Paper Group ANR 534
Improving the Performance of Unimodal Dynamic Hand-Gesture Recognition with Multimodal Training. Robust Semantic Segmentation with Ladder-DenseNet Models. Impacts of Weather Conditions on District Heat System. Streaming Methods for Restricted Strongly Convex Functions with Applications to Prototype Selection. Creating a contemporary corpus of simil …
Improving the Performance of Unimodal Dynamic Hand-Gesture Recognition with Multimodal Training
Title | Improving the Performance of Unimodal Dynamic Hand-Gesture Recognition with Multimodal Training |
Authors | Mahdi Abavisani, Hamid Reza Vaezi Joze, Vishal M. Patel |
Abstract | We present an efficient approach for leveraging the knowledge from multiple modalities in training unimodal 3D convolutional neural networks (3D-CNNs) for the task of dynamic hand gesture recognition. Instead of explicitly combining multimodal information, which is commonplace in many state-of-the-art methods, we propose a different framework in which we embed the knowledge of multiple modalities in individual networks so that each unimodal network can achieve an improved performance. In particular, we dedicate separate networks per available modality and enforce them to collaborate and learn to develop networks with common semantics and better representations. We introduce a “spatiotemporal semantic alignment” loss (SSA) to align the content of the features from different networks. In addition, we regularize this loss with our proposed “focal regularization parameter” to avoid negative knowledge transfer. Experimental results show that our framework improves the test time recognition accuracy of unimodal networks, and provides the state-of-the-art performance on various dynamic hand gesture recognition datasets. |
Tasks | Action Recognition In Videos, Gesture Recognition, Hand Gesture Recognition, Hand-Gesture Recognition, Transfer Learning |
Published | 2018-12-14 |
URL | https://arxiv.org/abs/1812.06145v2 |
https://arxiv.org/pdf/1812.06145v2.pdf | |
PWC | https://paperswithcode.com/paper/improving-the-performance-of-unimodal-dynamic |
Repo | |
Framework | |
Robust Semantic Segmentation with Ladder-DenseNet Models
Title | Robust Semantic Segmentation with Ladder-DenseNet Models |
Authors | Ivan Krešo, Marin Oršić, Petra Bevandić, Siniša Šegvić |
Abstract | We present semantic segmentation experiments with a model capable to perform predictions on four benchmark datasets: Cityscapes, ScanNet, WildDash and KITTI. We employ a ladder-style convolutional architecture featuring a modified DenseNet-169 model in the downsampling datapath, and only one convolution in each stage of the upsampling datapath. Due to limited computing resources, we perform the training only on Cityscapes Fine train+val, ScanNet train, WildDash val and KITTI train. We evaluate the trained model on the test subsets of the four benchmarks in concordance with the guidelines of the Robust Vision Challenge ROB 2018. The performed experiments reveal several interesting findings which we describe and discuss. |
Tasks | Semantic Segmentation |
Published | 2018-06-09 |
URL | http://arxiv.org/abs/1806.03465v1 |
http://arxiv.org/pdf/1806.03465v1.pdf | |
PWC | https://paperswithcode.com/paper/robust-semantic-segmentation-with-ladder |
Repo | |
Framework | |
Impacts of Weather Conditions on District Heat System
Title | Impacts of Weather Conditions on District Heat System |
Authors | Jiyang Xie, Zhanyu Ma, Jun Guo |
Abstract | Using artificial neural network for the prediction of heat demand has attracted more and more attention. Weather conditions, such as ambient temperature, wind speed and direct solar irradiance, have been identified as key input parameters. In order to further improve the model accuracy, it is of great importance to understand the influence of different parameters. Based on an Elman neural network (ENN), this paper investigates the impact of direct solar irradiance and wind speed on predicting the heat demand of a district heating network. Results show that including wind speed can generally result in a lower overall mean absolute percentage error (MAPE) (6.43%) than including direct solar irradiance (6.47%); while including direct solar irradiance can achieve a lower maximum absolute deviation (71.8%) than including wind speed (81.53%). In addition, even though including both wind speed and direct solar irradiance shows the best overall performance (MAPE=6.35%). |
Tasks | |
Published | 2018-08-02 |
URL | https://arxiv.org/abs/1808.00961v2 |
https://arxiv.org/pdf/1808.00961v2.pdf | |
PWC | https://paperswithcode.com/paper/impacts-of-weather-conditions-on-district |
Repo | |
Framework | |
Streaming Methods for Restricted Strongly Convex Functions with Applications to Prototype Selection
Title | Streaming Methods for Restricted Strongly Convex Functions with Applications to Prototype Selection |
Authors | Karthik S. Gurumoorthy, Amit Dhurandhar |
Abstract | In this paper, we show that if the optimization function is restricted-strongly-convex (RSC) and restricted-smooth (RSM) – a rich subclass of weakly submodular functions – then a streaming algorithm with constant factor approximation guarantee is possible. More generally, our results are applicable to any monotone weakly submodular function with submodularity ratio bounded from above. This (positive) result which provides a sufficient condition for having a constant factor streaming guarantee for weakly submodular functions may be of special interest given the recent negative result (Elenberg et al., 2017) for the general class of weakly submodular functions. We apply our streaming algorithms for creating compact synopsis of large complex datasets, by selecting $m$ representative elements, by optimizing a suitable RSC and RSM objective function. Above results hold even with additional constraints such as learning non-negative weights, for interpretability, for each selected element indicative of its importance. We empirically evaluate our algorithms on two real datasets: MNIST- a handwritten digits dataset and Letters- a UCI dataset containing the alphabet written in different fonts and styles. We observe that our algorithms are orders of magnitude faster than the state-of-the-art streaming algorithm for weakly submodular functions and with our main algorithm still providing equally good solutions in practice. |
Tasks | |
Published | 2018-07-21 |
URL | http://arxiv.org/abs/1807.08091v1 |
http://arxiv.org/pdf/1807.08091v1.pdf | |
PWC | https://paperswithcode.com/paper/streaming-methods-for-restricted-strongly |
Repo | |
Framework | |
Creating a contemporary corpus of similes in Serbian by using natural language processing
Title | Creating a contemporary corpus of similes in Serbian by using natural language processing |
Authors | Nikola Milosevic, Goran Nenadic |
Abstract | Simile is a figure of speech that compares two things through the use of connection words, but where comparison is not intended to be taken literally. They are often used in everyday communication, but they are also a part of linguistic cultural heritage. In this paper we present a methodology for semi-automated collection of similes from the World Wide Web using text mining and machine learning techniques. We expanded an existing corpus by collecting 442 similes from the internet and adding them to the existing corpus collected by Vuk Stefanovic Karadzic that contained 333 similes. We, also, introduce crowdsourcing to the collection of figures of speech, which helped us to build corpus containing 787 unique similes. |
Tasks | |
Published | 2018-11-22 |
URL | http://arxiv.org/abs/1811.10422v1 |
http://arxiv.org/pdf/1811.10422v1.pdf | |
PWC | https://paperswithcode.com/paper/creating-a-contemporary-corpus-of-similes-in |
Repo | |
Framework | |
An Analysis of Two Common Reference Points for EEGs
Title | An Analysis of Two Common Reference Points for EEGs |
Authors | Silvia Lopez, Aaron Gross, Scott Yang, Meysam Golmohammadi, Iyad Obeid, Joseph Picone |
Abstract | Clinical electroencephalographic (EEG) data varies significantly depending on a number of operational conditions (e.g., the type and placement of electrodes, the type of electrical grounding used). This investigation explores the statistical differences present in two different referential montages: Linked Ear (LE) and Averaged Reference (AR). Each of these accounts for approximately 45% of the data in the TUH EEG Corpus. In this study, we explore the impact this variability has on machine learning performance. We compare the statistical properties of features generated using these two montages, and explore the impact of performance on our standard Hidden Markov Model (HMM) based classification system. We show that a system trained on LE data significantly outperforms one trained only on AR data (77.2% vs. 61.4%). We also demonstrate that performance of a system trained on both data sets is somewhat compromised (71.4% vs. 77.2%). A statistical analysis of the data suggests that mean, variance and channel normalization should be considered. However, cepstral mean subtraction failed to produce an improvement in performance, suggesting that the impact of these statistical differences is subtler. |
Tasks | EEG |
Published | 2018-01-03 |
URL | http://arxiv.org/abs/1801.02474v1 |
http://arxiv.org/pdf/1801.02474v1.pdf | |
PWC | https://paperswithcode.com/paper/an-analysis-of-two-common-reference-points |
Repo | |
Framework | |
Pseudo-Recursal: Solving the Catastrophic Forgetting Problem in Deep Neural Networks
Title | Pseudo-Recursal: Solving the Catastrophic Forgetting Problem in Deep Neural Networks |
Authors | Craig Atkinson, Brendan McCane, Lech Szymanski, Anthony Robins |
Abstract | In general, neural networks are not currently capable of learning tasks in a sequential fashion. When a novel, unrelated task is learnt by a neural network, it substantially forgets how to solve previously learnt tasks. One of the original solutions to this problem is pseudo-rehearsal, which involves learning the new task while rehearsing generated items representative of the previous task/s. This is very effective for simple tasks. However, pseudo-rehearsal has not yet been successfully applied to very complex tasks because in these tasks it is difficult to generate representative items. We accomplish pseudo-rehearsal by using a Generative Adversarial Network to generate items so that our deep network can learn to sequentially classify the CIFAR-10, SVHN and MNIST datasets. After training on all tasks, our network loses only 1.67% absolute accuracy on CIFAR-10 and gains 0.24% absolute accuracy on SVHN. Our model’s performance is a substantial improvement compared to the current state of the art solution. |
Tasks | |
Published | 2018-02-12 |
URL | http://arxiv.org/abs/1802.03875v2 |
http://arxiv.org/pdf/1802.03875v2.pdf | |
PWC | https://paperswithcode.com/paper/pseudo-recursal-solving-the-catastrophic |
Repo | |
Framework | |
Robustness to Out-of-Distribution Inputs via Task-Aware Generative Uncertainty
Title | Robustness to Out-of-Distribution Inputs via Task-Aware Generative Uncertainty |
Authors | Rowan McAllister, Gregory Kahn, Jeff Clune, Sergey Levine |
Abstract | Deep learning provides a powerful tool for machine perception when the observations resemble the training data. However, real-world robotic systems must react intelligently to their observations even in unexpected circumstances. This requires a system to reason about its own uncertainty given unfamiliar, out-of-distribution observations. Approximate Bayesian approaches are commonly used to estimate uncertainty for neural network predictions, but can struggle with out-of-distribution observations. Generative models can in principle detect out-of-distribution observations as those with a low estimated density. However, the mere presence of an out-of-distribution input does not by itself indicate an unsafe situation. In this paper, we present a method for uncertainty-aware robotic perception that combines generative modeling and model uncertainty to cope with uncertainty stemming from out-of-distribution states. Our method estimates an uncertainty measure about the model’s prediction, taking into account an explicit (generative) model of the observation distribution to handle out-of-distribution inputs. This is accomplished by probabilistically projecting observations onto the training distribution, such that out-of-distribution inputs map to uncertain in-distribution observations, which in turn produce uncertain task-related predictions, but only if task-relevant parts of the image change. We evaluate our method on an action-conditioned collision prediction task with both simulated and real data, and demonstrate that our method of projecting out-of-distribution observations improves the performance of four standard Bayesian and non-Bayesian neural network approaches, offering more favorable trade-offs between the proportion of time a robot can remain autonomous and the proportion of impending crashes successfully avoided. |
Tasks | |
Published | 2018-12-27 |
URL | http://arxiv.org/abs/1812.10687v1 |
http://arxiv.org/pdf/1812.10687v1.pdf | |
PWC | https://paperswithcode.com/paper/robustness-to-out-of-distribution-inputs-via |
Repo | |
Framework | |
Abstract Meaning Representation for Multi-Document Summarization
Title | Abstract Meaning Representation for Multi-Document Summarization |
Authors | Kexin Liao, Logan Lebanoff, Fei Liu |
Abstract | Generating an abstract from a collection of documents is a desirable capability for many real-world applications. However, abstractive approaches to multi-document summarization have not been thoroughly investigated. This paper studies the feasibility of using Abstract Meaning Representation (AMR), a semantic representation of natural language grounded in linguistic theory, as a form of content representation. Our approach condenses source documents to a set of summary graphs following the AMR formalism. The summary graphs are then transformed to a set of summary sentences in a surface realization step. The framework is fully data-driven and flexible. Each component can be optimized independently using small-scale, in-domain training data. We perform experiments on benchmark summarization datasets and report promising results. We also describe opportunities and challenges for advancing this line of research. |
Tasks | Document Summarization, Multi-Document Summarization |
Published | 2018-06-14 |
URL | http://arxiv.org/abs/1806.05655v1 |
http://arxiv.org/pdf/1806.05655v1.pdf | |
PWC | https://paperswithcode.com/paper/abstract-meaning-representation-for-multi |
Repo | |
Framework | |
Closed Form Word Embedding Alignment
Title | Closed Form Word Embedding Alignment |
Authors | Sunipa Dev, Safia Hassan, Jeff M. Phillips |
Abstract | We develop a family of techniques to align word embeddings which are derived from different source datasets or created using different mechanisms (e.g., GloVe or word2vec). Our methods are simple and have a closed form to optimally rotate, translate, and scale to minimize root mean squared errors or maximize the average cosine similarity between two embeddings of the same vocabulary into the same dimensional space. Our methods extend approaches known as Absolute Orientation, which are popular for aligning objects in three-dimensions, and generalize an approach by Smith etal (ICLR 2017). We prove new results for optimal scaling and for maximizing cosine similarity. Then we demonstrate how to evaluate the similarity of embeddings from different sources or mechanisms, and that certain properties like synonyms and analogies are preserved across the embeddings and can be enhanced by simply aligning and averaging ensembles of embeddings. |
Tasks | Word Embeddings |
Published | 2018-06-04 |
URL | https://arxiv.org/abs/1806.01330v3 |
https://arxiv.org/pdf/1806.01330v3.pdf | |
PWC | https://paperswithcode.com/paper/absolute-orientation-for-word-embedding |
Repo | |
Framework | |
Deep-CLASS at ISIC Machine Learning Challenge 2018
Title | Deep-CLASS at ISIC Machine Learning Challenge 2018 |
Authors | Sara Nasiri, Matthias Jung, Julien Helsper, Madjid Fathi |
Abstract | This paper reports the method and evaluation results of MedAusbild team for ISIC challenge task. Since early 2017, our team has worked on melanoma classification [1][6], and has employed deep learning since beginning of 2018 [7]. Deep learning helps researchers absolutely to treat and detect diseases by analyzing medical data (e.g., medical images). One of the representative models among the various deep-learning models is a convolutional neural network (CNN). Although our team has an experience with segmentation and classification of benign and malignant skin-lesions, we have participated in the task 3 of ISIC Challenge 2018 for classification of seven skin diseases, explained in this paper. |
Tasks | |
Published | 2018-07-24 |
URL | http://arxiv.org/abs/1807.08993v1 |
http://arxiv.org/pdf/1807.08993v1.pdf | |
PWC | https://paperswithcode.com/paper/deep-class-at-isic-machine-learning-challenge |
Repo | |
Framework | |
The Adversarial Attack and Detection under the Fisher Information Metric
Title | The Adversarial Attack and Detection under the Fisher Information Metric |
Authors | Chenxiao Zhao, P. Thomas Fletcher, Mixue Yu, Yaxin Peng, Guixu Zhang, Chaomin Shen |
Abstract | Many deep learning models are vulnerable to the adversarial attack, i.e., imperceptible but intentionally-designed perturbations to the input can cause incorrect output of the networks. In this paper, using information geometry, we provide a reasonable explanation for the vulnerability of deep learning models. By considering the data space as a non-linear space with the Fisher information metric induced from a neural network, we first propose an adversarial attack algorithm termed one-step spectral attack (OSSA). The method is described by a constrained quadratic form of the Fisher information matrix, where the optimal adversarial perturbation is given by the first eigenvector, and the model vulnerability is reflected by the eigenvalues. The larger an eigenvalue is, the more vulnerable the model is to be attacked by the corresponding eigenvector. Taking advantage of the property, we also propose an adversarial detection method with the eigenvalues serving as characteristics. Both our attack and detection algorithms are numerically optimized to work efficiently on large datasets. Our evaluations show superior performance compared with other methods, implying that the Fisher information is a promising approach to investigate the adversarial attacks and defenses. |
Tasks | Adversarial Attack |
Published | 2018-10-09 |
URL | http://arxiv.org/abs/1810.03806v2 |
http://arxiv.org/pdf/1810.03806v2.pdf | |
PWC | https://paperswithcode.com/paper/the-adversarial-attack-and-detection-under |
Repo | |
Framework | |
Assessment of Breast Cancer Histology using Densely Connected Convolutional Networks
Title | Assessment of Breast Cancer Histology using Densely Connected Convolutional Networks |
Authors | Matthias Kohl, Christoph Walz, Florian Ludwig, Stefan Braunewell, Maximilian Baust |
Abstract | Breast cancer is the most frequently diagnosed cancer and leading cause of cancer-related death among females worldwide. In this article, we investigate the applicability of densely connected convolutional neural networks to the problems of histology image classification and whole slide image segmentation in the area of computer-aided diagnoses for breast cancer. To this end, we study various approaches for transfer learning and apply them to the data set from the 2018 grand challenge on breast cancer histology images (BACH). |
Tasks | Image Classification, Semantic Segmentation, Transfer Learning |
Published | 2018-04-09 |
URL | http://arxiv.org/abs/1804.04595v1 |
http://arxiv.org/pdf/1804.04595v1.pdf | |
PWC | https://paperswithcode.com/paper/assessment-of-breast-cancer-histology-using |
Repo | |
Framework | |
Ergodic Inference: Accelerate Convergence by Optimisation
Title | Ergodic Inference: Accelerate Convergence by Optimisation |
Authors | Yichuan Zhang, José Miguel Hernández-Lobato |
Abstract | Statistical inference methods are fundamentally important in machine learning. Most state-of-the-art inference algorithms are variants of Markov chain Monte Carlo (MCMC) or variational inference (VI). However, both methods struggle with limitations in practice: MCMC methods can be computationally demanding; VI methods may have large bias. In this work, we aim to improve upon MCMC and VI by a novel hybrid method based on the idea of reducing simulation bias of finite-length MCMC chains using gradient-based optimisation. The proposed method can generate low-biased samples by increasing the length of MCMC simulation and optimising the MCMC hyper-parameters, which offers attractive balance between approximation bias and computational efficiency. We show that our method produces promising results on popular benchmarks when compared to recent hybrid methods of MCMC and VI. |
Tasks | |
Published | 2018-05-25 |
URL | https://arxiv.org/abs/1805.10377v4 |
https://arxiv.org/pdf/1805.10377v4.pdf | |
PWC | https://paperswithcode.com/paper/ergodic-measure-preserving-flows |
Repo | |
Framework | |
Accelerating Nonnegative Matrix Factorization Algorithms using Extrapolation
Title | Accelerating Nonnegative Matrix Factorization Algorithms using Extrapolation |
Authors | Andersen Man Shun Ang, Nicolas Gillis |
Abstract | In this paper, we propose a general framework to accelerate significantly the algorithms for nonnegative matrix factorization (NMF). This framework is inspired from the extrapolation scheme used to accelerate gradient methods in convex optimization and from the method of parallel tangents. However, the use of extrapolation in the context of the two-block exact coordinate descent algorithms tackling the non-convex NMF problems is novel. We illustrate the performance of this approach on two state-of-the-art NMF algorithms, namely, accelerated hierarchical alternating least squares (A-HALS) and alternating nonnegative least squares (ANLS), using synthetic, image and document data sets. |
Tasks | |
Published | 2018-05-17 |
URL | http://arxiv.org/abs/1805.06604v2 |
http://arxiv.org/pdf/1805.06604v2.pdf | |
PWC | https://paperswithcode.com/paper/accelerating-nonnegative-matrix-factorization |
Repo | |
Framework | |