January 28, 2020

3565 words 17 mins read

Paper Group ANR 856

Interactive Open-Ended Learning for 3D Object Recognition. An Entropy-based Variable Feature Weighted Fuzzy k-Means Algorithm for High Dimensional Data. Class-specific Anchoring Proposal for 3D Object Recognition in LIDAR and RGB Images. Benchmarking Minimax Linkage. Supplementary material for Uncorrected least-squares temporal difference with lamb …

Interactive Open-Ended Learning for 3D Object Recognition


Title	Interactive Open-Ended Learning for 3D Object Recognition
Authors	S. Hamidreza Kasaei
Abstract	The thesis contributes in several important ways to the research area of 3D object category learning and recognition. To cope with the mentioned limitations, we look at human cognition, in particular at the fact that human beings learn to recognize object categories ceaselessly over time. This ability to refine knowledge from the set of accumulated experiences facilitates the adaptation to new environments. Inspired by this capability, we seek to create a cognitive object perception and perceptual learning architecture that can learn 3D object categories in an open-ended fashion. In this context, ``open-ended’’ implies that the set of categories to be learned is not known in advance, and the training instances are extracted from actual experiences of a robot, and thus become gradually available, rather than being available since the beginning of the learning process. In particular, this architecture provides perception capabilities that will allow robots to incrementally learn object categories from the set of accumulated experiences and reason about how to perform complex tasks. This framework integrates detection, tracking, teaching, learning, and recognition of objects. An extensive set of systematic experiments, in multiple experimental settings, was carried out to thoroughly evaluate the described learning approaches. Experimental results show that the proposed system is able to interact with human users, learn new object categories over time, as well as perform complex tasks. The contributions presented in this thesis have been fully implemented and evaluated on different standard object and scene datasets and empirically evaluated on different robotic platforms. \|
Tasks	3D Object Recognition, Object Recognition
Published	2019-12-19
URL	https://arxiv.org/abs/1912.09539v1
PDF	https://arxiv.org/pdf/1912.09539v1.pdf
PWC	https://paperswithcode.com/paper/interactive-open-ended-learning-for-3d-object
Repo
Framework

An Entropy-based Variable Feature Weighted Fuzzy k-Means Algorithm for High Dimensional Data


Title	An Entropy-based Variable Feature Weighted Fuzzy k-Means Algorithm for High Dimensional Data
Authors	Vikas Singh, Nishchal K. Verma
Abstract	This paper presents a new fuzzy k-means algorithm for the clustering of high dimensional data in various subspaces. Since, In the case of high dimensional data, some features might be irrelevant and relevant but may have different significance in the clustering. For a better clustering, it is crucial to incorporate the contribution of these features in the clustering process. To combine these features, in this paper, we have proposed a new fuzzy k-means clustering algorithm in which the objective function of the fuzzy k-means is modified using two different entropy term. The first entropy term helps to minimize the within-cluster dispersion and maximize the negative entropy to determine clusters to contribute to the association of data points. The second entropy term helps to control the weight of the features because different features have different contributing weights in the clustering process for obtaining the better partition of the data. The efficacy of the proposed method is presented in terms of various clustering measures on multiple datasets and compared with various state-of-the-art methods.
Tasks
Published	2019-12-24
URL	https://arxiv.org/abs/1912.11209v1
PDF	https://arxiv.org/pdf/1912.11209v1.pdf
PWC	https://paperswithcode.com/paper/an-entropy-based-variable-feature-weighted
Repo
Framework

Class-specific Anchoring Proposal for 3D Object Recognition in LIDAR and RGB Images


Title	Class-specific Anchoring Proposal for 3D Object Recognition in LIDAR and RGB Images
Authors	Amir Hossein Raffiee, Humayun Irshad
Abstract	Detecting objects in a two-dimensional setting is often insufficient in the context of real-life applications where the surrounding environment needs to be accurately recognized and oriented in three-dimension (3D), such as in the case of autonomous driving vehicles. Therefore, accurately and efficiently detecting objects in the three-dimensional setting is becoming increasingly relevant to a wide range of industrial applications, and thus is progressively attracting the attention of researchers. Building systems to detect objects in 3D is a challenging task though, because it relies on the multi-modal fusion of data derived from different sources. In this paper, we study the effects of anchoring using the current state-of-the-art 3D object detector and propose Class-specific Anchoring Proposal (CAP) strategy based on object sizes and aspect ratios based clustering of anchors. The proposed anchoring strategy significantly increased detection accuracy’s by 7.19%, 8.13% and 8.8% on Easy, Moderate and Hard setting of the pedestrian class, 2.19%, 2.17% and 1.27% on Easy, Moderate and Hard setting of the car class and 12.1% on Easy setting of cyclist class. We also show that the clustering in anchoring process also enhances the performance of the regional proposal network in proposing regions of interests significantly. Finally, we propose the best cluster numbers for each class of objects in KITTI dataset that improves the performance of detection model significantly.
Tasks	3D Object Recognition, Autonomous Driving, Object Recognition
Published	2019-07-22
URL	https://arxiv.org/abs/1907.09081v1
PDF	https://arxiv.org/pdf/1907.09081v1.pdf
PWC	https://paperswithcode.com/paper/class-specific-anchoring-proposal-for-3d
Repo
Framework

Benchmarking Minimax Linkage


Title	Benchmarking Minimax Linkage
Authors	Xiao Hui Tai, Kayla Frisoli
Abstract	Minimax linkage was first introduced by Ao et al. [3] in 2004, as an alternative to standard linkage methods used in hierarchical clustering. Minimax linkage relies on distances to a prototype for each cluster; this prototype can be thought of as a representative object in the cluster, hence improving the interpretability of clustering results. Bien and Tibshirani analyzed properties of this method in 2011 [2], popularizing the method within the statistics community. Additionally, they performed comparisons of minimax linkage to standard linkage methods, making use of five data sets and two different evaluation metrics (distance to prototype and misclassification rate). In an effort to expand upon their work and evaluate minimax linkage more comprehensively, our benchmark study focuses on thorough method evaluation via multiple performance metrics on several well-described data sets. We also make all code and data publicly available through an R package, for full reproducibility. Similarly to [2], we find that minimax linkage often produces the smallest maximum minimax radius of all linkage methods, meaning that minimax linkage produces clusters where objects in a cluster are tightly clustered around their prototype. This is true across a range of values for the total number of clusters (k). However, this is not always the case, and special attention should be paid to the case when k is the true known value. For true k, minimax linkage does not always perform the best in terms of all the evaluation metrics studied, including maximum minimax radius. This paper was motivated by the IFCS Cluster Benchmarking Task Force’s call for clustering benchmark studies and the white paper [5], which put forth guidelines and principles for comprehensive benchmarking in clustering. Our work is designed to be a neutral benchmark study of minimax linkage.
Tasks
Published	2019-06-07
URL	https://arxiv.org/abs/1906.03336v1
PDF	https://arxiv.org/pdf/1906.03336v1.pdf
PWC	https://paperswithcode.com/paper/benchmarking-minimax-linkage
Repo
Framework

Supplementary material for Uncorrected least-squares temporal difference with lambda-return


Title	Supplementary material for Uncorrected least-squares temporal difference with lambda-return
Authors	Takayuki Osogami
Abstract	Here, we provide a supplementary material for Takayuki Osogami, “Uncorrected least-squares temporal difference with lambda-return,” which appears in {\it Proceedings of the 34th AAAI Conference on Artificial Intelligence} (AAAI-20).
Tasks
Published	2019-11-14
URL	https://arxiv.org/abs/1911.06057v1
PDF	https://arxiv.org/pdf/1911.06057v1.pdf
PWC	https://paperswithcode.com/paper/supplementary-material-for-uncorrected-least
Repo
Framework

Segmentation-Aware and Adaptive Iris Recognition


Title	Segmentation-Aware and Adaptive Iris Recognition
Authors	Kuo Wang, Ajay Kumar
Abstract	Iris recognition has emerged as one of the most accurate and convenient biometric for the human identification and has been increasingly employed in a wide range of e-security applications. The quality of iris images acquired at-a-distance or under less constrained imaging environments is known to degrade the iris matching accuracy. The periocular information is inherently embedded in such iris images and can be exploited to assist in the iris recognition under such non-ideal scenarios. Our analysis of such iris templates also indicates significant degradation and reduction in the region of interest, where the iris recognition can benefit from a similarity distance that can consider importance of different binary bits, instead of the direct use of Hamming distance in the literature. Periocular information can be dynamically reinforced, by incorporating the differences in the effective area of available iris regions, for more accurate iris recognition. This paper presents such a segmentation-assisted adaptive framework for more accurate less-constrained iris recognition. The effectiveness of this framework is evaluated on three publicly available iris databases using within-dataset and cross-dataset performance evaluation and validates the merit of the proposed iris recognition framework.
Tasks	Iris Recognition
Published	2019-12-31
URL	https://arxiv.org/abs/2001.00989v1
PDF	https://arxiv.org/pdf/2001.00989v1.pdf
PWC	https://paperswithcode.com/paper/segmentation-aware-and-adaptive-iris
Repo
Framework

Learning to Optimize Domain Specific Normalization with Domain Augmentation for Domain Generalization


Title	Learning to Optimize Domain Specific Normalization with Domain Augmentation for Domain Generalization
Authors	Seonguk Seo, Yumin Suh, Dongwan Kim, Jongwoo Han, Bohyung Han
Abstract	We propose a simple but effective multi-source domain generalization technique based on deep neural networks by incorporating optimized normalization layers specific to individual domains. Our approach employs multiple normalization methods while learning a separate affine parameter per domain. For each domain, the activations are normalized by a weighted average of multiple normalization statistics. The normalization statistics are kept track of separately for each normalization type if necessary. Specifically, we employ batch and instance normalizations in our implementation and attempt to identify the best combination of two normalization methods in each domain and normalization layer. In addition, we augment new domains through the combinations of multiple existing domains to increase the diversity of source domains available during training. The optimized normalization layers and the domain augmentation are effective to enhance the generalizability of the learned model. We demonstrate the state-ofthe-art accuracy of our algorithm in the standard benchmark datasets.
Tasks	Domain Generalization
Published	2019-07-09
URL	https://arxiv.org/abs/1907.04275v2
PDF	https://arxiv.org/pdf/1907.04275v2.pdf
PWC	https://paperswithcode.com/paper/learning-to-optimize-domain-specific
Repo
Framework

NumNet: Machine Reading Comprehension with Numerical Reasoning


Title	NumNet: Machine Reading Comprehension with Numerical Reasoning
Authors	Qiu Ran, Yankai Lin, Peng Li, Jie Zhou, Zhiyuan Liu
Abstract	Numerical reasoning, such as addition, subtraction, sorting and counting is a critical skill in human’s reading comprehension, which has not been well considered in existing machine reading comprehension (MRC) systems. To address this issue, we propose a numerical MRC model named as NumNet, which utilizes a numerically-aware graph neural network to consider the comparing information and performs numerical reasoning over numbers in the question and passage. Our system achieves an EM-score of 64.56% on the DROP dataset, outperforming all existing machine reading comprehension models by considering the numerical relations among numbers.
Tasks	Machine Reading Comprehension, Reading Comprehension
Published	2019-10-15
URL	https://arxiv.org/abs/1910.06701v1
PDF	https://arxiv.org/pdf/1910.06701v1.pdf
PWC	https://paperswithcode.com/paper/numnet-machine-reading-comprehension-with
Repo
Framework

Neither Global Nor Local: A Hierarchical Robust Subspace Clustering For Image Data


Title	Neither Global Nor Local: A Hierarchical Robust Subspace Clustering For Image Data
Authors	Maryam Abdolali, Mohammad Rahmati
Abstract	In this paper, we consider the problem of subspace clustering in presence of contiguous noise, occlusion and disguise. We argue that self-expressive representation of data in current state-of-the-art approaches is severely sensitive to occlusions and complex real-world noises. To alleviate this problem, we propose a hierarchical framework that brings robustness of local patches-based representations and discriminant property of global representations together. This approach consists of 1) a top-down stage, in which the input data is subject to repeated division to smaller patches and 2) a bottom-up stage, in which the low rank embedding of local patches in field of view of a corresponding patch in upper level are merged on a Grassmann manifold. This summarized information provides two key information for the corresponding patch on the upper level: cannot-links and recommended-links. This information is employed for computing a self-expressive representation of each patch at upper levels using a weighted sparse group lasso optimization problem. Numerical results on several real data sets confirm the efficiency of our approach.
Tasks
Published	2019-05-17
URL	https://arxiv.org/abs/1905.07220v1
PDF	https://arxiv.org/pdf/1905.07220v1.pdf
PWC	https://paperswithcode.com/paper/neither-global-nor-local-a-hierarchical
Repo
Framework

Limitations of Assessing Active Learning Performance at Runtime


Title	Limitations of Assessing Active Learning Performance at Runtime
Authors	Daniel Kottke, Jim Schellinger, Denis Huseljic, Bernhard Sick
Abstract	Classification algorithms aim to predict an unknown label (e.g., a quality class) for a new instance (e.g., a product). Therefore, training samples (instances and labels) are used to deduct classification hypotheses. Often, it is relatively easy to capture instances but the acquisition of the corresponding labels remain difficult or expensive. Active learning algorithms select the most beneficial instances to be labeled to reduce cost. In research, this labeling procedure is simulated and therefore a ground truth is available. But during deployment, active learning is a one-shot problem and an evaluation set is not available. Hence, it is not possible to reliably estimate the performance of the classification system during learning and it is difficult to decide when the system fulfills the quality requirements (stopping criteria). In this article, we formalize the task and review existing strategies to assess the performance of an actively trained classifier during training. Furthermore, we identified three major challenges: 1)~to derive a performance distribution, 2)~to preserve representativeness of the labeled subset, and 3) to correct against sampling bias induced by an intelligent selection strategy. In a qualitative analysis, we evaluate different existing approaches and show that none of them reliably estimates active learning performance stating a major challenge for future research for such systems. All plots and experiments are provided in a Jupyter notebook that is available for download.
Tasks	Active Learning
Published	2019-01-29
URL	http://arxiv.org/abs/1901.10338v1
PDF	http://arxiv.org/pdf/1901.10338v1.pdf
PWC	https://paperswithcode.com/paper/limitations-of-assessing-active-learning
Repo
Framework

Ranking metrics on non-shuffled traffic


Title	Ranking metrics on non-shuffled traffic
Authors	Alexandre Gilotte
Abstract	Ranking metrics are a family of metrics largely used to evaluate recommender systems. However they typically suffer from the fact the reward is affected by the order in which recommended items are displayed to the user. A classical way to overcome this position bias is to uniformly shuffle a proportion of the recommendations, but this method may result in a bad user experience. It is nevertheless common to use a stochastic policy to generate the recommendations, and we suggest a new method to overcome the position bias, by leveraging the stochasticity of the policy used to collect the dataset.
Tasks	Recommendation Systems
Published	2019-09-17
URL	https://arxiv.org/abs/1909.07926v1
PDF	https://arxiv.org/pdf/1909.07926v1.pdf
PWC	https://paperswithcode.com/paper/ranking-metrics-on-non-shuffled-traffic
Repo
Framework

Multi-level Convolutional Autoencoder Networks for Parametric Prediction of Spatio-temporal Dynamics


Title	Multi-level Convolutional Autoencoder Networks for Parametric Prediction of Spatio-temporal Dynamics
Authors	Jiayang Xu, Karthik Duraisamy
Abstract	A data-driven framework is proposed for the predictive modeling of complex spatio-temporal dynamics, leveraging nested non-linear manifolds. Three levels of neural networks are used, with the goal of predicting the future state of a system of interest in a parametric setting. A convolutional autoencoder is used as the top level to encode the high dimensional input data along spatial dimensions into a sequence of latent variables. A temporal convolutional autoencoder serves as the second level, which further encodes the output sequence from the first level along the temporal dimension, and outputs a set of latent variables that encapsulate the spatio-temporal evolution of the dynamics. A fully connected network is used as the third level to learn the mapping between these latent variables and the global parameters from training data, and predict them for new parameters. For future state predictions, the second level uses a temporal convolutional network to predict subsequent steps of the output sequence from the top level. Latent variables at the bottom-most level are decoded to obtain the dynamics in physical space at new global parameters and/or at a future time. The framework is evaluated on a range of problems involving discontinuities, wave propagation, strong transients, and coherent structures. The sensitivity of the results to different modeling choices is assessed. The results suggest that given adequate data and careful training, effective data-driven predictive models can be constructed. Perspectives are provided on the present approach and its place in the landscape of model reduction.
Tasks
Published	2019-12-23
URL	https://arxiv.org/abs/1912.11114v1
PDF	https://arxiv.org/pdf/1912.11114v1.pdf
PWC	https://paperswithcode.com/paper/multi-level-convolutional-autoencoder
Repo
Framework

Cross-domain recommender system using Generalized Canonical Correlation Analysis


Title	Cross-domain recommender system using Generalized Canonical Correlation Analysis
Authors	Seyed Mohammad Hashemi, Mohammad Rahmati
Abstract	Recommender systems provide personalized recommendations to the users from a large number of possible options in online stores. Matrix factorization is a well-known and accurate collaborative filtering approach for recommender system, which suffers from cold-start problem for new users and items. Whenever a new user participate with the system there is not enough interactions with the system, therefore there are not enough ratings in the user-item matrix to learn the matrix factorization model. Using auxiliary data such as users demographic, ratings and reviews in relevant domains, is an effective solution to reduce the new user problem. In this paper, we used data of users from other domains and build a common space to represent the latent factors of users from different domains. In this representation we proposed an iterative method which applied MAX-VAR generalized canonical correlation analysis (GCCA) on users latent factors learned from matrix factorization on each domain. Also, to improve the capability of GCCA to learn latent factors for new users, we propose generalized canonical correlation analysis by inverse sum of selection matrices (GCCA-ISSM) approach, which provides better recommendations in cold-start scenarios. The proposed approach is extended using content-based features from topic modeling extracted from users reviews. We demonstrate the accuracy and effectiveness of the proposed approaches on cross-domain ratings predictions using comprehensive experiments on Amazon and MovieLens datasets.
Tasks	Recommendation Systems
Published	2019-09-15
URL	https://arxiv.org/abs/1909.12746v1
PDF	https://arxiv.org/pdf/1909.12746v1.pdf
PWC	https://paperswithcode.com/paper/cross-domain-recommender-system-using
Repo
Framework

Deep Collaborative Filtering with Multi-Aspect Information in Heterogeneous Networks


Title	Deep Collaborative Filtering with Multi-Aspect Information in Heterogeneous Networks
Authors	Chuan Shi, Xiaotian Han, Li Song, Xiao Wang, Senzhang Wang, Junping Du, Philip S. Yu
Abstract	Recently, recommender systems play a pivotal role in alleviating the problem of information overload. Latent factor models have been widely used for recommendation. Most existing latent factor models mainly utilize the interaction information between users and items, although some recently extended models utilize some auxiliary information to learn a unified latent factor for users and items. The unified latent factor only represents the characteristics of users and the properties of items from the aspect of purchase history. However, the characteristics of users and the properties of items may stem from different aspects, e.g., the brand-aspect and category-aspect of items. Moreover, the latent factor models usually use the shallow projection, which cannot capture the characteristics of users and items well. In this paper, we propose a Neural network based Aspect-level Collaborative Filtering model (NeuACF) to exploit different aspect latent factors. Through modelling the rich object properties and relations in recommender system as a heterogeneous information network, NeuACF first extracts different aspect-level similarity matrices of users and items respectively through different meta-paths, and then feeds an elaborately designed deep neural network with these matrices to learn aspect-level latent factors. Finally, the aspect-level latent factors are fused for the top-N recommendation. Moreover, to fuse information from different aspects more effectively, we further propose NeuACF++ to fuse aspect-level latent factors with self-attention mechanism. Extensive experiments on three real world datasets show that NeuACF and NeuACF++ significantly outperform both existing latent factor models and recent neural network models.
Tasks	Recommendation Systems
Published	2019-09-14
URL	https://arxiv.org/abs/1909.06627v1
PDF	https://arxiv.org/pdf/1909.06627v1.pdf
PWC	https://paperswithcode.com/paper/deep-collaborative-filtering-with-multi
Repo
Framework

Deep Learning for Multi-Messenger Astrophysics: A Gateway for Discovery in the Big Data Era


Title	Deep Learning for Multi-Messenger Astrophysics: A Gateway for Discovery in the Big Data Era
Authors	Gabrielle Allen, Igor Andreoni, Etienne Bachelet, G. Bruce Berriman, Federica B. Bianco, Rahul Biswas, Matias Carrasco Kind, Kyle Chard, Minsik Cho, Philip S. Cowperthwaite, Zachariah B. Etienne, Daniel George, Tom Gibbs, Matthew Graham, William Gropp, Anushri Gupta, Roland Haas, E. A. Huerta, Elise Jennings, Daniel S. Katz, Asad Khan, Volodymyr Kindratenko, William T. C. Kramer, Xin Liu, Ashish Mahabal, Kenton McHenry, J. M. Miller, M. S. Neubauer, Steve Oberlin, Alexander R. Olivas Jr, Shawn Rosofsky, Milton Ruiz, Aaron Saxton, Bernard Schutz, Alex Schwing, Ed Seidel, Stuart L. Shapiro, Hongyu Shen, Yue Shen, Brigitta M. Sipőcz, Lunan Sun, John Towns, Antonios Tsokaros, Wei Wei, Jack Wells, Timothy J. Williams, Jinjun Xiong, Zhizhen Zhao
Abstract	This report provides an overview of recent work that harnesses the Big Data Revolution and Large Scale Computing to address grand computational challenges in Multi-Messenger Astrophysics, with a particular emphasis on real-time discovery campaigns. Acknowledging the transdisciplinary nature of Multi-Messenger Astrophysics, this document has been prepared by members of the physics, astronomy, computer science, data science, software and cyberinfrastructure communities who attended the NSF-, DOE- and NVIDIA-funded “Deep Learning for Multi-Messenger Astrophysics: Real-time Discovery at Scale” workshop, hosted at the National Center for Supercomputing Applications, October 17-19, 2018. Highlights of this report include unanimous agreement that it is critical to accelerate the development and deployment of novel, signal-processing algorithms that use the synergy between artificial intelligence (AI) and high performance computing to maximize the potential for scientific discovery with Multi-Messenger Astrophysics. We discuss key aspects to realize this endeavor, namely (i) the design and exploitation of scalable and computationally efficient AI algorithms for Multi-Messenger Astrophysics; (ii) cyberinfrastructure requirements to numerically simulate astrophysical sources, and to process and interpret Multi-Messenger Astrophysics data; (iii) management of gravitational wave detections and triggers to enable electromagnetic and astro-particle follow-ups; (iv) a vision to harness future developments of machine and deep learning and cyberinfrastructure resources to cope with the scale of discovery in the Big Data Era; (v) and the need to build a community that brings domain experts together with data scientists on equal footing to maximize and accelerate discovery in the nascent field of Multi-Messenger Astrophysics.
Tasks
Published	2019-02-01
URL	http://arxiv.org/abs/1902.00522v1
PDF	http://arxiv.org/pdf/1902.00522v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-for-multi-messenger
Repo
Framework