Paper Group ANR 674
Reliable Agglomerative Clustering. The GAN that Warped: Semantic Attribute Editing with Unpaired Data. Comprehensive Privacy Analysis of Deep Learning: Stand-alone and Federated Learning under Passive and Active White-box Inference Attacks. Generalized two-dimensional linear discriminant analysis with regularization. Novel Sparse Recovery Algorithm …
Reliable Agglomerative Clustering
Title | Reliable Agglomerative Clustering |
Authors | Morteza Haghir Chehreghani |
Abstract | We analyze the general behavior of agglomerative clustering methods, and argue that their strategy yields establishment of a new reliable linkage at each step. However, in order to provide adaptive, density-consistent and flexible solutions, we propose to extract all the reliable linkages at each step, instead of the smallest one. This leads to a new agglomerative clustering strategy, called reliable agglomerative clustering, which similar to the standard agglomerative variant can be applied with all common criteria. Moreover, we prove that this strategy with the \emph{single} linkage criterion yields a minimum spanning tree algorithm. We perform experiments on several real-world datasets to demonstrate the superior performance of this strategy, compared to the standard alternative. |
Tasks | |
Published | 2018-12-20 |
URL | https://arxiv.org/abs/1901.02063v2 |
https://arxiv.org/pdf/1901.02063v2.pdf | |
PWC | https://paperswithcode.com/paper/reliable-agglomerative-clustering |
Repo | |
Framework | |
The GAN that Warped: Semantic Attribute Editing with Unpaired Data
Title | The GAN that Warped: Semantic Attribute Editing with Unpaired Data |
Authors | Garoe Dorta, Sara Vicente, Neill D. F. Campbell, Ivor J. A. Simpson |
Abstract | Deep neural networks have recently been used to edit images with great success, in particular for faces. However, they are often limited to only being able to work at a restricted range of resolutions. Many methods are so flexible that face edits can often result in an unwanted loss of identity. This work proposes to learn how to perform semantic image edits through the application of smooth warp fields. Previous approaches that attempted to use warping for semantic edits required paired data, i.e. example images of the same subject with different semantic attributes. In contrast, we employ recent advances in Generative Adversarial Networks that allow our model to be trained with unpaired data. We demonstrate face editing at very high resolutions (4k images) with a single forward pass of a deep network at a lower resolution. We also show that our edits are substantially better at preserving the subject’s identity. The robustness of our approach is demonstrated by showing plausible image editing results on the Cub200 birds dataset. To our knowledge this has not been previously accomplished, due the challenging nature of the dataset. |
Tasks | |
Published | 2018-11-30 |
URL | https://arxiv.org/abs/1811.12784v4 |
https://arxiv.org/pdf/1811.12784v4.pdf | |
PWC | https://paperswithcode.com/paper/the-gan-that-warped-semantic-attribute |
Repo | |
Framework | |
Comprehensive Privacy Analysis of Deep Learning: Stand-alone and Federated Learning under Passive and Active White-box Inference Attacks
Title | Comprehensive Privacy Analysis of Deep Learning: Stand-alone and Federated Learning under Passive and Active White-box Inference Attacks |
Authors | Milad Nasr, Reza Shokri, Amir Houmansadr |
Abstract | Deep neural networks are susceptible to various inference attacks as they remember information about their training data. We perform a comprehensive analysis of white-box privacy inference attacks on deep learning models. We measure the privacy leakage by leveraging the final model parameters as well as the parameter updates during the training and fine-tuning processes. We design the attacks in the stand-alone and federated settings, with respect to passive and active inference attackers, and assuming different adversary prior knowledge. We design and evaluate our novel white-box membership inference attacks against deep learning algorithms to measure their training data membership leakage. We show that a straightforward extension of the known black-box attacks to the white-box setting (through analyzing the outputs of activation functions) is ineffective. We therefore design new algorithms tailored to the white-box setting by exploiting the privacy vulnerabilities of the stochastic gradient descent algorithm, widely used to train deep neural networks. We show that even well-generalized models are significantly susceptible to white-box membership inference attacks, by analyzing state-of-the-art pre-trained and publicly available models for the CIFAR dataset. We also show how adversarial participants of a federated learning setting can run active membership inference attacks against other participants, even when the global model achieves high prediction accuracies. |
Tasks | |
Published | 2018-12-03 |
URL | http://arxiv.org/abs/1812.00910v1 |
http://arxiv.org/pdf/1812.00910v1.pdf | |
PWC | https://paperswithcode.com/paper/comprehensive-privacy-analysis-of-deep |
Repo | |
Framework | |
Generalized two-dimensional linear discriminant analysis with regularization
Title | Generalized two-dimensional linear discriminant analysis with regularization |
Authors | Chun-Na Li, Yuan-Hai Shao, Wei-Jie Chen, Zhen Wang, Nai-Yang Deng |
Abstract | Recent advances show that two-dimensional linear discriminant analysis (2DLDA) is a successful matrix based dimensionality reduction method. However, 2DLDA may encounter the singularity issue theoretically and the sensitivity to outliers. In this paper, a generalized Lp-norm 2DLDA framework with regularization for an arbitrary $p>0$ is proposed, named G2DLDA. There are mainly two contributions of G2DLDA: one is G2DLDA model uses an arbitrary Lp-norm to measure the between-class and within-class scatter, and hence a proper $p$ can be selected to achieve the robustness. The other one is that by introducing an extra regularization term, G2DLDA achieves better generalization performance, and solves the singularity problem. In addition, G2DLDA can be solved through a series of convex problems with equality constraint, and it has closed solution for each single problem. Its convergence can be guaranteed theoretically when $1\leq p\leq2$. Preliminary experimental results on three contaminated human face databases show the effectiveness of the proposed G2DLDA. |
Tasks | Dimensionality Reduction |
Published | 2018-01-23 |
URL | http://arxiv.org/abs/1801.07426v2 |
http://arxiv.org/pdf/1801.07426v2.pdf | |
PWC | https://paperswithcode.com/paper/generalized-two-dimensional-linear |
Repo | |
Framework | |
Novel Sparse Recovery Algorithms for 3D Debris Localization using Rotating Point Spread Function Imagery
Title | Novel Sparse Recovery Algorithms for 3D Debris Localization using Rotating Point Spread Function Imagery |
Authors | Chao Wang, Robert Plemmons, Sudhakar Prasad, Raymond Chan, Mila Nikolova |
Abstract | An optical imager that exploits off-center image rotation to encode both the lateral and depth coordinates of point sources in a single snapshot can perform 3D localization and tracking of space debris. When actively illuminated, unresolved space debris, which can be regarded as a swarm of point sources, can scatter a fraction of laser irradiance back into the imaging sensor. Determining the source locations and fluxes is a large-scale sparse 3D inverse problem, for which we have developed efficient and effective algorithms based on sparse recovery using non-convex optimization. Numerical simulations illustrate the efficiency and stability of the algorithms. |
Tasks | |
Published | 2018-09-27 |
URL | http://arxiv.org/abs/1809.10541v1 |
http://arxiv.org/pdf/1809.10541v1.pdf | |
PWC | https://paperswithcode.com/paper/novel-sparse-recovery-algorithms-for-3d |
Repo | |
Framework | |
Crick-net: A Convolutional Neural Network based Classification Approach for Detecting Waist High No Balls in Cricket
Title | Crick-net: A Convolutional Neural Network based Classification Approach for Detecting Waist High No Balls in Cricket |
Authors | Md. Harun-Ur-Rashid, Shekina Khatun, Mehe Zabin Trisha, Nafis Neehal, Md. Zahid Hasan |
Abstract | Cricket is undoubtedly one of the most popular games in this modern era. As human beings are prone to error, there remains a constant need for automated analysis and decision making of different events in this game. Simultaneously, with advent and advances in Artificial Intelligence and Computer Vision, application of these two in different domains has become an emerging trend. Applying several computer vision techniques in analyzing different Cricket events and automatically coming into decisions has become popular in recent days. In this paper, we have deployed a CNN based classification method with Inception V3 in order to automatically detect and differentiate waist high no balls with fair balls. Our approach achieves an overall average accuracy of 88% with a fairly low cross-entropy value. |
Tasks | Decision Making |
Published | 2018-05-15 |
URL | http://arxiv.org/abs/1805.05974v1 |
http://arxiv.org/pdf/1805.05974v1.pdf | |
PWC | https://paperswithcode.com/paper/crick-net-a-convolutional-neural-network |
Repo | |
Framework | |
CFA Bayer image sequence denoising and demosaicking chain
Title | CFA Bayer image sequence denoising and demosaicking chain |
Authors | Antoni Buades, Joan Duran |
Abstract | The demosaicking provokes the spatial and color correlation of noise, which is afterwards enhanced by the imaging pipeline. The correct removal previous or simultaneously with the demosaicking process is not usually considered in the literature. We present a novel imaging chain including a denoising of the Bayer CFA and a demosaicking method for image sequences. The proposed algorithm uses a spatio-temporal patch method for the noise removal and demosaicking of the CFA. The experimentation, including real examples, illustrates the superior performance of the proposed chain, avoiding the creation of artifacts and colored spots in the final image. |
Tasks | Demosaicking, Denoising |
Published | 2018-12-28 |
URL | http://arxiv.org/abs/1812.11207v1 |
http://arxiv.org/pdf/1812.11207v1.pdf | |
PWC | https://paperswithcode.com/paper/cfa-bayer-image-sequence-denoising-and |
Repo | |
Framework | |
CNN-PS: CNN-based Photometric Stereo for General Non-Convex Surfaces
Title | CNN-PS: CNN-based Photometric Stereo for General Non-Convex Surfaces |
Authors | Satoshi Ikehata |
Abstract | Most conventional photometric stereo algorithms inversely solve a BRDF-based image formation model. However, the actual imaging process is often far more complex due to the global light transport on the non-convex surfaces. This paper presents a photometric stereo network that directly learns relationships between the photometric stereo input and surface normals of a scene. For handling unordered, arbitrary number of input images, we merge all the input data to the intermediate representation called {\it observation map} that has a fixed shape, is able to be fed into a CNN. To improve both training and prediction, we take into account the rotational pseudo-invariance of the observation map that is derived from the isotropic constraint. For training the network, we create a synthetic photometric stereo dataset that is generated by a physics-based renderer, therefore the global light transport is considered. Our experimental results on both synthetic and real datasets show that our method outperforms conventional BRDF-based photometric stereo algorithms especially when scenes are highly non-convex. |
Tasks | |
Published | 2018-08-30 |
URL | http://arxiv.org/abs/1808.10093v1 |
http://arxiv.org/pdf/1808.10093v1.pdf | |
PWC | https://paperswithcode.com/paper/cnn-ps-cnn-based-photometric-stereo-for |
Repo | |
Framework | |
A Pragmatic AI Approach to Creating Artistic Visual Variations by Neural Style Transfer
Title | A Pragmatic AI Approach to Creating Artistic Visual Variations by Neural Style Transfer |
Authors | Chaehan So |
Abstract | On a constant quest for inspiration, designers can become more effective with tools that facilitate their creative process and let them overcome design fixation. This paper explores the practicality of applying neural style transfer as an emerging design tool for generating creative digital content. To this aim, the present work explores a well-documented neural style transfer algorithm (Johnson 2016) in four experiments on four relevant visual parameters: number of iterations, learning rate, total variation, content vs. style weight. The results allow a pragmatic recommendation of parameter configuration (number of iterations: 200 to 300, learning rate: 2e-1 to 4e-1, total variation: 1e-4 to 1e-8, content weights vs. style weights: 50:100 to 200:100) that saves extensive experimentation time and lowers the technical entry barrier. With this rule-of-thumb insight, visual designers can effectively apply deep learning to create artistic visual variations of digital content. This could enable designers to leverage AI for creating design works as state-of-the-art. |
Tasks | Style Transfer |
Published | 2018-05-28 |
URL | http://arxiv.org/abs/1805.10852v1 |
http://arxiv.org/pdf/1805.10852v1.pdf | |
PWC | https://paperswithcode.com/paper/a-pragmatic-ai-approach-to-creating-artistic |
Repo | |
Framework | |
Adversarial Training of Word2Vec for Basket Completion
Title | Adversarial Training of Word2Vec for Basket Completion |
Authors | Ugo Tanielian, Mike Gartrell, Flavian Vasile |
Abstract | In recent years, the Word2Vec model trained with the Negative Sampling loss function has shown state-of-the-art results in a number of machine learning tasks, including language modeling tasks, such as word analogy and word similarity, and in recommendation tasks, through Prod2Vec, an extension that applies to modeling user shopping activity and user preferences. Several methods that aim to improve upon the standard Negative Sampling loss have been proposed. In our paper we pursue more sophisticated Negative Sampling, by leveraging ideas from the field of Generative Adversarial Networks (GANs), and propose Adversarial Negative Sampling. We build upon the recent progress made in stabilizing the training objective of GANs in the discrete data setting, and introduce a new GAN-Word2Vec model.We evaluate our model on the task of basket completion, and show significant improvements in performance over Word2Vec trained using standard loss functions, including Noise Contrastive Estimation and Negative Sampling. |
Tasks | Language Modelling |
Published | 2018-05-22 |
URL | http://arxiv.org/abs/1805.08720v1 |
http://arxiv.org/pdf/1805.08720v1.pdf | |
PWC | https://paperswithcode.com/paper/adversarial-training-of-word2vec-for-basket |
Repo | |
Framework | |
A Machine-learning framework for automatic reference-free quality assessment in MRI
Title | A Machine-learning framework for automatic reference-free quality assessment in MRI |
Authors | Thomas Küstner, Sergios Gatidis, Annika Liebgott, Martin Schwartz, Lukas Mauch, Petros Martirosian, Holger Schmidt, Nina F. Schwenzer, Konstantin Nikolaou, Fabian Bamberg, Bin Yang, Fritz Schick |
Abstract | Magnetic resonance (MR) imaging offers a wide variety of imaging techniques. A large amount of data is created per examination which needs to be checked for sufficient quality in order to derive a meaningful diagnosis. This is a manual process and therefore time- and cost-intensive. Any imaging artifacts originating from scanner hardware, signal processing or induced by the patient may reduce the image quality and complicate the diagnosis or any image post-processing. Therefore, the assessment or the ensurance of sufficient image quality in an automated manner is of high interest. Usually no reference image is available or difficult to define. Therefore, classical reference-based approaches are not applicable. Model observers mimicking the human observers (HO) can assist in this task. Thus, we propose a new machine-learning-based reference-free MR image quality assessment framework which is trained on HO-derived labels to assess MR image quality immediately after each acquisition. We include the concept of active learning and present an efficient blinded reading platform to reduce the effort in the HO labeling procedure. Derived image features and the applied classifiers (support-vector-machine, deep neural network) are investigated for a cohort of 250 patients. The MR image quality assessment framework can achieve a high test accuracy of 93.7$%$ for estimating quality classes on a 5-point Likert-scale. The proposed MR image quality assessment framework is able to provide an accurate and efficient quality estimation which can be used as a prospective quality assurance including automatic acquisition adaptation or guided MR scanner operation, and/or as a retrospective quality assessment including support of diagnostic decisions or quality control in cohort studies. |
Tasks | Active Learning, Image Quality Assessment |
Published | 2018-06-25 |
URL | http://arxiv.org/abs/1806.09602v2 |
http://arxiv.org/pdf/1806.09602v2.pdf | |
PWC | https://paperswithcode.com/paper/a-machine-learning-framework-for-automatic |
Repo | |
Framework | |
Deep calibration of rough stochastic volatility models
Title | Deep calibration of rough stochastic volatility models |
Authors | Christian Bayer, Benjamin Stemper |
Abstract | Sparked by Al`os, Le'on, and Vives (2007); Fukasawa (2011, 2017); Gatheral, Jaisson, and Rosenbaum (2018), so-called rough stochastic volatility models such as the rough Bergomi model by Bayer, Friz, and Gatheral (2016) constitute the latest evolution in option price modeling. Unlike standard bivariate diffusion models such as Heston (1993), these non-Markovian models with fractional volatility drivers allow to parsimoniously recover key stylized facts of market implied volatility surfaces such as the exploding power-law behaviour of the at-the-money volatility skew as time to maturity goes to zero. Standard model calibration routines rely on the repetitive evaluation of the map from model parameters to Black-Scholes implied volatility, rendering calibration of many (rough) stochastic volatility models prohibitively expensive since there the map can often only be approximated by costly Monte Carlo (MC) simulations (Bennedsen, Lunde, & Pakkanen, 2017; McCrickerd & Pakkanen, 2018; Bayer et al., 2016; Horvath, Jacquier, & Muguruza, 2017). As a remedy, we propose to combine a standard Levenberg-Marquardt calibration routine with neural network regression, replacing expensive MC simulations with cheap forward runs of a neural network trained to approximate the implied volatility map. Numerical experiments confirm the high accuracy and speed of our approach. |
Tasks | Calibration |
Published | 2018-10-08 |
URL | http://arxiv.org/abs/1810.03399v1 |
http://arxiv.org/pdf/1810.03399v1.pdf | |
PWC | https://paperswithcode.com/paper/deep-calibration-of-rough-stochastic |
Repo | |
Framework | |
Mirrored Langevin Dynamics
Title | Mirrored Langevin Dynamics |
Authors | Ya-Ping Hsieh, Ali Kavis, Paul Rolland, Volkan Cevher |
Abstract | We consider the problem of sampling from constrained distributions, which has posed significant challenges to both non-asymptotic analysis and algorithmic design. We propose a unified framework, which is inspired by the classical mirror descent, to derive novel first-order sampling schemes. We prove that, for a general target distribution with strongly convex potential, our framework implies the existence of a first-order algorithm achieving $\tilde{O}(\epsilon^{-2}d)$ convergence, suggesting that the state-of-the-art $\tilde{O}(\epsilon^{-6}d^5)$ can be vastly improved. With the important Latent Dirichlet Allocation (LDA) application in mind, we specialize our algorithm to sample from Dirichlet posteriors, and derive the first non-asymptotic $\tilde{O}(\epsilon^{-2}d^2)$ rate for first-order sampling. We further extend our framework to the mini-batch setting and prove convergence rates when only stochastic gradients are available. Finally, we report promising experimental results for LDA on real datasets. |
Tasks | |
Published | 2018-02-27 |
URL | http://arxiv.org/abs/1802.10174v4 |
http://arxiv.org/pdf/1802.10174v4.pdf | |
PWC | https://paperswithcode.com/paper/mirrored-langevin-dynamics |
Repo | |
Framework | |
Detection-by-Localization: Maintenance-Free Change Object Detector
Title | Detection-by-Localization: Maintenance-Free Change Object Detector |
Authors | Tanaka Kanji |
Abstract | Recent researches demonstrate that self-localization performance is a very useful measure of likelihood-of-change (LoC) for change detection. In this paper, this “detection-by-localization” scheme is studied in a novel generalized task of object-level change detection. In our framework, a given query image is segmented into object-level subimages (termed “scene parts”), which are then converted to subimage-level pixel-wise LoC maps via the detection-by-localization scheme. Our approach models a self-localization system as a ranking function, outputting a ranked list of reference images, without requiring relevance score. Thanks to this new setting, we can generalize our approach to a broad class of self-localization systems. Our ranking based self-localization model allows to fuse self-localization results from different modalities via an unsupervised rank fusion derived from a field of multi-modal information retrieval (MMR). |
Tasks | Information Retrieval |
Published | 2018-09-14 |
URL | http://arxiv.org/abs/1809.05267v1 |
http://arxiv.org/pdf/1809.05267v1.pdf | |
PWC | https://paperswithcode.com/paper/detection-by-localization-maintenance-free |
Repo | |
Framework | |
Why ReLU Units Sometimes Die: Analysis of Single-Unit Error Backpropagation in Neural Networks
Title | Why ReLU Units Sometimes Die: Analysis of Single-Unit Error Backpropagation in Neural Networks |
Authors | Scott C. Douglas, Jiutian Yu |
Abstract | Recently, neural networks in machine learning use rectified linear units (ReLUs) in early processing layers for better performance. Training these structures sometimes results in “dying ReLU units” with near-zero outputs. We first explore this condition via simulation using the CIFAR-10 dataset and variants of two popular convolutive neural network architectures. Our explorations show that the output activation probability Pr[y>0] is generally less than 0.5 at system convergence for layers that do not employ skip connections, and this activation probability tends to decrease as one progresses from input layer to output layer. Employing a simplified model of a single ReLU unit trained by a variant of error backpropagation, we then perform a statistical convergence analysis to explore the model’s evolutionary behavior. Our analysis describes the potentially-slower convergence speeds of dying ReLU units, and this issue can occur regardless of how the weights are initialized. |
Tasks | |
Published | 2018-12-14 |
URL | http://arxiv.org/abs/1812.05981v1 |
http://arxiv.org/pdf/1812.05981v1.pdf | |
PWC | https://paperswithcode.com/paper/why-relu-units-sometimes-die-analysis-of |
Repo | |
Framework | |