Paper Group ANR 180
Deep Spectral Reflectance and Illuminant Estimation from Self-Interreflections. Generative Models for Fast Calorimeter Simulation.LHCb case. Band Selection from Hyperspectral Images Using Attention-based Convolutional Neural Networks. Adapting predominant and novel sense discovery algorithms for identifying corpus-specific sense differences. Deep N …
Deep Spectral Reflectance and Illuminant Estimation from Self-Interreflections
| Title | Deep Spectral Reflectance and Illuminant Estimation from Self-Interreflections |
| Authors | Rada Deeb, Joost Van De Weijer, Damien Muselet, Mathieu Hebert, Alain Tremeau |
| Abstract | In this work, we propose a CNN-based approach to estimate the spectral reflectance of a surface and the spectral power distribution of the light from a single RGB image of a V-shaped surface. Interreflections happening in a concave surface lead to gradients of RGB values over its area. These gradients carry a lot of information concerning the physical properties of the surface and the illuminant. Our network is trained with only simulated data constructed using a physics-based interreflection model. Coupling interreflection effects with deep learning helps to retrieve the spectral reflectance under an unknown light and to estimate the spectral power distribution of this light as well. In addition, it is more robust to the presence of image noise than the classical approaches. Our results show that the proposed approach outperforms the state of the art learning-based approaches on simulated data. In addition, it gives better results on real data compared to other interreflection-based approaches. |
| Tasks | |
| Published | 2018-12-09 |
| URL | http://arxiv.org/abs/1812.03559v1 |
| http://arxiv.org/pdf/1812.03559v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-spectral-reflectance-and-illuminant |
| Repo | |
| Framework | |
Generative Models for Fast Calorimeter Simulation.LHCb case
| Title | Generative Models for Fast Calorimeter Simulation.LHCb case |
| Authors | Viktoria Chekalina, Elena Orlova, Fedor Ratnikov, Dmitry Ulyanov, Andrey Ustyuzhanin, Egor Zakharov |
| Abstract | Simulation is one of the key components in high energy physics. Historically it relies on the Monte Carlo methods which require a tremendous amount of computation resources. These methods may have difficulties with the expected High Luminosity Large Hadron Collider (HL LHC) need, so the experiment is in urgent need of new fast simulation techniques. We introduce a new Deep Learning framework based on Generative Adversarial Networks which can be faster than traditional simulation methods by 5 order of magnitude with reasonable simulation accuracy. This approach will allow physicists to produce a big enough amount of simulated data needed by the next HL LHC experiments using limited computing resources. |
| Tasks | |
| Published | 2018-12-04 |
| URL | http://arxiv.org/abs/1812.01319v2 |
| http://arxiv.org/pdf/1812.01319v2.pdf | |
| PWC | https://paperswithcode.com/paper/generative-models-for-fast-calorimeter |
| Repo | |
| Framework | |
Band Selection from Hyperspectral Images Using Attention-based Convolutional Neural Networks
| Title | Band Selection from Hyperspectral Images Using Attention-based Convolutional Neural Networks |
| Authors | Pablo Ribalta Lorenzo, Lukasz Tulczyjew, Michal Marcinkiewicz, Jakub Nalepa |
| Abstract | This paper introduces new attention-based convolutional neural networks for selecting bands from hyperspectral images. The proposed approach re-uses convolutional activations at different depths, identifying the most informative regions of the spectrum with the help of gating mechanisms. Our attention techniques are modular and easy to implement, and they can be seamlessly trained end-to-end using gradient descent. Our rigorous experiments showed that deep models equipped with the attention mechanism deliver high-quality classification, and repeatedly identify significant bands in the training data, permitting the creation of refined and extremely compact sets that retain the most meaningful features. |
| Tasks | |
| Published | 2018-10-24 |
| URL | https://arxiv.org/abs/1811.02667v3 |
| https://arxiv.org/pdf/1811.02667v3.pdf | |
| PWC | https://paperswithcode.com/paper/band-selection-from-hyperspectral-images |
| Repo | |
| Framework | |
Adapting predominant and novel sense discovery algorithms for identifying corpus-specific sense differences
| Title | Adapting predominant and novel sense discovery algorithms for identifying corpus-specific sense differences |
| Authors | Binny Mathew, Suman Kalyan Maity, Pratip Sarkar, Animesh Mukherjee, Pawan Goyal |
| Abstract | Word senses are not static and may have temporal, spatial or corpus-specific scopes. Identifying such scopes might benefit the existing WSD systems largely. In this paper, while studying corpus specific word senses, we adapt three existing predominant and novel-sense discovery algorithms to identify these corpus-specific senses. We make use of text data available in the form of millions of digitized books and newspaper archives as two different sources of corpora and propose automated methods to identify corpus-specific word senses at various time points. We conduct an extensive and thorough human judgment experiment to rigorously evaluate and compare the performance of these approaches. Post adaptation, the output of the three algorithms are in the same format and the accuracy results are also comparable, with roughly 45-60% of the reported corpus-specific senses being judged as genuine. |
| Tasks | |
| Published | 2018-02-01 |
| URL | http://arxiv.org/abs/1802.00231v1 |
| http://arxiv.org/pdf/1802.00231v1.pdf | |
| PWC | https://paperswithcode.com/paper/adapting-predominant-and-novel-sense |
| Repo | |
| Framework | |
Deep Neural Network Concepts for Background Subtraction: A Systematic Review and Comparative Evaluation
| Title | Deep Neural Network Concepts for Background Subtraction: A Systematic Review and Comparative Evaluation |
| Authors | Thierry Bouwmans, Sajid Javed, Maryam Sultana, Soon Ki Jung |
| Abstract | Conventional neural networks show a powerful framework for background subtraction in video acquired by static cameras. Indeed, the well-known SOBS method and its variants based on neural networks were the leader methods on the largescale CDnet 2012 dataset during a long time. Recently, convolutional neural networks which belong to deep learning methods were employed with success for background initialization, foreground detection and deep learned features. Currently, the top current background subtraction methods in CDnet 2014 are based on deep neural networks with a large gap of performance in comparison on the conventional unsupervised approaches based on multi-features or multi-cues strategies. Furthermore, a huge amount of papers was published since 2016 when Braham and Van Droogenbroeck published their first work on CNN applied to background subtraction providing a regular gain of performance. In this context, we provide the first review of deep neural network concepts in background subtraction for novices and experts in order to analyze this success and to provide further directions. For this, we first surveyed the methods used background initialization, background subtraction and deep learned features. Then, we discuss the adequacy of deep neural networks for background subtraction. Finally, experimental results are presented on the CDnet 2014 dataset. |
| Tasks | |
| Published | 2018-11-13 |
| URL | http://arxiv.org/abs/1811.05255v1 |
| http://arxiv.org/pdf/1811.05255v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-neural-network-concepts-for-background |
| Repo | |
| Framework | |
Deep learning with t-exponential Bayesian kitchen sinks
| Title | Deep learning with t-exponential Bayesian kitchen sinks |
| Authors | Harris Partaourides, Sotirios Chatzis |
| Abstract | Bayesian learning has been recently considered as an effective means of accounting for uncertainty in trained deep network parameters. This is of crucial importance when dealing with small or sparse training datasets. On the other hand, shallow models that compute weighted sums of their inputs, after passing them through a bank of arbitrary randomized nonlinearities, have been recently shown to enjoy good test error bounds that depend on the number of nonlinearities. Inspired from these advances, in this paper we examine novel deep network architectures, where each layer comprises a bank of arbitrary nonlinearities, linearly combined using multiple alternative sets of weights. We effect model training by means of approximate inference based on a t-divergence measure; this generalizes the Kullback-Leibler divergence in the context of the t-exponential family of distributions. We adopt the t-exponential family since it can more flexibly accommodate real-world data, that entail outliers and distributions with fat tails, compared to conventional Gaussian model assumptions. We extensively evaluate our approach using several challenging benchmarks, and provide comparative results to related state-of-the-art techniques. |
| Tasks | |
| Published | 2018-02-10 |
| URL | http://arxiv.org/abs/1802.03651v1 |
| http://arxiv.org/pdf/1802.03651v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-with-t-exponential-bayesian |
| Repo | |
| Framework | |
Navigating Diverse Data Science Learning: Critical Reflections Towards Future Practice
| Title | Navigating Diverse Data Science Learning: Critical Reflections Towards Future Practice |
| Authors | Yehia Elkhatib |
| Abstract | Data Science is currently a popular field of science attracting expertise from very diverse backgrounds. Current learning practices need to acknowledge this and adapt to it. This paper summarises some experiences relating to such learning approaches from teaching a postgraduate Data Science module, and draws some learned lessons that are of relevance to others teaching Data Science. |
| Tasks | |
| Published | 2018-07-05 |
| URL | http://arxiv.org/abs/1807.03750v1 |
| http://arxiv.org/pdf/1807.03750v1.pdf | |
| PWC | https://paperswithcode.com/paper/navigating-diverse-data-science-learning |
| Repo | |
| Framework | |
Can Autism be Catered with Artificial Intelligence-Assisted Intervention Technology? A Literature Review
| Title | Can Autism be Catered with Artificial Intelligence-Assisted Intervention Technology? A Literature Review |
| Authors | Muhammad Shoaib Jaliawala, Rizwan Ahmed Khan |
| Abstract | This article presents an extensive literature review of technology based intervention methodologies for individuals facing Autism Spectrum Disorder (ASD). Reviewed methodologies include: contemporary Computer Aided Systems (CAS), Computer Vision Assisted Technologies (CVAT) and Virtual Reality (VR) or Artificial Intelligence (AI)-Assisted interventions. The research over the past decade has provided enough demonstrations that individuals with ASD have a strong interest in technology based interventions, which are useful in both, clinical settings as well as at home and classrooms. Despite showing great promise, research in developing an advanced technology based intervention that is clinically quantitative for ASD is minimal. Moreover, the clinicians are generally not convinced about the potential of the technology based interventions due to non-empirical nature of published results. A major reason behind this lack of acceptability is that a vast majority of studies on distinct intervention methodologies do not follow any specific standard or research design. We conclude from our findings that there remains a gap between the research community of computer science, psychology and neuroscience to develop an AI assisted intervention technology for individuals suffering from ASD. Following the development of a standardized AI based intervention technology, a database needs to be developed, to devise effective AI algorithms. |
| Tasks | |
| Published | 2018-03-14 |
| URL | http://arxiv.org/abs/1803.05181v5 |
| http://arxiv.org/pdf/1803.05181v5.pdf | |
| PWC | https://paperswithcode.com/paper/can-autism-be-catered-with-artificial |
| Repo | |
| Framework | |
NAVREN-RL: Learning to fly in real environment via end-to-end deep reinforcement learning using monocular images
| Title | NAVREN-RL: Learning to fly in real environment via end-to-end deep reinforcement learning using monocular images |
| Authors | Malik Aqeel Anwar, Arijit Raychowdhury |
| Abstract | We present NAVREN-RL, an approach to NAVigate an unmanned aerial vehicle in an indoor Real ENvironment via end-to-end reinforcement learning RL. A suitable reward function is designed keeping in mind the cost and weight constraints for micro drone with minimum number of sensing modalities. Collection of small number of expert data and knowledge based data aggregation is integrated into the RL process to aid convergence. Experimentation is carried out on a Parrot AR drone in different indoor arenas and the results are compared with other baseline technologies. We demonstrate how the drone successfully avoids obstacles and navigates across different arenas. |
| Tasks | |
| Published | 2018-07-22 |
| URL | http://arxiv.org/abs/1807.08241v1 |
| http://arxiv.org/pdf/1807.08241v1.pdf | |
| PWC | https://paperswithcode.com/paper/navren-rl-learning-to-fly-in-real-environment |
| Repo | |
| Framework | |
A Deep Multi-task Learning Approach to Skin Lesion Classification
| Title | A Deep Multi-task Learning Approach to Skin Lesion Classification |
| Authors | Haofu Liao, Jiebo Luo |
| Abstract | Skin lesion identification is a key step toward dermatological diagnosis. When describing a skin lesion, it is very important to note its body site distribution as many skin diseases commonly affect particular parts of the body. To exploit the correlation between skin lesions and their body site distributions, in this study, we investigate the possibility of improving skin lesion classification using the additional context information provided by body location. Specifically, we build a deep multi-task learning (MTL) framework to jointly optimize skin lesion classification and body location classification (the latter is used as an inductive bias). Our MTL framework uses the state-of-the-art ImageNet pretrained model with specialized loss functions for the two related tasks. Our experiments show that the proposed MTL based method performs more robustly than its standalone (single-task) counterpart. |
| Tasks | Multi-Task Learning, Skin Lesion Classification, Skin Lesion Identification |
| Published | 2018-12-09 |
| URL | https://arxiv.org/abs/1812.03527v2 |
| https://arxiv.org/pdf/1812.03527v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-deep-multi-task-learning-approach-to-skin |
| Repo | |
| Framework | |
Bi-Adversarial Auto-Encoder for Zero-Shot Learning
| Title | Bi-Adversarial Auto-Encoder for Zero-Shot Learning |
| Authors | Yunlong Yu, Zhong Ji, Yanwei Pang, Jichang Guo, Zhongfei Zhang, Fei Wu |
| Abstract | Existing generative Zero-Shot Learning (ZSL) methods only consider the unidirectional alignment from the class semantics to the visual features while ignoring the alignment from the visual features to the class semantics, which fails to construct the visual-semantic interactions well. In this paper, we propose to synthesize visual features based on an auto-encoder framework paired with bi-adversarial networks respectively for visual and semantic modalities to reinforce the visual-semantic interactions with a bi-directional alignment, which ensures the synthesized visual features to fit the real visual distribution and to be highly related to the semantics. The encoder aims at synthesizing real-like visual features while the decoder forces both the real and the synthesized visual features to be more related to the class semantics. To further capture the discriminative information of the synthesized visual features, both the real and synthesized visual features are forced to be classified into the correct classes via a classification network. Experimental results on four benchmark datasets show that the proposed approach is particularly competitive on both the traditional ZSL and the generalized ZSL tasks. |
| Tasks | Zero-Shot Learning |
| Published | 2018-11-20 |
| URL | http://arxiv.org/abs/1811.08103v1 |
| http://arxiv.org/pdf/1811.08103v1.pdf | |
| PWC | https://paperswithcode.com/paper/bi-adversarial-auto-encoder-for-zero-shot |
| Repo | |
| Framework | |
Assessing Language Models with Scaling Properties
| Title | Assessing Language Models with Scaling Properties |
| Authors | Shuntaro Takahashi, Kumiko Tanaka-Ishii |
| Abstract | Language models have primarily been evaluated with perplexity. While perplexity quantifies the most comprehensible prediction performance, it does not provide qualitative information on the success or failure of models. Another approach for evaluating language models is thus proposed, using the scaling properties of natural language. Five such tests are considered, with the first two accounting for the vocabulary population and the other three for the long memory of natural language. The following models were evaluated with these tests: n-grams, probabilistic context-free grammar (PCFG), Simon and Pitman-Yor (PY) processes, hierarchical PY, and neural language models. Only the neural language models exhibit the long memory properties of natural language, but to a limited degree. The effectiveness of every test of these models is also discussed. |
| Tasks | |
| Published | 2018-04-24 |
| URL | http://arxiv.org/abs/1804.08881v1 |
| http://arxiv.org/pdf/1804.08881v1.pdf | |
| PWC | https://paperswithcode.com/paper/assessing-language-models-with-scaling |
| Repo | |
| Framework | |
Can we steal your vocal identity from the Internet?: Initial investigation of cloning Obama’s voice using GAN, WaveNet and low-quality found data
| Title | Can we steal your vocal identity from the Internet?: Initial investigation of cloning Obama’s voice using GAN, WaveNet and low-quality found data |
| Authors | Jaime Lorenzo-Trueba, Fuming Fang, Xin Wang, Isao Echizen, Junichi Yamagishi, Tomi Kinnunen |
| Abstract | Thanks to the growing availability of spoofing databases and rapid advances in using them, systems for detecting voice spoofing attacks are becoming more and more capable, and error rates close to zero are being reached for the ASVspoof2015 database. However, speech synthesis and voice conversion paradigms that are not considered in the ASVspoof2015 database are appearing. Such examples include direct waveform modelling and generative adversarial networks. We also need to investigate the feasibility of training spoofing systems using only low-quality found data. For that purpose, we developed a generative adversarial network-based speech enhancement system that improves the quality of speech data found in publicly available sources. Using the enhanced data, we trained state-of-the-art text-to-speech and voice conversion models and evaluated them in terms of perceptual speech quality and speaker similarity. The results show that the enhancement models significantly improved the SNR of low-quality degraded data found in publicly available sources and that they significantly improved the perceptual cleanliness of the source speech without significantly degrading the naturalness of the voice. However, the results also show limitations when generating speech with the low-quality found data. |
| Tasks | Speech Enhancement, Speech Synthesis, Voice Conversion |
| Published | 2018-03-02 |
| URL | http://arxiv.org/abs/1803.00860v1 |
| http://arxiv.org/pdf/1803.00860v1.pdf | |
| PWC | https://paperswithcode.com/paper/can-we-steal-your-vocal-identity-from-the |
| Repo | |
| Framework | |
Ballistocardiogram Signal Processing: A Literature Review
| Title | Ballistocardiogram Signal Processing: A Literature Review |
| Authors | Ibrahim Sadek |
| Abstract | Time-domain algorithms are focused on detecting local maxima or local minima using a moving window, and therefore finding the interval between the dominant J-peaks of ballistocardiogram (BCG) signal. However, this approach has many limitations due to the nonlinear and nonstationary behavior of the BCG signal. This is because the BCG signal does not display consistent J-peaks, which can usually be the case for overnight, in-home monitoring, particularly with frail elderly. Additionally, its accuracy will be undoubtedly affected by motion artifacts. Second, frequency-domain algorithms do not provide information about interbeat intervals. Nevertheless, they can provide information about heart rate variability. This is usually done by taking the fast Fourier transform or the inverse Fourier transform of the logarithm of the estimated spectrum, i.e., cepstrum of the signal using a sliding window. Thereafter, the dominant frequency is obtained in a particular frequency range. The limit of these algorithms is that the peak in the spectrum may get wider and multiple peaks may appear, which might cause a problem in measuring the vital signs. At last, the objective of wavelet-domain algorithms is to decompose the signal into different components, hence the component which shows an agreement with the vital signs can be selected i.e., the selected component contains only information about the heart cycles or respiratory cycles, respectively. An empirical mode decomposition is an alternative approach to wavelet decomposition, and it is also a very suitable approach to cope with nonlinear and nonstationary signals such as cardiorespiratory signals. Apart from the above-mentioned algorithms, machine learning approaches have been implemented for measuring heartbeats. However, manual labeling of training data is a restricting property. |
| Tasks | Heart Rate Variability |
| Published | 2018-07-03 |
| URL | http://arxiv.org/abs/1807.00951v1 |
| http://arxiv.org/pdf/1807.00951v1.pdf | |
| PWC | https://paperswithcode.com/paper/ballistocardiogram-signal-processing-a |
| Repo | |
| Framework | |
Lung and Pancreatic Tumor Characterization in the Deep Learning Era: Novel Supervised and Unsupervised Learning Approaches
| Title | Lung and Pancreatic Tumor Characterization in the Deep Learning Era: Novel Supervised and Unsupervised Learning Approaches |
| Authors | Sarfaraz Hussein, Pujan Kandel, Candice W. Bolan, Michael B. Wallace, Ulas Bagci |
| Abstract | Risk stratification (characterization) of tumors from radiology images can be more accurate and faster with computer-aided diagnosis (CAD) tools. Tumor characterization through such tools can also enable non-invasive cancer staging, prognosis, and foster personalized treatment planning as a part of precision medicine. In this study, we propose both supervised and unsupervised machine learning strategies to improve tumor characterization. Our first approach is based on supervised learning for which we demonstrate significant gains with deep learning algorithms, particularly by utilizing a 3D Convolutional Neural Network and Transfer Learning. Motivated by the radiologists’ interpretations of the scans, we then show how to incorporate task dependent feature representations into a CAD system via a graph-regularized sparse Multi-Task Learning (MTL) framework. In the second approach, we explore an unsupervised learning algorithm to address the limited availability of labeled training data, a common problem in medical imaging applications. Inspired by learning from label proportion (LLP) approaches in computer vision, we propose to use proportion-SVM for characterizing tumors. We also seek the answer to the fundamental question about the goodness of “deep features” for unsupervised tumor classification. We evaluate our proposed supervised and unsupervised learning algorithms on two different tumor diagnosis challenges: lung and pancreas with 1018 CT and 171 MRI scans, respectively, and obtain the state-of-the-art sensitivity and specificity results in both problems. |
| Tasks | Multi-Task Learning, Transfer Learning |
| Published | 2018-01-10 |
| URL | http://arxiv.org/abs/1801.03230v3 |
| http://arxiv.org/pdf/1801.03230v3.pdf | |
| PWC | https://paperswithcode.com/paper/lung-and-pancreatic-tumor-characterization-in |
| Repo | |
| Framework | |
