January 29, 2020

2695 words 13 mins read

Paper Group ANR 719

Applications of Generative Adversarial Models in Visual Search Reformulation. Multimodal Abstractive Summarization for How2 Videos. Still no free lunches: the price to pay for tighter PAC-Bayes bounds. Vouw: Geometric Pattern Mining using the MDL Principle. Classification Accuracy Score for Conditional Generative Models. Eigenvalue and Generalized …

Applications of Generative Adversarial Models in Visual Search Reformulation


Title	Applications of Generative Adversarial Models in Visual Search Reformulation
Authors	Kyle Xiao, Houdong Hu, Yan Wang
Abstract	Query reformulation is the process by which a input search query is refined by the user to match documents outside the original top-n results. On average, roughly 50% of text search queries involve some form of reformulation, and term suggestion tools are used 35% of the time when offered to users. As prevalent as text search queries are, however, such a feature has yet to be explored at scale for visual search. This is because reformulation for images presents a novel challenge to seamlessly transform visual features to match user intent within the context of a typical user session. In this paper, we present methods of semantically transforming visual queries, such as utilizing operations in the latent space of a generative adversarial model for the scenarios of fashion and product search.
Tasks
Published	2019-10-28
URL	https://arxiv.org/abs/1910.12460v1
PDF	https://arxiv.org/pdf/1910.12460v1.pdf
PWC	https://paperswithcode.com/paper/applications-of-generative-adversarial-models
Repo
Framework

Multimodal Abstractive Summarization for How2 Videos


Title	Multimodal Abstractive Summarization for How2 Videos
Authors	Shruti Palaskar, Jindrich Libovický, Spandana Gella, Florian Metze
Abstract	In this paper, we study abstractive summarization for open-domain videos. Unlike the traditional text news summarization, the goal is less to “compress” text information but rather to provide a fluent textual summary of information that has been collected and fused from different source modalities, in our case video and audio transcripts (or text). We show how a multi-source sequence-to-sequence model with hierarchical attention can integrate information from different modalities into a coherent output, compare various models trained with different modalities and present pilot experiments on the How2 corpus of instructional videos. We also propose a new evaluation metric (Content F1) for abstractive summarization task that measures semantic adequacy rather than fluency of the summaries, which is covered by metrics like ROUGE and BLEU.
Tasks	Abstractive Text Summarization
Published	2019-06-19
URL	https://arxiv.org/abs/1906.07901v1
PDF	https://arxiv.org/pdf/1906.07901v1.pdf
PWC	https://paperswithcode.com/paper/multimodal-abstractive-summarization-for-how2
Repo
Framework

Still no free lunches: the price to pay for tighter PAC-Bayes bounds


Title	Still no free lunches: the price to pay for tighter PAC-Bayes bounds
Authors	Benjamin Guedj, Louis Pujol
Abstract	“No free lunch” results state the impossibility of obtaining meaningful bounds on the error of a learning algorithm without prior assumptions and modelling. Some models are expensive (strong assumptions, such as as subgaussian tails), others are cheap (simply finite variance). As it is well known, the more you pay, the more you get: in other words, the most expensive models yield the more interesting bounds. Recent advances in robust statistics have investigated procedures to obtain tight bounds while keeping the cost minimal. The present paper explores and exhibits what the limits are for obtaining tight PAC-Bayes bounds in a robust setting for cheap models, addressing the question: is PAC-Bayes good value for money?
Tasks
Published	2019-10-10
URL	https://arxiv.org/abs/1910.04460v1
PDF	https://arxiv.org/pdf/1910.04460v1.pdf
PWC	https://paperswithcode.com/paper/still-no-free-lunches-the-price-to-pay-for
Repo
Framework

Vouw: Geometric Pattern Mining using the MDL Principle


Title	Vouw: Geometric Pattern Mining using the MDL Principle
Authors	Micky Faas, Matthijs van Leeuwen
Abstract	We introduce geometric pattern mining, the problem of finding recurring local structure in discrete, geometric matrices. It differs from existing pattern mining problems by identifying complex spatial relations between elements, resulting in arbitrarily shaped patterns. After we formalise this new type of pattern mining, we propose an approach to selecting a set of patterns using the Minimum Description Length principle. We demonstrate the potential of our approach by introducing Vouw, a heuristic algorithm for mining exact geometric patterns. We show that Vouw delivers high-quality results with a synthetic benchmark.
Tasks
Published	2019-11-21
URL	https://arxiv.org/abs/1911.09587v2
PDF	https://arxiv.org/pdf/1911.09587v2.pdf
PWC	https://paperswithcode.com/paper/vouw-geometric-pattern-mining-using-the-mdl
Repo
Framework

Classification Accuracy Score for Conditional Generative Models


Title	Classification Accuracy Score for Conditional Generative Models
Authors	Suman Ravuri, Oriol Vinyals
Abstract	Deep generative models (DGMs) of images are now sufficiently mature that they produce nearly photorealistic samples and obtain scores similar to the data distribution on heuristics such as Frechet Inception Distance (FID). These results, especially on large-scale datasets such as ImageNet, suggest that DGMs are learning the data distribution in a perceptually meaningful space and can be used in downstream tasks. To test this latter hypothesis, we use class-conditional generative models from a number of model classes—variational autoencoders, autoregressive models, and generative adversarial networks (GANs)—to infer the class labels of real data. We perform this inference by training an image classifier using only synthetic data and using the classifier to predict labels on real data. The performance on this task, which we call Classification Accuracy Score (CAS), reveals some surprising results not identified by traditional metrics and constitute our contributions. First, when using a state-of-the-art GAN (BigGAN-deep), Top-1 and Top-5 accuracy decrease by 27.9% and 41.6%, respectively, compared to the original data; and conditional generative models from other model classes, such as Vector-Quantized Variational Autoencoder-2 (VQ-VAE-2) and Hierarchical Autoregressive Models (HAMs), substantially outperform GANs on this benchmark. Second, CAS automatically surfaces particular classes for which generative models failed to capture the data distribution, and were previously unknown in the literature. Third, we find traditional GAN metrics such as Inception Score (IS) and FID neither predictive of CAS nor useful when evaluating non-GAN models. Furthermore, in order to facilitate better diagnoses of generative models, we open-source the proposed metric.
Tasks
Published	2019-05-26
URL	https://arxiv.org/abs/1905.10887v2
PDF	https://arxiv.org/pdf/1905.10887v2.pdf
PWC	https://paperswithcode.com/paper/classification-accuracy-score-for-conditional
Repo
Framework

Eigenvalue and Generalized Eigenvalue Problems: Tutorial


Title	Eigenvalue and Generalized Eigenvalue Problems: Tutorial
Authors	Benyamin Ghojogh, Fakhri Karray, Mark Crowley
Abstract	This paper is a tutorial for eigenvalue and generalized eigenvalue problems. We first introduce eigenvalue problem, eigen-decomposition (spectral decomposition), and generalized eigenvalue problem. Then, we mention the optimization problems which yield to the eigenvalue and generalized eigenvalue problems. We also provide examples from machine learning, including principal component analysis, kernel supervised principal component analysis, and Fisher discriminant analysis, which result in eigenvalue and generalized eigenvalue problems. Finally, we introduce the solutions to both eigenvalue and generalized eigenvalue problems.
Tasks
Published	2019-03-25
URL	http://arxiv.org/abs/1903.11240v1
PDF	http://arxiv.org/pdf/1903.11240v1.pdf
PWC	https://paperswithcode.com/paper/eigenvalue-and-generalized-eigenvalue
Repo
Framework

Spectral Metric for Dataset Complexity Assessment


Title	Spectral Metric for Dataset Complexity Assessment
Authors	Frederic Branchaud-Charron, Andrew Achkar, Pierre-Marc Jodoin
Abstract	In this paper, we propose a new measure to gauge the complexity of image classification problems. Given an annotated image dataset, our method computes a complexity measure called the cumulative spectral gradient (CSG) which strongly correlates with the test accuracy of convolutional neural networks (CNN). The CSG measure is derived from the probabilistic divergence between classes in a spectral clustering framework. We show that this metric correlates with the overall separability of the dataset and thus its inherent complexity. As will be shown, our metric can be used for dataset reduction, to assess which classes are more difficult to disentangle, and approximate the accuracy one could expect to get with a CNN. Results obtained on 11 datasets and three CNN models reveal that our method is more accurate and faster than previous complexity measures.
Tasks	Image Classification
Published	2019-05-17
URL	https://arxiv.org/abs/1905.07299v1
PDF	https://arxiv.org/pdf/1905.07299v1.pdf
PWC	https://paperswithcode.com/paper/spectral-metric-for-dataset-complexity
Repo
Framework

A New Approach for Topic Detection using Adaptive Neural Networks


Title	A New Approach for Topic Detection using Adaptive Neural Networks
Authors	Meriem Manai
Abstract	Topic detection becomes more important due to the increase of information electronically available and the necessity to process and filter it. In this context our master’s thesis work was carried out, where we proposed to present a new approach to the detection of topics called ClusART. Thus, we proposed a three-phase approach, namely : a first phase during which lexical preprocessing was conducted. A second phase during which the construction and generation of vectors representing the documents was carried out. A third phase which is itself composed of two steps. In the first step we used the FuzzyART algorithm for the training phase. In the second step we used a classifier using Paragraph Vector for the test phase. The comparative study of our approach on the 20 Newsgroups dataset showed that our approach is able to detect almost relevant topics.
Tasks
Published	2019-03-09
URL	http://arxiv.org/abs/1903.03775v1
PDF	http://arxiv.org/pdf/1903.03775v1.pdf
PWC	https://paperswithcode.com/paper/a-new-approach-for-topic-detection-using
Repo
Framework

Recurrent Value Functions


Title	Recurrent Value Functions
Authors	Pierre Thodoroff, Nishanth Anand, Lucas Caccia, Doina Precup, Joelle Pineau
Abstract	Despite recent successes in Reinforcement Learning, value-based methods often suffer from high variance hindering performance. In this paper, we illustrate this in a continuous control setting where state of the art methods perform poorly whenever sensor noise is introduced. To overcome this issue, we introduce Recurrent Value Functions (RVFs) as an alternative to estimate the value function of a state. We propose to estimate the value function of the current state using the value function of past states visited along the trajectory. Due to the nature of their formulation, RVFs have a natural way of learning an emphasis function that selectively emphasizes important states. First, we establish RVF’s asymptotic convergence properties in tabular settings. We then demonstrate their robustness on a partially observable domain and continuous control tasks. Finally, we provide a qualitative interpretation of the learned emphasis function.
Tasks	Continuous Control
Published	2019-05-23
URL	https://arxiv.org/abs/1905.09562v1
PDF	https://arxiv.org/pdf/1905.09562v1.pdf
PWC	https://paperswithcode.com/paper/recurrent-value-functions
Repo
Framework

Learning Networked Exponential Families with Network Lasso


Title	Learning Networked Exponential Families with Network Lasso
Authors	Alexander Jung
Abstract	We propose networked exponential families to jointly leverage the information in the topology as well as the attributes (features) of networked data points. Networked exponential families are a flexible probabilistic model for heterogeneous datasets with intrinsic network structure. These models can be learnt efficiently using network Lasso which implicitly pools or clusters the data points according to the intrinsic network structure and the local likelihood. The resulting method can be formulated as a non-smooth convex optimization problem which we solve using a primal-dual splitting method. This primal-dual method is appealing for big data applications as it can be implemented as a highly scalable message passing algorithm.
Tasks
Published	2019-05-22
URL	https://arxiv.org/abs/1905.09056v6
PDF	https://arxiv.org/pdf/1905.09056v6.pdf
PWC	https://paperswithcode.com/paper/learning-networked-exponential-families-with
Repo
Framework

Toward Synergic Learning for Autonomous Manipulation of Deformable Tissues via Surgical Robots: An Approximate Q-Learning Approach


Title	Toward Synergic Learning for Autonomous Manipulation of Deformable Tissues via Surgical Robots: An Approximate Q-Learning Approach
Authors	Sahba Aghajani Pedram, Peter Walker Ferguson, Changyeob Shin, Ankur Mehta, Erik P. Dutson, Farshid Alambeigi, Jacob Rosen
Abstract	In this paper, we present a synergic learning algorithm to address the task of indirect manipulation of an unknown deformable tissue. Tissue manipulation is a common yet challenging task in various surgical interventions, which makes it a good candidate for robotic automation. We propose using a linear approximate Q-learning method in which human knowledge contributes to selecting useful yet simple features of tissue manipulation while the algorithm learns to take optimal actions and accomplish the task. The algorithm is implemented and evaluated on a simulation using the OpenCV and CHAI3D libraries. Successful simulation results for four different configurations which are based on realistic tissue manipulation scenarios are presented. Results indicate that with a careful selection of relatively simple and intuitive features, the developed Q-learning algorithm can successfully learn an optimal policy without any prior knowledge of tissue dynamics or camera intrinsic/extrinsic calibration parameters.
Tasks	Calibration, Q-Learning
Published	2019-10-08
URL	https://arxiv.org/abs/1910.03398v2
PDF	https://arxiv.org/pdf/1910.03398v2.pdf
PWC	https://paperswithcode.com/paper/toward-synergic-learning-for-autonomous
Repo
Framework

Pattern-based design applied to cultural heritage knowledge graphs


Title	Pattern-based design applied to cultural heritage knowledge graphs
Authors	Valentina Anita Carriero, Aldo Gangemi, Maria Letizia Mancinelli, Andrea Giovanni Nuzzolese, Valentina Presutti, Chiara Veninata
Abstract	Ontology Design Patterns (ODPs) have become an established and recognised practice for guaranteeing good quality ontology engineering. There are several ODP repositories where ODPs are shared as well as ontology design methodologies recommending their reuse. Performing rigorous testing is recommended as well for supporting ontology maintenance and validating the resulting resource against its motivating requirements. Nevertheless, it is less than straightforward to find guidelines on how to apply such methodologies for developing domain-specific knowledge graphs. ArCo is the knowledge graph of Italian Cultural Heritage and has been developed by using eXtreme Design (XD), an ODP- and test-driven methodology. During its development, XD has been adapted to the need of the CH domain e.g. gathering requirements from an open, diverse community of consumers, a new ODP has been defined and many have been specialised to address specific CH requirements. This paper presents ArCo and describes how to apply XD to the development and validation of a CH knowledge graph, also detailing the (intellectual) process implemented for matching the encountered modelling problems to ODPs. Relevant contributions also include a novel web tool for supporting unit-testing of knowledge graphs, a rigorous evaluation of ArCo, and a discussion of methodological lessons learned during ArCo development.
Tasks	Knowledge Graphs
Published	2019-11-18
URL	https://arxiv.org/abs/1911.07585v1
PDF	https://arxiv.org/pdf/1911.07585v1.pdf
PWC	https://paperswithcode.com/paper/pattern-based-design-applied-to-cultural
Repo
Framework

Auto-weighted Mutli-view Sparse Reconstructive Embedding


Title	Auto-weighted Mutli-view Sparse Reconstructive Embedding
Authors	Huibing Wang, Haohao Li, Xianping Fu
Abstract	With the development of multimedia era, multi-view data is generated in various fields. Contrast with those single-view data, multi-view data brings more useful information and should be carefully excavated. Therefore, it is essential to fully exploit the complementary information embedded in multiple views to enhance the performances of many tasks. Especially for those high-dimensional data, how to develop a multi-view dimension reduction algorithm to obtain the low-dimensional representations is of vital importance but chanllenging. In this paper, we propose a novel multi-view dimensional reduction algorithm named Auto-weighted Mutli-view Sparse Reconstructive Embedding (AMSRE) to deal with this problem. AMSRE fully exploits the sparse reconstructive correlations between features from multiple views. Furthermore, it is equipped with an auto-weighted technique to treat multiple views discriminatively according to their contributions. Various experiments have verified the excellent performances of the proposed AMSRE.
Tasks	Dimensionality Reduction
Published	2019-01-05
URL	http://arxiv.org/abs/1901.02352v1
PDF	http://arxiv.org/pdf/1901.02352v1.pdf
PWC	https://paperswithcode.com/paper/auto-weighted-mutli-view-sparse
Repo
Framework

Machine learning for design optimization of storage ring nonlinear dynamics


Title	Machine learning for design optimization of storage ring nonlinear dynamics
Authors	Faya Wang, Minghao Song, Auralee Edelen, Xiaobiao Huang
Abstract	A novel approach to expedite design optimization of nonlinear beam dynamics in storage rings is proposed and demonstrated in this study. At each iteration, a neural network surrogate model is used to suggest new trial solutions in a multi-objective optimization task. The surrogate model is then updated with the new solutions, and this process is repeated until the final optimized solution is obtained. We apply this approach to optimize the nonlinear beam dynamics of the SPEAR3 storage ring, where sextupole knobs are adjusted to simultaneously improve the dynamic aperture and the momentum aperture. The approach is shown to converge to the Pareto front considerably faster than the genetic and particle swarm algorithms.
Tasks
Published	2019-10-31
URL	https://arxiv.org/abs/1910.14220v1
PDF	https://arxiv.org/pdf/1910.14220v1.pdf
PWC	https://paperswithcode.com/paper/machine-learning-for-design-optimization-of
Repo
Framework

Active Transfer Learning for Persian Offline Signature Verification


Title	Active Transfer Learning for Persian Offline Signature Verification
Authors	Taraneh Younesian, Saeed Masoudnia, Reshad Hosseini, Babak N. Araabi
Abstract	Offline Signature Verification (OSV) remains a challenging pattern recognition task, especially in the presence of skilled forgeries that are not available during the training. This challenge is aggravated when there are small labeled training data available but with large intra-personal variations. In this study, we address this issue by employing an active learning approach, which selects the most informative instances to label and therefore reduces the human labeling effort significantly. Our proposed OSV includes three steps: feature learning, active learning, and final verification. We benefit from transfer learning using a pre-trained CNN for feature learning. We also propose SVM-based active learning for each user to separate his genuine signatures from the random forgeries. We finally used the SVMs to verify the authenticity of the questioned signature. We examined our proposed active transfer learning method on UTSig: A Persian offline signature dataset. We achieved near 13% improvement compared to the random selection of instances. Our results also showed 1% improvement over the state-of-the-art method in which a fully supervised setting with five more labeled instances per user was used.
Tasks	Active Learning, Transfer Learning
Published	2019-02-28
URL	http://arxiv.org/abs/1903.06255v1
PDF	http://arxiv.org/pdf/1903.06255v1.pdf
PWC	https://paperswithcode.com/paper/active-transfer-learning-for-persian-offline
Repo
Framework