Paper Group ANR 1131
Learning Linear Non-Gaussian Causal Models in the Presence of Latent Variables. Instant Motion Tracking and Its Applications to Augmented Reality. Epsilon-Lexicase Selection for Regression. Patch-Based Image Similarity for Intraoperative 2D/3D Pelvis Registration During Periacetabular Osteotomy. Identifying Personality Traits Using Overlap Dynamics …
Learning Linear Non-Gaussian Causal Models in the Presence of Latent Variables
| Title | Learning Linear Non-Gaussian Causal Models in the Presence of Latent Variables |
| Authors | Saber Salehkaleybar, AmirEmad Ghassami, Negar Kiyavash, Kun Zhang |
| Abstract | We consider the problem of learning causal models from observational data generated by linear non-Gaussian acyclic causal models with latent variables. Without considering the effect of latent variables, one usually infers wrong causal relationships among the observed variables. Under faithfulness assumption, we propose a method to check whether there exists a causal path between any two observed variables. From this information, we can obtain the causal order among them. The next question is then whether or not the causal effects can be uniquely identified as well. It can be shown that causal effects among observed variables cannot be identified uniquely even under the assumptions of faithfulness and non-Gaussianity of exogenous noises. However, we will propose an efficient method to identify the set of all possible causal effects that are compatible with the observational data. Furthermore, we present some structural conditions on the causal graph under which we can learn causal effects among observed variables uniquely. We also provide necessary and sufficient graphical conditions for unique identification of the number of variables in the system. Experiments on synthetic data and real-world data show the effectiveness of our proposed algorithm on learning causal models. |
| Tasks | |
| Published | 2019-08-11 |
| URL | https://arxiv.org/abs/1908.03932v1 |
| https://arxiv.org/pdf/1908.03932v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-linear-non-gaussian-causal-models-in |
| Repo | |
| Framework | |
Instant Motion Tracking and Its Applications to Augmented Reality
| Title | Instant Motion Tracking and Its Applications to Augmented Reality |
| Authors | Jianing Wei, Genzhi Ye, Tyler Mullen, Matthias Grundmann, Adel Ahmadyan, Tingbo Hou |
| Abstract | Augmented Reality (AR) brings immersive experiences to users. With recent advances in computer vision and mobile computing, AR has scaled across platforms, and has increased adoption in major products. One of the key challenges in enabling AR features is proper anchoring of the virtual content to the real world, a process referred to as tracking. In this paper, we present a system for motion tracking, which is capable of robustly tracking planar targets and performing relative-scale 6DoF tracking without calibration. Our system runs in real-time on mobile phones and has been deployed in multiple major products on hundreds of millions of devices. |
| Tasks | Calibration |
| Published | 2019-07-16 |
| URL | https://arxiv.org/abs/1907.06796v1 |
| https://arxiv.org/pdf/1907.06796v1.pdf | |
| PWC | https://paperswithcode.com/paper/instant-motion-tracking-and-its-applications |
| Repo | |
| Framework | |
Epsilon-Lexicase Selection for Regression
| Title | Epsilon-Lexicase Selection for Regression |
| Authors | William La Cava, Lee Spector, Kourosh Danai |
| Abstract | Lexicase selection is a parent selection method that considers test cases separately, rather than in aggregate, when performing parent selection. It performs well in discrete error spaces but not on the continuous-valued problems that compose most system identification tasks. In this paper, we develop a new form of lexicase selection for symbolic regression, named epsilon-lexicase selection, that redefines the pass condition for individuals on each test case in a more effective way. We run a series of experiments on real-world and synthetic problems with several treatments of epsilon and quantify how epsilon affects parent selection and model performance. epsilon-lexicase selection is shown to be effective for regression, producing better fit models compared to other techniques such as tournament selection and age-fitness Pareto optimization. We demonstrate that epsilon can be adapted automatically for individual test cases based on the population performance distribution. Our experiments show that epsilon-lexicase selection with automatic epsilon produces the most accurate models across tested problems with negligible computational overhead. We show that behavioral diversity is exceptionally high in lexicase selection treatments, and that epsilon-lexicase selection makes use of more fitness cases when selecting parents than lexicase selection, which helps explain the performance improvement. |
| Tasks | |
| Published | 2019-05-30 |
| URL | https://arxiv.org/abs/1905.13266v1 |
| https://arxiv.org/pdf/1905.13266v1.pdf | |
| PWC | https://paperswithcode.com/paper/epsilon-lexicase-selection-for-regression |
| Repo | |
| Framework | |
Patch-Based Image Similarity for Intraoperative 2D/3D Pelvis Registration During Periacetabular Osteotomy
| Title | Patch-Based Image Similarity for Intraoperative 2D/3D Pelvis Registration During Periacetabular Osteotomy |
| Authors | Robert Grupp, Mehran Armand, Russell Taylor |
| Abstract | Periacetabular osteotomy is a challenging surgical procedure for treating developmental hip dysplasia, providing greater coverage of the femoral head via relocation of a patient’s acetabulum. Since fluoroscopic imaging is frequently used in the surgical workflow, computer-assisted X-Ray navigation of osteotomes and the relocated acetabular fragment should be feasible. We use intensity-based 2D/3D registration to estimate the pelvis pose with respect to fluoroscopic images, recover relative poses of multiple views, and triangulate landmarks which may be used for navigation. Existing similarity metrics are unable to consistently account for the inherent mismatch between the preoperative intact pelvis, and the intraoperative reality of a fractured pelvis. To mitigate the effect of this mismatch, we continuously estimate the relevance of each pixel to solving the registration and use these values as weightings in a patch-based similarity metric. Limiting computation to randomly selected subsets of patches results in faster runtimes than existing patch-based methods. A simulation study was conducted with random fragment shapes, relocations, and fluoroscopic views, and the proposed method achieved a 1.7 mm mean triangulation error over all landmarks, compared to mean errors of 3 mm and 2.8 mm for the non-patched and image-intensity-variance-weighted patch similarity metrics, respectively. |
| Tasks | |
| Published | 2019-09-23 |
| URL | https://arxiv.org/abs/1909.10443v1 |
| https://arxiv.org/pdf/1909.10443v1.pdf | |
| PWC | https://paperswithcode.com/paper/190910443 |
| Repo | |
| Framework | |
Identifying Personality Traits Using Overlap Dynamics in Multiparty Dialogue
| Title | Identifying Personality Traits Using Overlap Dynamics in Multiparty Dialogue |
| Authors | Mingzhi Yu, Emer Gilmartin, Diane Litman |
| Abstract | Research on human spoken language has shown that speech plays an important role in identifying speaker personality traits. In this work, we propose an approach for identifying speaker personality traits using overlap dynamics in multiparty spoken dialogues. We first define a set of novel features representing the overlap dynamics of each speaker. We then investigate the impact of speaker personality traits on these features using ANOVA tests. We find that features of overlap dynamics significantly vary for speakers with different levels of both Extraversion and Conscientiousness. Finally, we find that classifiers using only overlap dynamics features outperform random guessing in identifying Extraversion and Agreeableness, and that the improvements are statistically significant. |
| Tasks | |
| Published | 2019-09-02 |
| URL | https://arxiv.org/abs/1909.00876v1 |
| https://arxiv.org/pdf/1909.00876v1.pdf | |
| PWC | https://paperswithcode.com/paper/identifying-personality-traits-using-overlap |
| Repo | |
| Framework | |
Multi-fidelity Bayesian Optimization with Max-value Entropy Search and its parallelization
| Title | Multi-fidelity Bayesian Optimization with Max-value Entropy Search and its parallelization |
| Authors | Shion Takeno, Hitoshi Fukuoka, Yuhki Tsukada, Toshiyuki Koyama, Motoki Shiga, Ichiro Takeuchi, Masayuki Karasuyama |
| Abstract | In a standard setting of Bayesian optimization (BO), the objective function evaluation is assumed to be highly expensive. Multi-fidelity Bayesian optimization (MFBO) accelerates BO by incorporating lower fidelity observations available with a lower sampling cost. In this paper, we focus on the information-based approach, which is a popular and empirically successful approach in BO. For MFBO, however, existing information-based methods are plagued by difficulty in estimating the information gain. We propose an approach based on max-value entropy search (MES), which greatly facilitates computations by considering the entropy of the optimal function value instead of the optimal input point. We show that, in our multi-fidelity MES (MF-MES), most of additional computations, compared with usual MES, is reduced to analytical computations. Although an additional numerical integration is necessary for the information across different fidelities, this is only in one dimensional space, which can be performed efficiently and accurately. Further, we also propose parallelization of MF-MES. Since there exist a variety of different sampling costs, queries typically occur asynchronously in MFBO. We show that similar simple computations can be derived for asynchronous parallel MFBO. We demonstrate effectiveness of our approach by using benchmark datasets and a real-world application to materials science data. |
| Tasks | |
| Published | 2019-01-24 |
| URL | https://arxiv.org/abs/1901.08275v2 |
| https://arxiv.org/pdf/1901.08275v2.pdf | |
| PWC | https://paperswithcode.com/paper/multi-fidelity-bayesian-optimization-with-max |
| Repo | |
| Framework | |
Let’s Play Mahjong!
| Title | Let’s Play Mahjong! |
| Authors | Sanjiang Li, Xueqing Yan |
| Abstract | Mahjong is a very popular tile-based game commonly played by four players. Each player begins with a hand of 13 tiles and, in turn, players draw and discard (i.e., change) tiles until they complete a legal hand using a 14th tile. In this paper, we initiate a mathematical and AI study of the Mahjong game and try to answer two fundamental questions: how bad is a hand of 14 tiles? and which tile should I discard? We define and characterise the notion of deficiency and present an optimal policy to discard a tile in order to increase the chance of completing a legal hand within $k$ tile changes for each $k\geq 1$. |
| Tasks | |
| Published | 2019-03-08 |
| URL | http://arxiv.org/abs/1903.03294v1 |
| http://arxiv.org/pdf/1903.03294v1.pdf | |
| PWC | https://paperswithcode.com/paper/lets-play-mahjong |
| Repo | |
| Framework | |
Supervised and Unsupervised End-to-End Deep Learning for Gene Ontology Classification of Neural In Situ Hybridization Images
| Title | Supervised and Unsupervised End-to-End Deep Learning for Gene Ontology Classification of Neural In Situ Hybridization Images |
| Authors | Ido Cohen, Eli David, Nathan S. Netanyahu |
| Abstract | In recent years, large datasets of high-resolution mammalian neural images have become available, which has prompted active research on the analysis of gene expression data. Traditional image processing methods are typically applied for learning functional representations of genes, based on their expressions in these brain images. In this paper, we describe a novel end-to-end deep learning-based method for generating compact representations of in situ hybridization (ISH) images, which are invariant-to-translation. In contrast to traditional image processing methods, our method relies, instead, on deep convolutional denoising autoencoders (CDAE) for processing raw pixel inputs, and generating the desired compact image representations. We provide an in-depth description of our deep learning-based approach, and present extensive experimental results, demonstrating that representations extracted by CDAE can help learn features of functional gene ontology categories for their classification in a highly accurate manner. Our methods improve the previous state-of-the-art classification rate (Liscovitch, et al.) from an average AUC of 0.92 to 0.997, i.e., it achieves 96% reduction in error rate. Furthermore, the representation vectors generated due to our method are more compact in comparison to previous state-of-the-art methods, allowing for a more efficient high-level representation of images. These results are obtained with significantly downsampled images in comparison to the original high-resolution ones, further underscoring the robustness of our proposed method. |
| Tasks | Denoising |
| Published | 2019-11-30 |
| URL | https://arxiv.org/abs/1912.01494v1 |
| https://arxiv.org/pdf/1912.01494v1.pdf | |
| PWC | https://paperswithcode.com/paper/supervised-and-unsupervised-end-to-end-deep |
| Repo | |
| Framework | |
Mapping Missing Population in Rural India: A Deep Learning Approach with Satellite Imagery
| Title | Mapping Missing Population in Rural India: A Deep Learning Approach with Satellite Imagery |
| Authors | Wenjie Hu, Jay Harshadbhai Patel, Zoe-Alanah Robert, Paul Novosad, Samuel Asher, Zhongyi Tang, Marshall Burke, David Lobell, Stefano Ermon |
| Abstract | Millions of people worldwide are absent from their country’s census. Accurate, current, and granular population metrics are critical to improving government allocation of resources, to measuring disease control, to responding to natural disasters, and to studying any aspect of human life in these communities. Satellite imagery can provide sufficient information to build a population map without the cost and time of a government census. We present two Convolutional Neural Network (CNN) architectures which efficiently and effectively combine satellite imagery inputs from multiple sources to accurately predict the population density of a region. In this paper, we use satellite imagery from rural villages in India and population labels from the 2011 SECC census. Our best model achieves better performance than previous papers as well as LandScan, a community standard for global population distribution. |
| Tasks | |
| Published | 2019-05-04 |
| URL | https://arxiv.org/abs/1905.02196v1 |
| https://arxiv.org/pdf/1905.02196v1.pdf | |
| PWC | https://paperswithcode.com/paper/mapping-missing-population-in-rural-india-a |
| Repo | |
| Framework | |
Security for Distributed Deep Neural Networks Towards Data Confidentiality & Intellectual Property Protection
| Title | Security for Distributed Deep Neural Networks Towards Data Confidentiality & Intellectual Property Protection |
| Authors | Laurent Gomez, Marcus Wilhelm, José Márquez, Patrick Duverger |
| Abstract | Current developments in Enterprise Systems observe a paradigm shift, moving the needle from the backend to the edge sectors of those; by distributing data, decentralizing applications and integrating novel components seamlessly to the central systems. Distributively deployed AI capabilities will thrust this transition. Several non-functional requirements arise along with these developments, security being at the center of the discussions. Bearing those requirements in mind, hereby we propose an approach to holistically protect distributed Deep Neural Network (DNN) based/enhanced software assets, i.e. confidentiality of their input & output data streams as well as safeguarding their Intellectual Property. Making use of Fully Homomorphic Encryption (FHE), our approach enables the protection of Distributed Neural Networks, while processing encrypted data. On that respect we evaluate the feasibility of this solution on a Convolutional Neuronal Network (CNN) for image classification deployed on distributed infrastructures. |
| Tasks | Image Classification |
| Published | 2019-07-09 |
| URL | https://arxiv.org/abs/1907.04246v1 |
| https://arxiv.org/pdf/1907.04246v1.pdf | |
| PWC | https://paperswithcode.com/paper/security-for-distributed-deep-neural-networks |
| Repo | |
| Framework | |
Adversarial Lipschitz Regularization
| Title | Adversarial Lipschitz Regularization |
| Authors | Dávid Terjék |
| Abstract | Generative adversarial networks (GANs) are one of the most popular approaches when it comes to training generative models, among which variants of Wasserstein GANs are considered superior to the standard GAN formulation in terms of learning stability and sample quality. However, Wasserstein GANs require the critic to be 1-Lipschitz, which is often enforced implicitly by penalizing the norm of its gradient, or by globally restricting its Lipschitz constant via weight normalization techniques. Training with a regularization term penalizing the violation of the Lipschitz constraint explicitly, instead of through the norm of the gradient, was found to be practically infeasible in most situations. Inspired by Virtual Adversarial Training, we propose a method called Adversarial Lipschitz Regularization, and show that using an explicit Lipschitz penalty is indeed viable and leads to competitive performance when applied to Wasserstein GANs, highlighting an important connection between Lipschitz regularization and adversarial training. |
| Tasks | |
| Published | 2019-07-12 |
| URL | https://arxiv.org/abs/1907.05681v3 |
| https://arxiv.org/pdf/1907.05681v3.pdf | |
| PWC | https://paperswithcode.com/paper/virtual-adversarial-lipschitz-regularization |
| Repo | |
| Framework | |
Neural Image Compression and Explanation
| Title | Neural Image Compression and Explanation |
| Authors | Xiang Li, Shihao Ji |
| Abstract | Explaining the prediction of deep neural networks (DNNs) and semantic image compression are two active research areas of deep learning with a numerous of applications in decision-critical systems, such as surveillance cameras, drones and self-driving cars, where interpretable decision is critical and storage/network bandwidth is limited. In this paper, we propose a novel end-to-end Neural Image Compression and Explanation (NICE) framework that learns to (1) explain the prediction of convolutional neural networks (CNNs), and (2) subsequently compress the input images for efficient storage or transmission. Specifically, NICE generates a sparse mask over an input image by attaching a stochastic binary gate to each pixel of the image, whose parameters are learned through the interaction with the CNN classifier to be explained. The generated mask is able to capture the saliency of each pixel measured by its influence to the final prediction of CNN; it can also be used to produce a mixed-resolution image, where important pixels maintain their original high resolution and insignificant background pixels are subsampled to a low resolution. The produced images achieve a high compression rate (e.g., about 0.6x of original image file size), while retaining a similar classification accuracy. Extensive experiments across multiple image classification benchmarks demonstrate the superior performance of NICE compared to the state-of-the-art methods in terms of explanation quality and image compression rate. |
| Tasks | Image Classification, Image Compression, Self-Driving Cars |
| Published | 2019-08-09 |
| URL | https://arxiv.org/abs/1908.08988v1 |
| https://arxiv.org/pdf/1908.08988v1.pdf | |
| PWC | https://paperswithcode.com/paper/neural-image-compression-and-explanation |
| Repo | |
| Framework | |
Imitation in the Imitation Game
| Title | Imitation in the Imitation Game |
| Authors | Ravi Kashyap |
| Abstract | We discuss the objectives of automation equipped with non-trivial decision making, or creating artificial intelligence, in the financial markets and provide a possible alternative. Intelligence might be an unintended consequence of curiosity left to roam free, best exemplified by a frolicking infant. For this unintentional yet welcome aftereffect to set in a foundational list of guiding principles needs to be present. A consideration of these requirements allows us to propose a test of intelligence for trading programs, on the lines of the Turing Test, long the benchmark for intelligent machines. We discuss the application of this methodology to the dilemma in finance, which is whether, when and how much to Buy, Sell or Hold. |
| Tasks | Decision Making |
| Published | 2019-11-03 |
| URL | https://arxiv.org/abs/1911.06893v1 |
| https://arxiv.org/pdf/1911.06893v1.pdf | |
| PWC | https://paperswithcode.com/paper/imitation-in-the-imitation-game |
| Repo | |
| Framework | |
Analyzing ImageNet with Spectral Relevance Analysis: Towards ImageNet un-Hans’ed
| Title | Analyzing ImageNet with Spectral Relevance Analysis: Towards ImageNet un-Hans’ed |
| Authors | Christopher J. Anders, Talmaj Marinč, David Neumann, Wojciech Samek, Klaus-Robert Müller, Sebastian Lapuschkin |
| Abstract | Today’s machine learning models for computer vision are typically trained on very large (benchmark) data sets with millions of samples. These may, however, contain biases, artifacts, or errors that have gone unnoticed and are exploited by the model. In the worst case, the trained model may become a ‘Clever Hans’ predictor that does not learn a valid and generalizable strategy to solve the problem it was trained for, but bases its decisions on spurious correlations in the training data. Recently developed techniques allow to explain individual model decisions and thus to gain deeper insights into the model’s prediction strategies. In this paper, we contribute by providing a comprehensive analysis framework based on a scalable statistical analysis of attributions from explanation methods for large data corpora, here ImageNet. Based on a recent technique - Spectral Relevance Analysis (SpRAy) - we propose three technical contributions and resulting findings: (a) novel similarity metrics based on Wasserstein for comparing attributions to allow for the first time scale, translational, and rotational invariant comparisons of attributions, (b) a scalable quantification of artifactual and poisoned classes where the ML models under study exhibit Clever Hans behavior, (c) a cleaning procedure that allows to relief data of artifacts and biases in a systematic manner yielding significantly reduced Clever Hans behavior, i.e. we un-Hans the ImageNet data corpus. Using this novel method set, we provide qualitative and quantitative analyses of the biases and artifacts in ImageNet and demonstrate that the usage of these insights can give rise to improved models and functionally cleaned data corpora. |
| Tasks | |
| Published | 2019-12-22 |
| URL | https://arxiv.org/abs/1912.11425v1 |
| https://arxiv.org/pdf/1912.11425v1.pdf | |
| PWC | https://paperswithcode.com/paper/analyzing-imagenet-with-spectral-relevance |
| Repo | |
| Framework | |
Solving general elliptical mixture models through an approximate Wasserstein manifold
| Title | Solving general elliptical mixture models through an approximate Wasserstein manifold |
| Authors | Shengxi Li, Zeyang Yu, Min Xiang, Danilo Mandic |
| Abstract | We address the estimation problem for general finite mixture models, with a particular focus on the elliptical mixture models (EMMs). Compared to the widely adopted Kullback-Leibler divergence, we show that the Wasserstein distance provides a more desirable optimisation space. We thus provide a stable solution to the EMMs that is both robust to initialisations and reaches a superior optimum by adaptively optimising along a manifold of an approximate Wasserstein distance. To this end, we first provide a unifying account of computable and identifiable EMMs, which serves as a basis to rigorously address the underpinning optimisation problem. Due to a probability constraint, solving this problem is extremely cumbersome and unstable, especially under the Wasserstein distance. To relieve this issue, we introduce an efficient optimisation method on a statistical manifold defined under an approximate Wasserstein distance, which allows for explicit metrics and computable operations, thus significantly stabilising and improving the EMM estimation. We further propose an adaptive method to accelerate the convergence. Experimental results demonstrate the excellent performance of the proposed EMM solver. |
| Tasks | |
| Published | 2019-06-09 |
| URL | https://arxiv.org/abs/1906.03700v3 |
| https://arxiv.org/pdf/1906.03700v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-general-solver-to-the-elliptical-mixture |
| Repo | |
| Framework | |
