Paper Group ANR 363
Water Distribution System Design Using Multi-Objective Particle Swarm Optimisation. Causal statistical modeling and calculation of distribution functions of classification features. Can Attention Masks Improve Adversarial Robustness?. Speaker diarisation using 2D self-attentive combination of embeddings. Modeling Food Popularity Dependencies using …
Water Distribution System Design Using Multi-Objective Particle Swarm Optimisation
| Title | Water Distribution System Design Using Multi-Objective Particle Swarm Optimisation |
| Authors | Mahesh B. Patil, M. Naveen Naidu, A. Vasan, Murari R. R. Varma |
| Abstract | Application of the multi-objective particle swarm optimisation (MOPSO) algorithm to design of water distribution systems is described. An earlier MOPSO algorithm is augmented with (a) local search, (b) a modified strategy for assigning the leader, and (c) a modified mutation scheme. For one of the benchmark problems described in the literature, the effect of each of the above features on the algorithm performance is demonstrated. The augmented MOPSO algorithm (called MOPSO+) is applied to five benchmark problems, and in each case, it finds non-dominated solutions not reported earlier. In addition, for the purpose of comparing Pareto fronts (sets of non-dominated solutions) obtained by different algorithms, a new criterion is suggested, and its usefulness is pointed out with an example. Finally, some suggestions regarding future research directions are made. |
| Tasks | |
| Published | 2019-03-14 |
| URL | http://arxiv.org/abs/1903.06127v1 |
| http://arxiv.org/pdf/1903.06127v1.pdf | |
| PWC | https://paperswithcode.com/paper/water-distribution-system-design-using-multi |
| Repo | |
| Framework | |
Causal statistical modeling and calculation of distribution functions of classification features
| Title | Causal statistical modeling and calculation of distribution functions of classification features |
| Authors | Uwe Petersohn, Thomas Dedek, Sandra Zimmer, Hans Biskupski |
| Abstract | Statistical system models provide the basis for the examination of various sorts of distributions. Classification distributions are a very common and versatile form of statistics in e.g. real economic, social, and IT systems. The statistical distributions of classification features can be applied in determining the a priori probabilities in Bayesian networks. We investigate a statistical model of classification distributions based on finding the critical point of a specialized form of entropy. A distribution function for classification features is derived, with the two parameters $n_0$, minimal class, and $\bar{N}$, average number of classes. Efficient algorithms for the computation of the class probabilities and the approximation of real frequency distributions are developed and applied to examples from different domains. The method is compared to established distributions like Zipf’s law. The majority of examples can be approximated with a sufficient quality ($3-5%$). |
| Tasks | |
| Published | 2019-12-19 |
| URL | https://arxiv.org/abs/1912.09334v1 |
| https://arxiv.org/pdf/1912.09334v1.pdf | |
| PWC | https://paperswithcode.com/paper/causal-statistical-modeling-and-calculation |
| Repo | |
| Framework | |
Can Attention Masks Improve Adversarial Robustness?
| Title | Can Attention Masks Improve Adversarial Robustness? |
| Authors | Pratik Vaishnavi, Tianji Cong, Kevin Eykholt, Atul Prakash, Amir Rahmati |
| Abstract | Deep Neural Networks (DNNs) are known to be susceptible to adversarial examples. Adversarial examples are maliciously crafted inputs that are designed to fool a model, but appear normal to human beings. Recent work has shown that pixel discretization can be used to make classifiers for MNIST highly robust to adversarial examples. However, pixel discretization fails to provide significant protection on more complex datasets. In this paper, we take the first step towards reconciling these contrary findings. Focusing on the observation that discrete pixelization in MNIST makes the background completely black and foreground completely white, we hypothesize that the important property for increasing robustness is the elimination of image background using attention masks before classifying an object. To examine this hypothesis, we create foreground attention masks for two different datasets, GTSRB and MS-COCO. Our initial results suggest that using attention mask leads to improved robustness. On the adversarially trained classifiers, we see an adversarial robustness increase of over 20% on MS-COCO. |
| Tasks | |
| Published | 2019-11-27 |
| URL | https://arxiv.org/abs/1911.11946v2 |
| https://arxiv.org/pdf/1911.11946v2.pdf | |
| PWC | https://paperswithcode.com/paper/can-attention-masks-improve-adversarial |
| Repo | |
| Framework | |
Speaker diarisation using 2D self-attentive combination of embeddings
| Title | Speaker diarisation using 2D self-attentive combination of embeddings |
| Authors | Guangzhi Sun, Chao Zhang, Phil Woodland |
| Abstract | Speaker diarisation systems often cluster audio segments using speaker embeddings such as i-vectors and d-vectors. Since different types of embeddings are often complementary, this paper proposes a generic framework to improve performance by combining them into a single embedding, referred to as a c-vector. This combination uses a 2-dimensional (2D) self-attentive structure, which extends the standard self-attentive layer by averaging not only across time but also across different types of embeddings. Two types of 2D self-attentive structure in this paper are the simultaneous combination and the consecutive combination, adopting a single and multiple self-attentive layers respectively. The penalty term in the original self-attentive layer which is jointly minimised with the objective function to encourage diversity of annotation vectors is also modified to obtain not only different local peaks but also the overall trends in the multiple annotation vectors. Experiments on the AMI meeting corpus show that our modified penalty term improves the d- vector relative speaker error rate (SER) by 6% and 21% for d-vector systems, and a 10% further relative SER reduction can be obtained using the c-vector from our best 2D self-attentive structure. |
| Tasks | |
| Published | 2019-02-08 |
| URL | http://arxiv.org/abs/1902.03190v1 |
| http://arxiv.org/pdf/1902.03190v1.pdf | |
| PWC | https://paperswithcode.com/paper/speaker-diarisation-using-2d-self-attentive |
| Repo | |
| Framework | |
Modeling Food Popularity Dependencies using Social Media data
| Title | Modeling Food Popularity Dependencies using Social Media data |
| Authors | Devashish Khulbe, Manu Pathak |
| Abstract | The rise in popularity of major social media platforms have enabled people to share photos and textual information about their daily life. One of the popular topics about which information is shared is food. Since a lot of media about food are attributed to particular locations and restaurants, information like spatio-temporal popularity of various cuisines can be analyzed. Tracking the popularity of food types and retail locations across space and time can also be useful for business owners and restaurant investors. In this work, we present an approach using off-the shelf machine learning techniques to identify trends and popularity of cuisine types in an area using geo-tagged data from social media, Google images and Yelp. After adjusting for time, we use the Kernel Density Estimation to get hot spots across the location and model the dependencies among food cuisines popularity using Bayesian Networks. We consider the Manhattan borough of New York City as the location for our analyses but the approach can be used for any area with social media data and information about retail businesses. |
| Tasks | Density Estimation |
| Published | 2019-06-26 |
| URL | https://arxiv.org/abs/1906.12331v2 |
| https://arxiv.org/pdf/1906.12331v2.pdf | |
| PWC | https://paperswithcode.com/paper/modeling-food-popularity-dependencies-using |
| Repo | |
| Framework | |
Convolutions on Spherical Images
| Title | Convolutions on Spherical Images |
| Authors | Marc Eder, Jan-Michael Frahm |
| Abstract | Applying convolutional neural networks to spherical images requires particular considerations. We look to the millennia of work on cartographic map projections to provide the tools to define an optimal representation of spherical images for the convolution operation. We propose a representation for deep spherical image inference based on the icosahedral Snyder equal-area (ISEA) projection, a projection onto a geodesic grid, and show that it vastly exceeds the state-of-the-art for convolution on spherical images, improving semantic segmentation results by 12.6%. |
| Tasks | Semantic Segmentation |
| Published | 2019-05-21 |
| URL | https://arxiv.org/abs/1905.08409v1 |
| https://arxiv.org/pdf/1905.08409v1.pdf | |
| PWC | https://paperswithcode.com/paper/convolutions-on-spherical-images |
| Repo | |
| Framework | |
Semantic Bilinear Pooling for Fine-Grained Recognition
| Title | Semantic Bilinear Pooling for Fine-Grained Recognition |
| Authors | Xinjie Li, Chun Yang, Songlu Chen, Chao Zhu, Xu-Cheng Yin |
| Abstract | Naturally, fine-grained recognition, e.g., vehicle identification or bird classification, has specific hierarchical labels, where fine categories are always harder to be classified than coarse categories. However, most of the recent deep learning based methods neglect the semantic structure of fine-grained objects and do not take advantage of the traditional fine-grained recognition techniques (e.g. coarse-to-fine classification). In this paper, we propose a novel framework with a two-branch network (coarse branch and fine branch), i.e., semantic bilinear pooling, for fine-grained recognition with a hierarchical label tree. This framework can adaptively learn the semantic information from the hierarchical levels. Specifically, we design a generalized cross-entropy loss for the training of the proposed framework to fully exploit the semantic priors via considering the relevance between adjacent levels and enlarge the distance between samples of different coarse classes. Furthermore, our method leverages only the fine branch when testing so that it adds no overhead to the testing time. Experimental results show that our proposed method achieves state-of-the-art performance on four public datasets. |
| Tasks | Multi-Label Learning |
| Published | 2019-04-03 |
| URL | https://arxiv.org/abs/1904.01893v3 |
| https://arxiv.org/pdf/1904.01893v3.pdf | |
| PWC | https://paperswithcode.com/paper/semantic-bilinear-pooling-for-fine-grained |
| Repo | |
| Framework | |
Radar-based Road User Classification and Novelty Detection with Recurrent Neural Network Ensembles
| Title | Radar-based Road User Classification and Novelty Detection with Recurrent Neural Network Ensembles |
| Authors | Nicolas Scheiner, Nils Appenrodt, Jürgen Dickmann, Bernhard Sick |
| Abstract | Radar-based road user classification is an important yet still challenging task towards autonomous driving applications. The resolution of conventional automotive radar sensors results in a sparse data representation which is tough to recover by subsequent signal processing. In this article, classifier ensembles originating from a one-vs-one binarization paradigm are enriched by one-vs-all correction classifiers. They are utilized to efficiently classify individual traffic participants and also identify hidden object classes which have not been presented to the classifiers during training. For each classifier of the ensemble an individual feature set is determined from a total set of 98 features. Thereby, the overall classification performance can be improved when compared to previous methods and, additionally, novel classes can be identified much more accurately. Furthermore, the proposed structure allows to give new insights in the importance of features for the recognition of individual classes which is crucial for the development of new algorithms and sensor requirements. |
| Tasks | Autonomous Driving |
| Published | 2019-05-28 |
| URL | https://arxiv.org/abs/1905.11703v1 |
| https://arxiv.org/pdf/1905.11703v1.pdf | |
| PWC | https://paperswithcode.com/paper/radar-based-road-user-classification-and |
| Repo | |
| Framework | |
Black Box Recursive Translations for Molecular Optimization
| Title | Black Box Recursive Translations for Molecular Optimization |
| Authors | Farhan Damani, Vishnu Sresht, Stephen Ra |
| Abstract | Machine learning algorithms for generating molecular structures offer a promising new approach to drug discovery. We cast molecular optimization as a translation problem, where the goal is to map an input compound to a target compound with improved biochemical properties. Remarkably, we observe that when generated molecules are iteratively fed back into the translator, molecular compound attributes improve with each step. We show that this finding is invariant to the choice of translation model, making this a “black box” algorithm. We call this method Black Box Recursive Translation (BBRT), a new inference method for molecular property optimization. This simple, powerful technique operates strictly on the inputs and outputs of any translation model. We obtain new state-of-the-art results for molecular property optimization tasks using our simple drop-in replacement with well-known sequence and graph-based models. Our method provides a significant boost in performance relative to its non-recursive peers with just a simple “for” loop. Further, BBRT is highly interpretable, allowing users to map the evolution of newly discovered compounds from known starting points. |
| Tasks | Drug Discovery |
| Published | 2019-12-21 |
| URL | https://arxiv.org/abs/1912.10156v1 |
| https://arxiv.org/pdf/1912.10156v1.pdf | |
| PWC | https://paperswithcode.com/paper/black-box-recursive-translations-for-1 |
| Repo | |
| Framework | |
Combining Online Learning Guarantees
| Title | Combining Online Learning Guarantees |
| Authors | Ashok Cutkosky |
| Abstract | We show how to take any two parameter-free online learning algorithms with different regret guarantees and obtain a single algorithm whose regret is the minimum of the two base algorithms. Our method is embarrassingly simple: just add the iterates. This trick can generate efficient algorithms that adapt to many norms simultaneously, as well as providing diagonal-style algorithms that still maintain dimension-free guarantees. We then proceed to show how a variant on this idea yields a black-box procedure for generating optimistic online learning algorithms. This yields the first optimistic regret guarantees in the unconstrained setting and generically increases adaptivity. Further, our optimistic algorithms are guaranteed to do no worse than their non-optimistic counterparts regardless of the quality of the optimistic estimates provided to the algorithm. |
| Tasks | |
| Published | 2019-02-24 |
| URL | http://arxiv.org/abs/1902.09003v1 |
| http://arxiv.org/pdf/1902.09003v1.pdf | |
| PWC | https://paperswithcode.com/paper/combining-online-learning-guarantees |
| Repo | |
| Framework | |
Deep Visual Waterline Detection within Inland Marine Environment
| Title | Deep Visual Waterline Detection within Inland Marine Environment |
| Authors | Jing Huang, Hengfeng Miao, Lin Li, Yuanqiao Wen, Changshi Xiao |
| Abstract | Waterline usually plays as an important visual cue for maritime applications. However, the visual complexity of inland waterline presents a significant challenge for the development of highly efficient computer vision algorithms tailored for waterline detection in a complicated inland water environment. This paper attempts to find a solution to guarantee the effectiveness of waterline detection for inland maritime applications with general digital camera sensor. To this end, a general deep-learning-based paradigm applicable in variable inland waters, named DeepWL, is proposed, which concerns the efficiency of waterline detection simultaneously. Specifically, there are two novel deep network models, named WLdetectNet and WLgenerateNet respectively, cooperating in the paradigm that afford a continuous waterline image-map estimation from a single captured video stream. Experimental results demonstrate the effectiveness and superiority of the proposed approach via qualitative and quantitative assessment on the concerned performances. Moreover, due to its own generality, the proposed approach has the potential to be applied to the waterline detection tasks of other water areas such as coastal waters. |
| Tasks | |
| Published | 2019-11-24 |
| URL | https://arxiv.org/abs/1911.10498v1 |
| https://arxiv.org/pdf/1911.10498v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-visual-waterline-detection-within-inland |
| Repo | |
| Framework | |
Calibrationless Parallel MRI using Model based Deep Learning (C-MODL)
| Title | Calibrationless Parallel MRI using Model based Deep Learning (C-MODL) |
| Authors | Aniket Pramanik, Hemant Aggarwal, Mathews Jacob |
| Abstract | We introduce a fast model based deep learning approach for calibrationless parallel MRI reconstruction. The proposed scheme is a non-linear generalization of structured low rank (SLR) methods that self learn linear annihilation filters from the same subject. It pre-learns non-linear annihilation relations in the Fourier domain from exemplar data. The pre-learning strategy significantly reduces the computational complexity, making the proposed scheme three orders of magnitude faster than SLR schemes. The proposed framework also allows the use of a complementary spatial domain prior; the hybrid regularization scheme offers improved performance over calibrated image domain MoDL approach. The calibrationless strategy minimizes potential mismatches between calibration data and the main scan, while eliminating the need for a fully sampled calibration region. |
| Tasks | Calibration |
| Published | 2019-11-27 |
| URL | https://arxiv.org/abs/1911.12443v2 |
| https://arxiv.org/pdf/1911.12443v2.pdf | |
| PWC | https://paperswithcode.com/paper/calibrationless-parallel-mri-using-model |
| Repo | |
| Framework | |
Lifelong Neural Topic Learning in Contextualized Autoregressive Topic Models of Language via Informative Transfers
| Title | Lifelong Neural Topic Learning in Contextualized Autoregressive Topic Models of Language via Informative Transfers |
| Authors | Yatin Chaudhary, Pankaj Gupta, Thomas Runkler |
| Abstract | Topic models such as LDA, DocNADE, iDocNADEe have been popular in document analysis. However, the traditional topic models have several limitations including: (1) Bag-of-words (BoW) assumption, where they ignore word ordering, (2) Data sparsity, where the application of topic models is challenging due to limited word co-occurrences, leading to incoherent topics and (3) No Continuous Learning framework for topic learning in lifelong fashion, exploiting historical knowledge (or latent topics) and minimizing catastrophic forgetting. This thesis focuses on addressing the above challenges within neural topic modeling framework. We propose: (1) Contextualized topic model that combines a topic and a language model and introduces linguistic structures (such as word ordering, syntactic and semantic features, etc.) in topic modeling, (2) A novel lifelong learning mechanism into neural topic modeling framework to demonstrate continuous learning in sequential document collections and minimizing catastrophic forgetting. Additionally, we perform a selective data augmentation to alleviate the need for complete historical corpora during data hallucination or replay. |
| Tasks | Data Augmentation, Language Modelling, Topic Models |
| Published | 2019-09-29 |
| URL | https://arxiv.org/abs/1909.13315v1 |
| https://arxiv.org/pdf/1909.13315v1.pdf | |
| PWC | https://paperswithcode.com/paper/lifelong-neural-topic-learning-in |
| Repo | |
| Framework | |
Understanding Adversarial Robustness Through Loss Landscape Geometries
| Title | Understanding Adversarial Robustness Through Loss Landscape Geometries |
| Authors | Vinay Uday Prabhu, Dian Ang Yap, Joyce Xu, John Whaley |
| Abstract | The pursuit of explaining and improving generalization in deep learning has elicited efforts both in regularization techniques as well as visualization techniques of the loss surface geometry. The latter is related to the intuition prevalent in the community that flatter local optima leads to lower generalization error. In this paper, we harness the state-of-the-art “filter normalization” technique of loss-surface visualization to qualitatively understand the consequences of using adversarial training data augmentation as the explicit regularization technique of choice. Much to our surprise, we discover that this oft deployed adversarial augmentation technique does not actually result in “flatter” loss-landscapes, which requires rethinking adversarial training generalization, and the relationship between generalization and loss landscapes geometries. |
| Tasks | Data Augmentation |
| Published | 2019-07-22 |
| URL | https://arxiv.org/abs/1907.09061v1 |
| https://arxiv.org/pdf/1907.09061v1.pdf | |
| PWC | https://paperswithcode.com/paper/understanding-adversarial-robustness-through |
| Repo | |
| Framework | |
HeartFit: An Accurate Platform for Heart Murmur Diagnosis Utilizing Deep Learning
| Title | HeartFit: An Accurate Platform for Heart Murmur Diagnosis Utilizing Deep Learning |
| Authors | Ankit Gupta, George Tang, Sylesh Suresh |
| Abstract | Cardiovascular disease (CD) is the number one leading cause of death worldwide, accounting for more than 17 million deaths in 2015. Critical indicators of CD include heart murmurs, intense sounds emitted by the heart during periods of irregular blood flow. Current diagnosis of heart murmurs relies on echocardiography (ECHO), which costs thousands of dollars and medical professionals to analyze the results, making it very unsuitable for areas with inadequate medical facilities. Thus, there is a need for an accessible alternative. Based on a simple interface and deep learning, HeartFit allows users to administer diagnoses themselves. An inexpensive, custom designed stethoscope in conjunction with a mobile application allows users to record and upload audio of their heart to a database. Using a deep learning network architecture, the database classifies the audio and returns the diagnosis to the user. The model consists of a deep recurrent convolutional neural network trained on 300 prelabeled heartbeat audio samples. After the model was validated on a previously unseen set of 100 heartbeat audio samples, it achieved a f beta score of 0.9545 and an accuracy of 95.5 percent. This value exceeds that of clinical examination accuracy, which is around 83 percent to 91 percent and costs orders of magnitude less than ECHO, demonstrating the effectiveness of the HeartFit platform. Through the platform, users can obtain immediate, accurate diagnosis of heart murmurs without any professional medical assistance, revolutionizing how we combat CD. |
| Tasks | |
| Published | 2019-07-24 |
| URL | https://arxiv.org/abs/1907.11649v1 |
| https://arxiv.org/pdf/1907.11649v1.pdf | |
| PWC | https://paperswithcode.com/paper/heartfit-an-accurate-platform-for-heart |
| Repo | |
| Framework | |
