Paper Group ANR 382
Consider ethical and social challenges in smart grid research. Discussion of “The Blessings of Multiple Causes” by Wang and Blei. Single Image Deblurring and Camera Motion Estimation with Depth Map. Sentiment and Sarcasm Classification with Multitask Learning. Ensemble Teaching for Hybrid Label Propagation. Probabilistic sequential matrix factoriza …
Consider ethical and social challenges in smart grid research
| Title | Consider ethical and social challenges in smart grid research |
| Authors | Valentin Robu, David Flynn, Merlinda Andoni, Maizura Mokhtar |
| Abstract | Artificial Intelligence and Machine Learning are increasingly seen as key technologies for building more decentralised and resilient energy grids, but researchers must consider the ethical and social implications of their use |
| Tasks | |
| Published | 2019-11-26 |
| URL | https://arxiv.org/abs/1912.00783v1 |
| https://arxiv.org/pdf/1912.00783v1.pdf | |
| PWC | https://paperswithcode.com/paper/consider-ethical-and-social-challenges-in |
| Repo | |
| Framework | |
Discussion of “The Blessings of Multiple Causes” by Wang and Blei
| Title | Discussion of “The Blessings of Multiple Causes” by Wang and Blei |
| Authors | Kosuke Imai, Zhichao Jiang |
| Abstract | This commentary has two goals. We first critically review the deconfounder method and point out its advantages and limitations. We then briefly consider three possible ways to address some of the limitations of the deconfounder method. |
| Tasks | |
| Published | 2019-10-15 |
| URL | https://arxiv.org/abs/1910.06991v1 |
| https://arxiv.org/pdf/1910.06991v1.pdf | |
| PWC | https://paperswithcode.com/paper/discussion-of-the-blessings-of-multiple |
| Repo | |
| Framework | |
Single Image Deblurring and Camera Motion Estimation with Depth Map
| Title | Single Image Deblurring and Camera Motion Estimation with Depth Map |
| Authors | Liyuan Pan, Yuchao Dai, Miaomiao Liu |
| Abstract | Camera shake during exposure is a major problem in hand-held photography, as it causes image blur that destroys details in the captured images.~In the real world, such blur is mainly caused by both the camera motion and the complex scene structure.~While considerable existing approaches have been proposed based on various assumptions regarding the scene structure or the camera motion, few existing methods could handle the real 6 DoF camera motion.~In this paper, we propose to jointly estimate the 6 DoF camera motion and remove the non-uniform blur caused by camera motion by exploiting their underlying geometric relationships, with a single blurry image and its depth map (either direct depth measurements, or a learned depth map) as input.~We formulate our joint deblurring and 6 DoF camera motion estimation as an energy minimization problem which is solved in an alternative manner. Our model enables the recovery of the 6 DoF camera motion and the latent clean image, which could also achieve the goal of generating a sharp sequence from a single blurry image. Experiments on challenging real-world and synthetic datasets demonstrate that image blur from camera shake can be well addressed within our proposed framework. |
| Tasks | Deblurring, Motion Estimation |
| Published | 2019-03-01 |
| URL | http://arxiv.org/abs/1903.00231v1 |
| http://arxiv.org/pdf/1903.00231v1.pdf | |
| PWC | https://paperswithcode.com/paper/single-image-deblurring-and-camera-motion |
| Repo | |
| Framework | |
Sentiment and Sarcasm Classification with Multitask Learning
| Title | Sentiment and Sarcasm Classification with Multitask Learning |
| Authors | Navonil Majumder, Soujanya Poria, Haiyun Peng, Niyati Chhaya, Erik Cambria, Alexander Gelbukh |
| Abstract | Sentiment classification and sarcasm detection are both important natural language processing (NLP) tasks. Sentiment is always coupled with sarcasm where intensive emotion is expressed. Nevertheless, most literature considers them as two separate tasks. We argue that knowledge in sarcasm detection can also be beneficial to sentiment classification and vice versa. We show that these two tasks are correlated, and present a multi-task learning-based framework using a deep neural network that models this correlation to improve the performance of both tasks in a multi-task learning setting. Our method outperforms the state of the art by 3-4% in the benchmark dataset. |
| Tasks | Multi-Task Learning, Sarcasm Detection, Sentiment Analysis |
| Published | 2019-01-23 |
| URL | http://arxiv.org/abs/1901.08014v2 |
| http://arxiv.org/pdf/1901.08014v2.pdf | |
| PWC | https://paperswithcode.com/paper/sentiment-and-sarcasm-classification-with |
| Repo | |
| Framework | |
Ensemble Teaching for Hybrid Label Propagation
| Title | Ensemble Teaching for Hybrid Label Propagation |
| Authors | Chen Gong, Dacheng Tao, Xiaojun Chang, Jian Yang |
| Abstract | Label propagation aims to iteratively diffuse the label information from labeled examples to unlabeled examples over a similarity graph. Current label propagation algorithms cannot consistently yield satisfactory performance due to two reasons: one is the instability of single propagation method in dealing with various practical data, and the other one is the improper propagation sequence ignoring the labeling difficulties of different examples. To remedy above defects, this paper proposes a novel propagation algorithm called hybrid diffusion under ensemble teaching (HyDEnT). Specifically, HyDEnT integrates multiple propagation methods as base learners to fully exploit their individual wisdom, which helps HyDEnT to be stable and obtain consistent encouraging results. More importantly, HyDEnT conducts propagation under the guidance of an ensemble of teachers. That is to say, in every propagation round the simplest curriculum examples are wisely designated by a teaching algorithm, so that their labels can be reliably and accurately decided by the learners. To optimally choose these simplest examples, every teacher in the ensemble should comprehensively consider the examples’ difficulties from its own viewpoint, as well as the common knowledge shared by all the teachers. This is accomplished by a designed optimization problem, which can be efficiently solved via the block coordinate descent method. Thanks to the efforts of the teachers, all the unlabeled examples are logically propagated from simple to difficult, leading to better propagation quality of HyDEnT than the existing methods. |
| Tasks | |
| Published | 2019-04-08 |
| URL | http://arxiv.org/abs/1904.03828v1 |
| http://arxiv.org/pdf/1904.03828v1.pdf | |
| PWC | https://paperswithcode.com/paper/ensemble-teaching-for-hybrid-label |
| Repo | |
| Framework | |
Probabilistic sequential matrix factorization
| Title | Probabilistic sequential matrix factorization |
| Authors | Ömer Deniz Akyildiz, Theodoros Damoulas, Mark F. J. Steel |
| Abstract | We introduce the probabilistic sequential matrix factorization (PSMF) method for factorizing time-varying and non-stationary datasets consisting of high-dimensional time-series. In particular, we consider nonlinear-Gaussian state-space models in which sequential approximate inference results in the factorization of a data matrix into a dictionary and time-varying coefficients with (possibly nonlinear) Markovian dependencies. The assumed Markovian structure on the coefficients enables us to encode temporal dependencies into a low-dimensional feature space. The proposed inference method is solely based on an approximate extended Kalman filtering scheme which makes the resulting method particularly efficient. The PSMF can account for temporal nonlinearities and, more importantly, can be used to calibrate and estimate generic differentiable nonlinear subspace models. We show that the PSMF can be used in multiple contexts: modelling time series with a periodic subspace, robustifying changepoint detection methods, and imputing missing-data in high-dimensional time-series of air pollutants measured across London. |
| Tasks | Time Series |
| Published | 2019-10-09 |
| URL | https://arxiv.org/abs/1910.03906v1 |
| https://arxiv.org/pdf/1910.03906v1.pdf | |
| PWC | https://paperswithcode.com/paper/probabilistic-sequential-matrix-factorization |
| Repo | |
| Framework | |
ICDAR 2019 Competition on Scene Text Visual Question Answering
| Title | ICDAR 2019 Competition on Scene Text Visual Question Answering |
| Authors | Ali Furkan Biten, Rubèn Tito, Andres Mafla, Lluis Gomez, Marçal Rusiñol, Minesh Mathew, C. V. Jawahar, Ernest Valveny, Dimosthenis Karatzas |
| Abstract | This paper presents final results of ICDAR 2019 Scene Text Visual Question Answering competition (ST-VQA). ST-VQA introduces an important aspect that is not addressed by any Visual Question Answering system up to date, namely the incorporation of scene text to answer questions asked about an image. The competition introduces a new dataset comprising 23,038 images annotated with 31,791 question/answer pairs where the answer is always grounded on text instances present in the image. The images are taken from 7 different public computer vision datasets, covering a wide range of scenarios. The competition was structured in three tasks of increasing difficulty, that require reading the text in a scene and understanding it in the context of the scene, to correctly answer a given question. A novel evaluation metric is presented, which elegantly assesses both key capabilities expected from an optimal model: text recognition and image understanding. A detailed analysis of results from different participants is showcased, which provides insight into the current capabilities of VQA systems that can read. We firmly believe the dataset proposed in this challenge will be an important milestone to consider towards a path of more robust and general models that can exploit scene text to achieve holistic image understanding. |
| Tasks | Question Answering, Visual Question Answering |
| Published | 2019-06-30 |
| URL | https://arxiv.org/abs/1907.00490v1 |
| https://arxiv.org/pdf/1907.00490v1.pdf | |
| PWC | https://paperswithcode.com/paper/icdar-2019-competition-on-scene-text-visual |
| Repo | |
| Framework | |
Anti dependency distance minimization in short sequences. A graph theoretic approach
| Title | Anti dependency distance minimization in short sequences. A graph theoretic approach |
| Authors | Ramon Ferrer-i-Cancho, Carlos Gómez-Rodríguez |
| Abstract | Dependency distance minimization (DDm) is a word order principle favouring the placement of syntactically related words close to each other in sentences. Massive evidence of the principle has been reported for more than a decade with the help of syntactic dependency treebanks where long sentences abound. However, it has been predicted theoretically that the principle is more likely to be beaten in short sequences by the principle of surprisal minimization (predictability maximization). Here we introduce a simple binomial test to verify such a hypothesis. In short sentences, we find anti-DDm for some languages from different families. Our analysis of the syntactic dependency structures suggests that anti-DDm is produced by star trees. |
| Tasks | |
| Published | 2019-06-13 |
| URL | https://arxiv.org/abs/1906.05765v2 |
| https://arxiv.org/pdf/1906.05765v2.pdf | |
| PWC | https://paperswithcode.com/paper/anti-dependency-distance-minimization-in |
| Repo | |
| Framework | |
Stronger Convergence Results for Deep Residual Networks: Network Width Scales Linearly with Training Data Size
| Title | Stronger Convergence Results for Deep Residual Networks: Network Width Scales Linearly with Training Data Size |
| Authors | Talha Cihad Gulcu |
| Abstract | Deep neural networks are highly expressive machine learning models with the ability to interpolate arbitrary datasets. Deep nets are typically optimized via first-order methods and the optimization process crucially depends on the characteristics of the network as well as the dataset. This work sheds light on the relation between the network size and the properties of the dataset with an emphasis on deep residual networks (ResNets). Our contribution is that if the network Jacobian is full rank, gradient descent for the quadratic loss and smooth activation converges to the global minima even if the network width $m$ of the ResNet scales linearly with the sample size $n$, and independently from the network depth. To the best of our knowledge, this is the first work which provides a theoretical guarantee for the convergence of neural networks in the $m=\Omega(n)$ regime. |
| Tasks | |
| Published | 2019-11-11 |
| URL | https://arxiv.org/abs/1911.04351v1 |
| https://arxiv.org/pdf/1911.04351v1.pdf | |
| PWC | https://paperswithcode.com/paper/stronger-convergence-results-for-deep |
| Repo | |
| Framework | |
Directivity Modes of Earthquake Populations with Unsupervised Learning
| Title | Directivity Modes of Earthquake Populations with Unsupervised Learning |
| Authors | Zachary E. Ross, Daniel T. Trugman, Kamyar Azizzadenesheli, Anima Anandkumar |
| Abstract | We present a novel approach for resolving modes of rupture directivity in large populations of earthquakes. A seismic spectral decomposition technique is used to first produce relative measurements of radiated energy for earthquakes in a spatially-compact cluster. The azimuthal distribution of energy for each earthquake is then assumed to result from one of several distinct modes of rupture propagation. Rather than fitting a kinematic rupture model to determine the most likely mode of rupture propagation, we instead treat the modes as latent variables and learn them with a Gaussian mixture model. The mixture model simultaneously determines the number of events that best identify with each mode. The technique is demonstrated on four datasets in California with several thousand earthquakes. We show that the datasets naturally decompose into distinct rupture propagation modes that correspond to different rupture directions, and the fault plane is unambiguously identified for all cases. We find that these small earthquakes exhibit unilateral ruptures 53-74% of the time on average. The results provide important observational constraints on the physics of earthquakes and faults. |
| Tasks | |
| Published | 2019-06-30 |
| URL | https://arxiv.org/abs/1907.00496v1 |
| https://arxiv.org/pdf/1907.00496v1.pdf | |
| PWC | https://paperswithcode.com/paper/directivity-modes-of-earthquake-populations |
| Repo | |
| Framework | |
Data Science and Digital Systems: The 3Ds of Machine Learning Systems Design
| Title | Data Science and Digital Systems: The 3Ds of Machine Learning Systems Design |
| Authors | Neil D. Lawrence |
| Abstract | Machine learning solutions, in particular those based on deep learning methods, form an underpinning of the current revolution in “artificial intelligence” that has dominated popular press headlines and is having a significant influence on the wider tech agenda. Here we give an overview of the 3Ds of ML systems design: Data, Design and Deployment. By considering the 3Ds we can move towards \emph{data first} design. |
| Tasks | |
| Published | 2019-03-26 |
| URL | http://arxiv.org/abs/1903.11241v1 |
| http://arxiv.org/pdf/1903.11241v1.pdf | |
| PWC | https://paperswithcode.com/paper/data-science-and-digital-systems-the-3ds-of |
| Repo | |
| Framework | |
Semantic Deep Intermodal Feature Transfer: Transferring Feature Descriptors Between Imaging Modalities
| Title | Semantic Deep Intermodal Feature Transfer: Transferring Feature Descriptors Between Imaging Modalities |
| Authors | Sebastian P. Kleinschmidt, Bernardo Wagner |
| Abstract | Under difficult environmental conditions, the view of RGB cameras may be restricted by fog, dust or difficult lighting situations. Because thermal cameras visualize thermal radiation, they are not subject to the same limitations as RGB cameras. However, because RGB and thermal imaging differ significantly in appearance, common, state-of-the-art feature descriptors are unsuitable for intermodal feature matching between these imaging modalities. As a consequence, visual maps created with an RGB camera can currently not be used for localization using a thermal camera. In this paper, we introduce the Semantic Deep Intermodal Feature Transfer (Se-DIFT), an approach for transferring image feature descriptors from the visual to the thermal spectrum and vice versa. For this purpose, we predict potential feature appearance in varying imaging modalities using a deep convolutional encoder-decoder architecture in combination with a global feature vector. Since the representation of a thermal image is not only affected by features which can be extracted from an RGB image, we introduce the global feature vector which augments the auto encoder’s coding. The global feature vector contains additional information about the thermal history of a scene which is automatically extracted from external data sources. By augmenting the encoder’s coding, we decrease the L1 error of the prediction by more than 7% compared to the prediction of a traditional U-Net architecture. To evaluate our approach, we match image feature descriptors detected in RGB and thermal images using Se-DIFT. Subsequently, we make a competitive comparison on the intermodal transferability of SIFT, SURF, and ORB features using our approach. |
| Tasks | |
| Published | 2019-07-26 |
| URL | https://arxiv.org/abs/1907.11436v1 |
| https://arxiv.org/pdf/1907.11436v1.pdf | |
| PWC | https://paperswithcode.com/paper/semantic-deep-intermodal-feature-transfer |
| Repo | |
| Framework | |
A Hybrid Deep Learning Approach for Diagnosis of the Erythemato-Squamous Disease
| Title | A Hybrid Deep Learning Approach for Diagnosis of the Erythemato-Squamous Disease |
| Authors | Sayan Putatunda |
| Abstract | The diagnosis of the Erythemato-squamous disease (ESD) is accepted as a difficult problem in dermatology. ESD is a form of skin disease. It generally causes redness of the skin and also may cause loss of skin. They are generally due to genetic or environmental factors. ESD comprises six classes of skin conditions namely, pityriasis rubra pilaris, lichen planus, chronic dermatitis, psoriasis, seboreic dermatitis and pityriasis rosea. The automated diagnosis of ESD can help doctors and dermatologists in reducing the efforts from their end and in taking faster decisions for treatment. The literature is replete with works that used conventional machine learning methods for the diagnosis of ESD. However, there isn’t much instances of application of Deep learning for the diagnosis of ESD. In this paper, we propose a novel hybrid deep learning approach i.e. Derm2Vec for the diagnosis of the ESD. Derm2Vec is a hybrid deep learning model that consists of both Autoencoders and Deep Neural Networks. We also apply a conventional Deep Neural Network (DNN) for the classification of ESD. We apply both Derm2Vec and DNN along with other traditional machine learning methods on a real world dermatology dataset. The Derm2Vec method is found to be the best performer (when taking the prediction accuracy into account) followed by DNN and Extreme Gradient Boosting.The mean CV score of Derm2Vec, DNN and Extreme Gradient Boosting are 96.92 percent, 96.65 percent and 95.80 percent respectively. |
| Tasks | |
| Published | 2019-09-17 |
| URL | https://arxiv.org/abs/1909.07587v1 |
| https://arxiv.org/pdf/1909.07587v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-hybrid-deep-learning-approach-for-diagnosis |
| Repo | |
| Framework | |
LiDAR-assisted Large-scale Privacy Protection in Street-view Cycloramas
| Title | LiDAR-assisted Large-scale Privacy Protection in Street-view Cycloramas |
| Authors | Clint Sebastian, Bas Boom, Egor Bondarev, Peter H. N. de With |
| Abstract | Recently, privacy has a growing importance in several domains, especially in street-view images. The conventional way to achieve this is to automatically detect and blur sensitive information from these images. However, the processing cost of blurring increases with the ever-growing resolution of images. We propose a system that is cost-effective even after increasing the resolution by a factor of 2.5. The new system utilizes depth data obtained from LiDAR to significantly reduce the search space for detection, thereby reducing the processing cost. Besides this, we test several detectors after reducing the detection space and provide an alternative solution based on state-of-the-art deep learning detectors to the existing HoG-SVM-Deep system that is faster and has a higher performance. |
| Tasks | |
| Published | 2019-03-13 |
| URL | http://arxiv.org/abs/1903.05598v1 |
| http://arxiv.org/pdf/1903.05598v1.pdf | |
| PWC | https://paperswithcode.com/paper/lidar-assisted-large-scale-privacy-protection |
| Repo | |
| Framework | |
Emergent Behaviors from Folksonomy Driven Interactions
| Title | Emergent Behaviors from Folksonomy Driven Interactions |
| Authors | Massimiliano Dal Mas |
| Abstract | To reflect the evolving knowledge on the Web this paper considers ontologies based on folksonomies according to a new concept structure called “Folksodriven” to represent folksonomies. This paper describes a research program for studying Folksodriven tags interactions leading to Folksodriven cluster behavior. The goal of the research is to understand the type of simple local interactions which produce complex and purposive group behaviors on Folksodriven tags. We describe a synthetic, bottom-up approach to studying group behavior, consisting of designing and testing a variety of social interactions and cultural scenarios with Folksodriven tags. We propose a set of basic interactions which can be used to structure and simplify the process of both designing and analyzing emergent group behaviors. The presented behavior repertories was developed and tested on a folksonomy environment. |
| Tasks | |
| Published | 2019-12-31 |
| URL | https://arxiv.org/abs/2001.00569v1 |
| https://arxiv.org/pdf/2001.00569v1.pdf | |
| PWC | https://paperswithcode.com/paper/emergent-behaviors-from-folksonomy-driven |
| Repo | |
| Framework | |
