. |
| Tasks | Object Classification, Object Recognition |
| Published | 2018-07-23 |
| URL | https://arxiv.org/abs/1807.08476v2 |
| https://arxiv.org/pdf/1807.08476v2.pdf | |
| PWC | https://paperswithcode.com/paper/human-peripheral-blur-is-optimal-for-object |
| Repo | |
| Framework | |
Global Non-convex Optimization with Discretized Diffusions
| Title | Global Non-convex Optimization with Discretized Diffusions |
| Authors | Murat A. Erdogdu, Lester Mackey, Ohad Shamir |
| Abstract | An Euler discretization of the Langevin diffusion is known to converge to the global minimizers of certain convex and non-convex optimization problems. We show that this property holds for any suitably smooth diffusion and that different diffusions are suitable for optimizing different classes of convex and non-convex functions. This allows us to design diffusions suitable for globally optimizing convex and non-convex functions not covered by the existing Langevin theory. Our non-asymptotic analysis delivers computable optimization and integration error bounds based on easily accessed properties of the objective and chosen diffusion. Central to our approach are new explicit Stein factor bounds on the solutions of Poisson equations. We complement these results with improved optimization guarantees for targets other than the standard Gibbs measure. |
| Tasks | |
| Published | 2018-10-29 |
| URL | https://arxiv.org/abs/1810.12361v2 |
| https://arxiv.org/pdf/1810.12361v2.pdf | |
| PWC | https://paperswithcode.com/paper/global-non-convex-optimization-with |
| Repo | |
| Framework | |
Beyond Unfolding: Exact Recovery of Latent Convex Tensor Decomposition under Reshuffling
| Title | Beyond Unfolding: Exact Recovery of Latent Convex Tensor Decomposition under Reshuffling |
| Authors | Chao Li, Mohammad Emtiyaz Khan, Zhun Sun, Gang Niu, Bo Han, Shengli Xie, Qibin Zhao |
| Abstract | Exact recovery of tensor decomposition (TD) methods is a desirable property in both unsupervised learning and scientific data analysis. The numerical defects of TD methods, however, limit their practical applications on real-world data. As an alternative, convex tensor decomposition (CTD) was proposed to alleviate these problems, but its exact-recovery property is not properly addressed so far. To this end, we focus on latent convex tensor decomposition (LCTD), a practically widely-used CTD model, and rigorously prove a sufficient condition for its exact-recovery property. Furthermore, we show that such property can be also achieved by a more general model than LCTD. In the new model, we generalize the classic tensor (un-)folding into reshuffling operation, a more flexible mapping to relocate the entries of the matrix into a tensor. Armed with the reshuffling operations and exact-recovery property, we explore a totally novel application for (generalized) LCTD, i.e., image steganography. Experimental results on synthetic data validate our theory, and results on image steganography show that our method outperforms the state-of-the-art methods. |
| Tasks | Image Steganography |
| Published | 2018-05-22 |
| URL | https://arxiv.org/abs/1805.08465v3 |
| https://arxiv.org/pdf/1805.08465v3.pdf | |
| PWC | https://paperswithcode.com/paper/exact-recovery-of-low-rank-tensor |
| Repo | |
| Framework | |
Fourier Policy Gradients
| Title | Fourier Policy Gradients |
| Authors | Matthew Fellows, Kamil Ciosek, Shimon Whiteson |
| Abstract | We propose a new way of deriving policy gradient updates for reinforcement learning. Our technique, based on Fourier analysis, recasts integrals that arise with expected policy gradients as convolutions and turns them into multiplications. The obtained analytical solutions allow us to capture the low variance benefits of EPG in a broad range of settings. For the critic, we treat trigonometric and radial basis functions, two function families with the universal approximation property. The choice of policy can be almost arbitrary, including mixtures or hybrid continuous-discrete probability distributions. Moreover, we derive a general family of sample-based estimators for stochastic policy gradients, which unifies existing results on sample-based approximation. We believe that this technique has the potential to shape the next generation of policy gradient approaches, powered by analytical results. |
| Tasks | |
| Published | 2018-02-19 |
| URL | http://arxiv.org/abs/1802.06891v2 |
| http://arxiv.org/pdf/1802.06891v2.pdf | |
| PWC | https://paperswithcode.com/paper/fourier-policy-gradients |
| Repo | |
| Framework | |
Comparative Study on Generative Adversarial Networks
| Title | Comparative Study on Generative Adversarial Networks |
| Authors | Saifuddin Hitawala |
| Abstract | In recent years, there have been tremendous advancements in the field of machine learning. These advancements have been made through both academic as well as industrial research. Lately, a fair amount of research has been dedicated to the usage of generative models in the field of computer vision and image classification. These generative models have been popularized through a new framework called Generative Adversarial Networks. Moreover, many modified versions of this framework have been proposed in the last two years. We study the original model proposed by Goodfellow et al. as well as modifications over the original model and provide a comparative analysis of these models. |
| Tasks | Image Classification |
| Published | 2018-01-12 |
| URL | http://arxiv.org/abs/1801.04271v1 |
| http://arxiv.org/pdf/1801.04271v1.pdf | |
| PWC | https://paperswithcode.com/paper/comparative-study-on-generative-adversarial |
| Repo | |
| Framework | |
