January 30, 2020

3225 words 16 mins read

Paper Group ANR 452

Spatial Sampling Network for Fast Scene Understanding. On complexity of branching droplets in electrical field. DARNet: Deep Active Ray Network for Building Segmentation. Improving NeuroEvolution Efficiency by Surrogate Model-based Optimization with Phenotypic Distance Kernels. RankML: a Meta Learning-Based Approach for Pre-Ranking Machine Learning …

Spatial Sampling Network for Fast Scene Understanding


Title	Spatial Sampling Network for Fast Scene Understanding
Authors	Davide Mazzini, Raimondo Schettini
Abstract	We propose a network architecture to perform efficient scene understanding. This work presents three main novelties: the first is an Improved Guided Upsampling Module that can replace in toto the decoder part in common semantic segmentation networks. Our second contribution is the introduction of a new module based on spatial sampling to perform Instance Segmentation. It provides a very fast instance segmentation, needing only thresholding as post-processing step at inference time. Finally, we propose a novel efficient network design that includes the new modules and test it against different datasets for outdoor scene understanding. To our knowledge, our network is one of the themost efficient architectures for scene understanding published to date, furthermore being 8.6% more accurate than the fastest competitor on semantic segmentation and almost five times faster than the most efficient network for instance segmentation.
Tasks	Instance Segmentation, Scene Understanding, Semantic Segmentation
Published	2019-05-22
URL	https://arxiv.org/abs/1905.09033v1
PDF	https://arxiv.org/pdf/1905.09033v1.pdf
PWC	https://paperswithcode.com/paper/spatial-sampling-network-for-fast-scene
Repo
Framework

On complexity of branching droplets in electrical field


Title	On complexity of branching droplets in electrical field
Authors	Mohammad Mahdi Dehshibi, Jitka Cejkova, Dominik Svara, Andrew Adamatzky
Abstract	Decanol droplets in a thin layer of sodium decanoate with sodium chloride exhibit bifurcation branching growth due to interplay between osmotic pressure, diffusion and surface tension. We aimed to evaluate if morphology of the branching droplets changes when the droplets are subject to electrical potential difference. We analysed graph-theoretic structure of the droplets and applied several complexity measures. We found that, in overall, the current increases complexity of the branching droplets in terms of number of connected components and nodes in their graph presentations, morphological complexity and compressibility.
Tasks
Published	2019-01-15
URL	http://arxiv.org/abs/1901.05043v1
PDF	http://arxiv.org/pdf/1901.05043v1.pdf
PWC	https://paperswithcode.com/paper/on-complexity-of-branching-droplets-in
Repo
Framework

DARNet: Deep Active Ray Network for Building Segmentation


Title	DARNet: Deep Active Ray Network for Building Segmentation
Authors	Dominic Cheng, Renjie Liao, Sanja Fidler, Raquel Urtasun
Abstract	In this paper, we propose a Deep Active Ray Network (DARNet) for automatic building segmentation. Taking an image as input, it first exploits a deep convolutional neural network (CNN) as the backbone to predict energy maps, which are further utilized to construct an energy function. A polygon-based contour is then evolved via minimizing the energy function, of which the minimum defines the final segmentation. Instead of parameterizing the contour using Euclidean coordinates, we adopt polar coordinates, i.e., rays, which not only prevents self-intersection but also simplifies the design of the energy function. Moreover, we propose a loss function that directly encourages the contours to match building boundaries. Our DARNet is trained end-to-end by back-propagating through the energy minimization and the backbone CNN, which makes the CNN adapt to the dynamics of the contour evolution. Experiments on three building instance segmentation datasets demonstrate our DARNet achieves either state-of-the-art or comparable performances to other competitors.
Tasks	Instance Segmentation, Semantic Segmentation
Published	2019-05-15
URL	https://arxiv.org/abs/1905.05889v1
PDF	https://arxiv.org/pdf/1905.05889v1.pdf
PWC	https://paperswithcode.com/paper/darnet-deep-active-ray-network-for-building
Repo
Framework

Improving NeuroEvolution Efficiency by Surrogate Model-based Optimization with Phenotypic Distance Kernels


Title	Improving NeuroEvolution Efficiency by Surrogate Model-based Optimization with Phenotypic Distance Kernels
Authors	Jörg Stork, Martin Zaefferer, Thomas Bartz-Beielstein
Abstract	In NeuroEvolution, the topologies of artificial neural networks are optimized with evolutionary algorithms to solve tasks in data regression, data classification, or reinforcement learning. One downside of NeuroEvolution is the large amount of necessary fitness evaluations, which might render it inefficient for tasks with expensive evaluations, such as real-time learning. For these expensive optimization tasks, surrogate model-based optimization is frequently applied as it features a good evaluation efficiency. While a combination of both procedures appears as a valuable solution, the definition of adequate distance measures for the surrogate modeling process is difficult. In this study, we will extend cartesian genetic programming of artificial neural networks by the use of surrogate model-based optimization. We propose different distance measures and test our algorithm on a replicable benchmark task. The results indicate that we can significantly increase the evaluation efficiency and that a phenotypic distance, which is based on the behavior of the associated neural networks, is most promising.
Tasks
Published	2019-02-09
URL	http://arxiv.org/abs/1902.03419v1
PDF	http://arxiv.org/pdf/1902.03419v1.pdf
PWC	https://paperswithcode.com/paper/improving-neuroevolution-efficiency-by
Repo
Framework

RankML: a Meta Learning-Based Approach for Pre-Ranking Machine Learning Pipelines


Title	RankML: a Meta Learning-Based Approach for Pre-Ranking Machine Learning Pipelines
Authors	Doron Laadan, Roman Vainshtein, Yarden Curiel, Gilad Katz, Lior Rokach
Abstract	The explosion of digital data has created multiple opportunities for organizations and individuals to leverage machine learning (ML) to transform the way they operate. However, the shortage of experts in the field of machine learning – data scientists – is often a setback to the use of ML. In an attempt to alleviate this shortage, multiple approaches for the automation of machine learning have been proposed in recent years. While these approaches are effective, they often require a great deal of time and computing resources. In this study, we propose RankML, a meta-learning based approach for predicting the performance of whole machine learning pipelines. Given a previously-unseen dataset, a performance metric, and a set of candidate pipelines, RankML immediately produces a ranked list of all pipelines based on their predicted performance. Extensive evaluation on 244 datasets, both in regression and classification tasks, shows that our approach either outperforms or is comparable to state-of-the-art, computationally heavy approaches while requiring a fraction of the time and computational cost.
Tasks	Meta-Learning
Published	2019-10-31
URL	https://arxiv.org/abs/1911.00108v2
PDF	https://arxiv.org/pdf/1911.00108v2.pdf
PWC	https://paperswithcode.com/paper/rankml-a-meta-learning-based-approach-for-pre
Repo
Framework

A formal approach for customization of schema.org based on SHACL


Title	A formal approach for customization of schema.org based on SHACL
Authors	Umutcan Şimşek, Kevin Angele, Elias Kärle, Oleksandra Panasiuk, Dieter Fensel
Abstract	Schema.org is a widely adopted vocabulary for semantic annotation of content and data. However, its generic nature makes it complicated for data publishers to pick right types and properties for a specific domain and task. In this paper we propose a formal approach, a domain specification process that generates domain specific patterns by applying operators implemented in SHACL to the schema.org vocabulary. These patterns can support knowledge generation and assessment processes for specific domains and tasks. We demonstrated our approach with use cases in tourism domain.
Tasks
Published	2019-06-15
URL	https://arxiv.org/abs/1906.06492v1
PDF	https://arxiv.org/pdf/1906.06492v1.pdf
PWC	https://paperswithcode.com/paper/a-formal-approach-for-customization-of
Repo
Framework

A General Optimization Framework for Dynamic Time Warping


Title	A General Optimization Framework for Dynamic Time Warping
Authors	Dave Deriso, Stephen Boyd
Abstract	The goal of dynamic time warping is to transform or warp time in order to approximately align two signals together. We pose the choice of warping function as an optimization problem with several terms in the objective. The first term measures the misalignment of the time-warped signals. Two additional regularization terms penalize the cumulative warping and the instantaneous rate of time warping; constraints on the warping can be imposed by assigning the value +inf to the regularization terms. Different choices of the three objective terms yield different time warping functions that trade off signal fit or alignment and properties of the warping function. The optimization problem we formulate is a classical optimal control problem, with initial and terminal constraints, and a state dimension of one. We describe an effective general method that minimizes the objective by discretizing the values of the original and warped time, and using standard dynamic programming to compute the (globally) optimal warping function with the discretized values. Iterated refinement of this scheme yields a high accuracy warping function in just a few iterations. Our method is implemented as an open source Python package GDTW.
Tasks
Published	2019-05-30
URL	https://arxiv.org/abs/1905.12893v2
PDF	https://arxiv.org/pdf/1905.12893v2.pdf
PWC	https://paperswithcode.com/paper/a-general-optimization-framework-for-dynamic
Repo
Framework

On the Morality of Artificial Intelligence


Title	On the Morality of Artificial Intelligence
Authors	Alexandra Luccioni, Yoshua Bengio
Abstract	Much of the existing research on the social and ethical impact of Artificial Intelligence has been focused on defining ethical principles and guidelines surrounding Machine Learning (ML) and other Artificial Intelligence (AI) algorithms [IEEE, 2017, Jobin et al., 2019]. While this is extremely useful for helping define the appropriate social norms of AI, we believe that it is equally important to discuss both the potential and risks of ML and to inspire the community to use ML for beneficial objectives. In the present article, which is specifically aimed at ML practitioners, we thus focus more on the latter, carrying out an overview of existing high-level ethical frameworks and guidelines, but above all proposing both conceptual and practical principles and guidelines for ML research and deployment, insisting on concrete actions that can be taken by practitioners to pursue a more ethical and moral practice of ML aimed at using AI for social good.
Tasks
Published	2019-12-26
URL	https://arxiv.org/abs/1912.11945v1
PDF	https://arxiv.org/pdf/1912.11945v1.pdf
PWC	https://paperswithcode.com/paper/on-the-morality-of-artificial-intelligence
Repo
Framework

Openbots


Title	Openbots
Authors	Dennis Assenmacher, Lena Adam, Lena Frischlich, Heike Trautmann, Christian Grimme
Abstract	Social bots have recently gained attention in the context of public opinion manipulation on social media platforms. While a lot of research effort has been put into the classification and detection of such (semi-)automated programs, it is still unclear how sophisticated those bots actually are, which platforms they target, and where they originate from. To answer these questions, we gathered repository data from open source collaboration platforms to identify the status-quo as well as trends of publicly available bot code. Our findings indicate that most of the code on collaboration platforms is of supportive nature and provides modules of automation instead of fully fledged social bot programs. Hence, the cost (in terms of additional programming effort) for building social bots with the goal of topic-specific manipulation is higher than assumed and that methods in context of machine- or deep-learning currently only play a minor role. However, our approach can be applied as multifaceted knowledge discovery framework to monitor trends in public bot code evolution to detect new developments and streams.
Tasks
Published	2019-02-14
URL	http://arxiv.org/abs/1902.06691v2
PDF	http://arxiv.org/pdf/1902.06691v2.pdf
PWC	https://paperswithcode.com/paper/openbots
Repo
Framework

Multiplierless and Sparse Machine Learning based on Margin Propagation Networks


Title	Multiplierless and Sparse Machine Learning based on Margin Propagation Networks
Authors	Nazreen P. M., Shantanu Chakrabartty, Chetan Singh Thakur
Abstract	The new generation of machine learning processors have evolved from multi-core and parallel architectures (for example graphical processing units) that were designed to efficiently implement matrix-vector-multiplications (MVMs). This is because at the fundamental level, neural network and machine learning operations extensively use MVM operations and hardware compilers exploit the inherent parallelism in MVM operations to achieve hardware acceleration on GPUs, TPUs and FPGAs. A natural question to ask is whether MVM operations are even necessary to implement ML algorithms and whether simpler hardware primitives can be used to implement an ultra-energy-efficient ML processor/architecture. In this paper we propose an alternate hardware-software codesign of ML and neural network architectures where instead of using MVM operations and non-linear activation functions, the architecture only uses simple addition and thresholding operations to implement inference and learning. At the core of the proposed approach is margin-propagation based computation that maps multiplications into additions and additions into a dynamic rectifying-linear-unit (ReLU) operations. This mapping results in significant improvement in computational and hence energy cost. The training of a margin-propagation (MP) network involves optimizing an $L_1$ cost function, which in conjunction with ReLU operations leads to network sparsity and weight updates using only Boolean predicates. In this paper, we show how the MP network formulation can be applied for designing linear classifiers, multi-layer perceptrons and for designing support vector networks.
Tasks
Published	2019-10-05
URL	https://arxiv.org/abs/1910.02304v1
PDF	https://arxiv.org/pdf/1910.02304v1.pdf
PWC	https://paperswithcode.com/paper/multiplierless-and-sparse-machine-learning
Repo
Framework

ClusterFit: Improving Generalization of Visual Representations


Title	ClusterFit: Improving Generalization of Visual Representations
Authors	Xueting Yan, Ishan Misra, Abhinav Gupta, Deepti Ghadiyaram, Dhruv Mahajan
Abstract	Pre-training convolutional neural networks with weakly-supervised and self-supervised strategies is becoming increasingly popular for several computer vision tasks. However, due to the lack of strong discriminative signals, these learned representations may overfit to the pre-training objective (e.g., hashtag prediction) and not generalize well to downstream tasks. In this work, we present a simple strategy - ClusterFit (CF) to improve the robustness of the visual representations learned during pre-training. Given a dataset, we (a) cluster its features extracted from a pre-trained network using k-means and (b) re-train a new network from scratch on this dataset using cluster assignments as pseudo-labels. We empirically show that clustering helps reduce the pre-training task-specific information from the extracted features thereby minimizing overfitting to the same. Our approach is extensible to different pre-training frameworks – weak- and self-supervised, modalities – images and videos, and pre-training tasks – object and action classification. Through extensive transfer learning experiments on 11 different target datasets of varied vocabularies and granularities, we show that ClusterFit significantly improves the representation quality compared to the state-of-the-art large-scale (millions / billions) weakly-supervised image and video models and self-supervised image models.
Tasks	Action Classification, Transfer Learning
Published	2019-12-06
URL	https://arxiv.org/abs/1912.03330v1
PDF	https://arxiv.org/pdf/1912.03330v1.pdf
PWC	https://paperswithcode.com/paper/clusterfit-improving-generalization-of-visual
Repo
Framework

Spatiotemporal deep learning model for citywide air pollution interpolation and prediction


Title	Spatiotemporal deep learning model for citywide air pollution interpolation and prediction
Authors	Van-Duc Le, Tien-Cuong Bui, Sang Kyun Cha
Abstract	Recently, air pollution is one of the most concerns for big cities. Predicting air quality for any regions and at any time is a critical requirement of urban citizens. However, air pollution prediction for the whole city is a challenging problem. The reason is, there are many spatiotemporal factors affecting air pollution throughout the city. Collecting as many of them could help us to forecast air pollution better. In this research, we present many spatiotemporal datasets collected over Seoul city in Korea, which is currently much suffered by air pollution problem as well. These datasets include air pollution data, meteorological data, traffic volume, average driving speed, and air pollution indexes of external areas which are known to impact Seoul’s air pollution. To the best of our knowledge, traffic volume and average driving speed data are two new datasets in air pollution research. In addition, recent research in air pollution has tried to build models to interpolate and predict air pollution in the city. Nevertheless, they mostly focused on predicting air quality in discrete locations or used hand-crafted spatial and temporal features. In this paper, we propose the usage of Convolutional Long Short-Term Memory (ConvLSTM) model \cite{b16}, a combination of Convolutional Neural Networks and Long Short-Term Memory, which automatically manipulates both the spatial and temporal features of the data. Specially, we introduce how to transform the air pollution data into sequences of images which leverages the using of ConvLSTM model to interpolate and predict air quality for the entire city at the same time. We prove that our approach is suitable for spatiotemporal air pollution problems and also outperforms other related research.
Tasks	Air Pollution Prediction
Published	2019-11-29
URL	https://arxiv.org/abs/1911.12919v1
PDF	https://arxiv.org/pdf/1911.12919v1.pdf
PWC	https://paperswithcode.com/paper/spatiotemporal-deep-learning-model-for
Repo
Framework

Visual Relationship Detection with Low Rank Non-Negative Tensor Decomposition


Title	Visual Relationship Detection with Low Rank Non-Negative Tensor Decomposition
Authors	Mohammed Haroon Dupty, Zhen Zhang, Wee Sun Lee
Abstract	We address the problem of Visual Relationship Detection (VRD) which aims to describe the relationships between pairs of objects in the form of triplets of (subject, predicate, object). We observe that given a pair of bounding box proposals, objects often participate in multiple relations implying the distribution of triplets is multimodal. We leverage the strong correlations within triplets to learn the joint distribution of triplet variables conditioned on the image and the bounding box proposals, doing away with the hitherto used independent distribution of triplets. To make learning the triplet joint distribution feasible, we introduce a novel technique of learning conditional triplet distributions in the form of their normalized low rank non-negative tensor decompositions. Normalized tensor decompositions take form of mixture distributions of discrete variables and thus are able to capture multimodality. This allows us to efficiently learn higher order discrete multimodal distributions and at the same time keep the parameter size manageable. We further model the probability of selecting an object proposal pair and include a relation triplet prior in our model. We show that each part of the model improves performance and the combination outperforms state-of-the-art score on the Visual Genome (VG) and Visual Relationship Detection (VRD) datasets.
Tasks
Published	2019-11-22
URL	https://arxiv.org/abs/1911.09895v1
PDF	https://arxiv.org/pdf/1911.09895v1.pdf
PWC	https://paperswithcode.com/paper/visual-relationship-detection-with-low-rank
Repo
Framework

Next Generation Radiogenomics Sequencing for Prediction of EGFR and KRAS Mutation Status in NSCLC Patients Using Multimodal Imaging and Machine Learning Approaches


Title	Next Generation Radiogenomics Sequencing for Prediction of EGFR and KRAS Mutation Status in NSCLC Patients Using Multimodal Imaging and Machine Learning Approaches
Authors	Isaac Shiri, Hassan Maleki, Ghasem Hajianfar, Hamid Abdollahi, Saeed Ashrafinia, Mathieu Hatt, Mehrdad Oveisi, Arman Rahmim
Abstract	Aim: In the present work, we aimed to evaluate a comprehensive radiomics framework that enabled prediction of EGFR and KRAS mutation status in NSCLC cancer patients based on PET and CT multi-modalities radiomic features and machine learning (ML) algorithms. Methods: Our study involved 211 NSCLC cancer patient with PET and CTD images. More than twenty thousand radiomic features from different image-feature sets were extracted Feature value was normalized to obtain Z-scores, followed by student t-test students for comparison, high correlated features were eliminated and the False discovery rate (FDR) correction were performed Six feature selection methods and twelve classifiers were used to predict gene status in patient and model evaluation was reported on independent validation sets (68 patients). Results: The best predictive power of conventional PET parameters was achieved by SUVpeak (AUC: 0.69, P-value = 0.0002) and MTV (AUC: 0.55, P-value = 0.0011) for EGFR and KRAS, respectively. Univariate analysis of radiomics features improved prediction power up to AUC: 75 (q-value: 0.003, Short Run Emphasis feature of GLRLM from LOG preprocessed image of PET with sigma value 1.5) and AUC: 0.71 (q-value 0.00005, The Large Dependence Low Gray Level Emphasis from GLDM in LOG preprocessed image of CTD sigma value 5) for EGFR and KRAS, respectively. Furthermore, the machine learning algorithm improved the perdition power up to AUC: 0.82 for EGFR (LOG preprocessed of PET image set with sigma 3 with VT feature selector and SGD classifier) and AUC: 0.83 for KRAS (CT image set with sigma 3.5 with SM feature selector and SGD classifier). Conclusion: We demonstrated that radiomic features extracted from different image-feature sets could be used for EGFR and KRAS mutation status prediction in NSCLC patients, and showed that they have more predictive power than conventional imaging parameters.
Tasks	Feature Selection
Published	2019-07-03
URL	https://arxiv.org/abs/1907.02121v1
PDF	https://arxiv.org/pdf/1907.02121v1.pdf
PWC	https://paperswithcode.com/paper/next-generation-radiogenomics-sequencing-for
Repo
Framework

Data ultrametricity and clusterability


Title	Data ultrametricity and clusterability
Authors	Dan Simovici, Kaixun Hua
Abstract	The increasing needs of clustering massive datasets and the high cost of running clustering algorithms poses difficult problems for users. In this context it is important to determine if a data set is clusterable, that is, it may be partitioned efficiently into well-differentiated groups containing similar objects. We approach data clusterability from an ultrametric-based perspective. A novel approach to determine the ultrametricity of a dataset is proposed via a special type of matrix product, which allows us to evaluate the clusterability of the dataset. Furthermore, we show that by applying our technique to a dissimilarity space will generate the sub-dominant ultrametric of the dissimilarity.
Tasks
Published	2019-08-28
URL	https://arxiv.org/abs/1908.10833v1
PDF	https://arxiv.org/pdf/1908.10833v1.pdf
PWC	https://paperswithcode.com/paper/data-ultrametricity-and-clusterability
Repo
Framework