Paper Group ANR 287
A Comparison Study of Nonlinear Kernels. Exploiting N-Best Hypotheses to Improve an SMT Approach to Grammatical Error Correction. Spectral learning of dynamic systems from nonequilibrium data. Multi-resource defensive strategies for patrolling games with alarm systems. Fair Algorithms for Infinite and Contextual Bandits. From line segments to more …
A Comparison Study of Nonlinear Kernels
| Title | A Comparison Study of Nonlinear Kernels |
| Authors | Ping Li |
| Abstract | In this paper, we compare 5 different nonlinear kernels: min-max, RBF, fRBF (folded RBF), acos, and acos-$\chi^2$, on a wide range of publicly available datasets. The proposed fRBF kernel performs very similarly to the RBF kernel. Both RBF and fRBF kernels require an important tuning parameter ($\gamma$). Interestingly, for a significant portion of the datasets, the min-max kernel outperforms the best-tuned RBF/fRBF kernels. The acos kernel and acos-$\chi^2$ kernel also perform well in general and in some datasets achieve the best accuracies. One crucial issue with the use of nonlinear kernels is the excessive computational and memory cost. These days, one increasingly popular strategy is to linearize the kernels through various randomization algorithms. In our study, the randomization method for the min-max kernel demonstrates excellent performance compared to the randomization methods for other types of nonlinear kernels, measured in terms of the number of nonzero terms in the transformed dataset. Our study provides evidence for supporting the use of the min-max kernel and the corresponding randomized linearization method (i.e., the so-called “0-bit CWS”). Furthermore, the results motivate at least two directions for future research: (i) To develop new (and linearizable) nonlinear kernels for better accuracies; and (ii) To develop better linearization algorithms for improving the current linearization methods for the RBF kernel, the acos kernel, and the acos-$\chi^2$ kernel. One attempt is to combine the min-max kernel with the acos kernel or the acos-$\chi^2$ kernel. The advantages of these two new and tuning-free nonlinear kernels are demonstrated vias our extensive experiments. |
| Tasks | |
| Published | 2016-03-21 |
| URL | http://arxiv.org/abs/1603.06541v1 |
| http://arxiv.org/pdf/1603.06541v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-comparison-study-of-nonlinear-kernels |
| Repo | |
| Framework | |
Exploiting N-Best Hypotheses to Improve an SMT Approach to Grammatical Error Correction
| Title | Exploiting N-Best Hypotheses to Improve an SMT Approach to Grammatical Error Correction |
| Authors | Duc Tam Hoang, Shamil Chollampatt, Hwee Tou Ng |
| Abstract | Grammatical error correction (GEC) is the task of detecting and correcting grammatical errors in texts written by second language learners. The statistical machine translation (SMT) approach to GEC, in which sentences written by second language learners are translated to grammatically correct sentences, has achieved state-of-the-art accuracy. However, the SMT approach is unable to utilize global context. In this paper, we propose a novel approach to improve the accuracy of GEC, by exploiting the n-best hypotheses generated by an SMT approach. Specifically, we build a classifier to score the edits in the n-best hypotheses. The classifier can be used to select appropriate edits or re-rank the n-best hypotheses. We apply these methods to a state-of-the-art GEC system that uses the SMT approach. Our experiments show that our methods achieve statistically significant improvements in accuracy over the best published results on a benchmark test dataset on GEC. |
| Tasks | Grammatical Error Correction, Machine Translation |
| Published | 2016-06-01 |
| URL | http://arxiv.org/abs/1606.00210v1 |
| http://arxiv.org/pdf/1606.00210v1.pdf | |
| PWC | https://paperswithcode.com/paper/exploiting-n-best-hypotheses-to-improve-an |
| Repo | |
| Framework | |
Spectral learning of dynamic systems from nonequilibrium data
| Title | Spectral learning of dynamic systems from nonequilibrium data |
| Authors | Hao Wu, Frank Noé |
| Abstract | Observable operator models (OOMs) and related models are one of the most important and powerful tools for modeling and analyzing stochastic systems. They exactly describe dynamics of finite-rank systems and can be efficiently and consistently estimated through spectral learning under the assumption of identically distributed data. In this paper, we investigate the properties of spectral learning without this assumption due to the requirements of analyzing large-time scale systems, and show that the equilibrium dynamics of a system can be extracted from nonequilibrium observation data by imposing an equilibrium constraint. In addition, we propose a binless extension of spectral learning for continuous data. In comparison with the other continuous-valued spectral algorithms, the binless algorithm can achieve consistent estimation of equilibrium dynamics with only linear complexity. |
| Tasks | |
| Published | 2016-09-04 |
| URL | http://arxiv.org/abs/1609.00932v2 |
| http://arxiv.org/pdf/1609.00932v2.pdf | |
| PWC | https://paperswithcode.com/paper/spectral-learning-of-dynamic-systems-from |
| Repo | |
| Framework | |
Multi-resource defensive strategies for patrolling games with alarm systems
| Title | Multi-resource defensive strategies for patrolling games with alarm systems |
| Authors | Nicola Basilico, Giuseppe De Nittis, Nicola Gatti |
| Abstract | Security Games employ game theoretical tools to derive resource allocation strategies in security domains. Recent works considered the presence of alarm systems, even suffering various forms of uncertainty, and showed that disregarding alarm signals may lead to arbitrarily bad strategies. The central problem with an alarm system, unexplored in other Security Games, is finding the best strategy to respond to alarm signals for each mobile defensive resource. The literature provides results for the basic single-resource case, showing that even in that case the problem is computationally hard. In this paper, we focus on the challenging problem of designing algorithms scaling with multiple resources. First, we focus on finding the minimum number of resources assuring non-null protection to every target. Then, we deal with the computation of multi-resource strategies with different degrees of coordination among resources. For each considered problem, we provide a computational analysis and propose algorithmic methods. |
| Tasks | |
| Published | 2016-06-07 |
| URL | http://arxiv.org/abs/1606.02221v1 |
| http://arxiv.org/pdf/1606.02221v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-resource-defensive-strategies-for |
| Repo | |
| Framework | |
Fair Algorithms for Infinite and Contextual Bandits
| Title | Fair Algorithms for Infinite and Contextual Bandits |
| Authors | Matthew Joseph, Michael Kearns, Jamie Morgenstern, Seth Neel, Aaron Roth |
| Abstract | We study fairness in linear bandit problems. Starting from the notion of meritocratic fairness introduced in Joseph et al. [2016], we carry out a more refined analysis of a more general problem, achieving better performance guarantees with fewer modelling assumptions on the number and structure of available choices as well as the number selected. We also analyze the previously-unstudied question of fairness in infinite linear bandit problems, obtaining instance-dependent regret upper bounds as well as lower bounds demonstrating that this instance-dependence is necessary. The result is a framework for meritocratic fairness in an online linear setting that is substantially more powerful, general, and realistic than the current state of the art. |
| Tasks | Multi-Armed Bandits |
| Published | 2016-10-29 |
| URL | http://arxiv.org/abs/1610.09559v4 |
| http://arxiv.org/pdf/1610.09559v4.pdf | |
| PWC | https://paperswithcode.com/paper/fair-algorithms-for-infinite-and-contextual |
| Repo | |
| Framework | |
From line segments to more organized Gestalts
| Title | From line segments to more organized Gestalts |
| Authors | Boshra Rajaei, Rafael Grompone von Gioi, Jean-Michel Morel |
| Abstract | In this paper, we reconsider the early computer vision bottom-up program, according to which higher level features (geometric structures) in an image could be built up recursively from elementary features by simple grouping principles coming from Gestalt theory. Taking advantage of the (recent) advances in reliable line segment detectors, we propose three feature detectors that constitute one step up in this bottom up pyramid. For any digital image, our unsupervised algorithm computes three classic Gestalts from the set of predetected line segments: good continuations, nonlocal alignments, and bars. The methodology is based on a common stochastic {\it a contrario model} yielding three simple detection formulas, characterized by their number of false alarms. This detection algorithm is illustrated on several digital images. |
| Tasks | |
| Published | 2016-03-18 |
| URL | http://arxiv.org/abs/1603.05763v1 |
| http://arxiv.org/pdf/1603.05763v1.pdf | |
| PWC | https://paperswithcode.com/paper/from-line-segments-to-more-organized-gestalts |
| Repo | |
| Framework | |
Examining Representational Similarity in ConvNets and the Primate Visual Cortex
| Title | Examining Representational Similarity in ConvNets and the Primate Visual Cortex |
| Authors | Abhimanyu Dubey, Jayadeva, Sumeet Agarwal |
| Abstract | We compare several ConvNets with different depth and regularization techniques with multi-unit macaque IT cortex recordings and assess the impact of the same on representational similarity with the primate visual cortex. We find that with increasing depth and validation performance, ConvNet features are closer to cortical IT representations. |
| Tasks | |
| Published | 2016-09-12 |
| URL | http://arxiv.org/abs/1609.03529v1 |
| http://arxiv.org/pdf/1609.03529v1.pdf | |
| PWC | https://paperswithcode.com/paper/examining-representational-similarity-in |
| Repo | |
| Framework | |
A Comprehensive Survey on Cross-modal Retrieval
| Title | A Comprehensive Survey on Cross-modal Retrieval |
| Authors | Kaiye Wang, Qiyue Yin, Wei Wang, Shu Wu, Liang Wang |
| Abstract | In recent years, cross-modal retrieval has drawn much attention due to the rapid growth of multimodal data. It takes one type of data as the query to retrieve relevant data of another type. For example, a user can use a text to retrieve relevant pictures or videos. Since the query and its retrieved results can be of different modalities, how to measure the content similarity between different modalities of data remains a challenge. Various methods have been proposed to deal with such a problem. In this paper, we first review a number of representative methods for cross-modal retrieval and classify them into two main groups: 1) real-valued representation learning, and 2) binary representation learning. Real-valued representation learning methods aim to learn real-valued common representations for different modalities of data. To speed up the cross-modal retrieval, a number of binary representation learning methods are proposed to map different modalities of data into a common Hamming space. Then, we introduce several multimodal datasets in the community, and show the experimental results on two commonly used multimodal datasets. The comparison reveals the characteristic of different kinds of cross-modal retrieval methods, which is expected to benefit both practical applications and future research. Finally, we discuss open problems and future research directions. |
| Tasks | Cross-Modal Retrieval, Representation Learning |
| Published | 2016-07-21 |
| URL | http://arxiv.org/abs/1607.06215v1 |
| http://arxiv.org/pdf/1607.06215v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-comprehensive-survey-on-cross-modal |
| Repo | |
| Framework | |
On the Sampling Strategy for Evaluation of Spectral-spatial Methods in Hyperspectral Image Classification
| Title | On the Sampling Strategy for Evaluation of Spectral-spatial Methods in Hyperspectral Image Classification |
| Authors | Jie Liang, Jun Zhou, Yuntao Qian, Lian Wen, Xiao Bai, Yongsheng Gao |
| Abstract | Spectral-spatial processing has been increasingly explored in remote sensing hyperspectral image classification. While extensive studies have focused on developing methods to improve the classification accuracy, experimental setting and design for method evaluation have drawn little attention. In the scope of supervised classification, we find that traditional experimental designs for spectral processing are often improperly used in the spectral-spatial processing context, leading to unfair or biased performance evaluation. This is especially the case when training and testing samples are randomly drawn from the same image - a practice that has been commonly adopted in the experiments. Under such setting, the dependence caused by overlap between the training and testing samples may be artificially enhanced by some spatial information processing methods such as spatial filtering and morphological operation. Such interaction between training and testing sets has violated data independence assumption that is abided by supervised learning theory and performance evaluation mechanism. Therefore, the widely adopted pixel-based random sampling strategy is not always suitable to evaluate spectral-spatial classification algorithms because it is difficult to determine whether the improvement of classification accuracy is caused by incorporating spatial information into classifier or by increasing the overlap between training and testing samples. To partially solve this problem, we propose a novel controlled random sampling strategy for spectral-spatial methods. It can greatly reduce the overlap between training and testing samples and provides more objective and accurate evaluation. |
| Tasks | Hyperspectral Image Classification, Image Classification |
| Published | 2016-05-19 |
| URL | http://arxiv.org/abs/1605.05829v1 |
| http://arxiv.org/pdf/1605.05829v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-sampling-strategy-for-evaluation-of |
| Repo | |
| Framework | |
Randomized Prediction Games for Adversarial Machine Learning
| Title | Randomized Prediction Games for Adversarial Machine Learning |
| Authors | Samuel Rota Bulò, Battista Biggio, Ignazio Pillai, Marcello Pelillo, Fabio Roli |
| Abstract | In spam and malware detection, attackers exploit randomization to obfuscate malicious data and increase their chances of evading detection at test time; e.g., malware code is typically obfuscated using random strings or byte sequences to hide known exploits. Interestingly, randomization has also been proposed to improve security of learning algorithms against evasion attacks, as it results in hiding information about the classifier to the attacker. Recent work has proposed game-theoretical formulations to learn secure classifiers, by simulating different evasion attacks and modifying the classification function accordingly. However, both the classification function and the simulated data manipulations have been modeled in a deterministic manner, without accounting for any form of randomization. In this work, we overcome this limitation by proposing a randomized prediction game, namely, a non-cooperative game-theoretic formulation in which the classifier and the attacker make randomized strategy selections according to some probability distribution defined over the respective strategy set. We show that our approach allows one to improve the trade-off between attack detection and false alarms with respect to state-of-the-art secure classifiers, even against attacks that are different from those hypothesized during design, on application examples including handwritten digit recognition, spam and malware detection. |
| Tasks | Handwritten Digit Recognition, Malware Detection |
| Published | 2016-09-03 |
| URL | http://arxiv.org/abs/1609.00804v1 |
| http://arxiv.org/pdf/1609.00804v1.pdf | |
| PWC | https://paperswithcode.com/paper/randomized-prediction-games-for-adversarial |
| Repo | |
| Framework | |
Boosting Question Answering by Deep Entity Recognition
| Title | Boosting Question Answering by Deep Entity Recognition |
| Authors | Piotr Przybyła |
| Abstract | In this paper an open-domain factoid question answering system for Polish, RAFAEL, is presented. The system goes beyond finding an answering sentence; it also extracts a single string, corresponding to the required entity. Herein the focus is placed on different approaches to entity recognition, essential for retrieving information matching question constraints. Apart from traditional approach, including named entity recognition (NER) solutions, a novel technique, called Deep Entity Recognition (DeepER), is introduced and implemented. It allows a comprehensive search of all forms of entity references matching a given WordNet synset (e.g. an impressionist), based on a previously assembled entity library. It has been created by analysing the first sentences of encyclopaedia entries and disambiguation and redirect pages. DeepER also provides automatic evaluation, which makes possible numerous experiments, including over a thousand questions from a quiz TV show answered on the grounds of Polish Wikipedia. The final results of a manual evaluation on a separate question set show that the strength of DeepER approach lies in its ability to answer questions that demand answers beyond the traditional categories of named entities. |
| Tasks | Named Entity Recognition, Question Answering |
| Published | 2016-05-27 |
| URL | http://arxiv.org/abs/1605.08675v1 |
| http://arxiv.org/pdf/1605.08675v1.pdf | |
| PWC | https://paperswithcode.com/paper/boosting-question-answering-by-deep-entity |
| Repo | |
| Framework | |
Examining the Impact of Blur on Recognition by Convolutional Networks
| Title | Examining the Impact of Blur on Recognition by Convolutional Networks |
| Authors | Igor Vasiljevic, Ayan Chakrabarti, Gregory Shakhnarovich |
| Abstract | State-of-the-art algorithms for many semantic visual tasks are based on the use of convolutional neural networks. These networks are commonly trained, and evaluated, on large annotated datasets of artifact-free high-quality images. In this paper, we investigate the effect of one such artifact that is quite common in natural capture settings: optical blur. We show that standard network models, trained only on high-quality images, suffer a significant degradation in performance when applied to those degraded by blur due to defocus, or subject or camera motion. We investigate the extent to which this degradation is due to the mismatch between training and input image statistics. Specifically, we find that fine-tuning a pre-trained model with blurred images added to the training set allows it to regain much of the lost accuracy. We also show that there is a fair amount of generalization between different degrees and types of blur, which implies that a single network model can be used robustly for recognition when the nature of the blur in the input is unknown. We find that this robustness arises as a result of these models learning to generate blur invariant representations in their hidden layers. Our findings provide useful insights towards developing vision systems that can perform reliably on real world images affected by blur. |
| Tasks | |
| Published | 2016-11-17 |
| URL | http://arxiv.org/abs/1611.05760v2 |
| http://arxiv.org/pdf/1611.05760v2.pdf | |
| PWC | https://paperswithcode.com/paper/examining-the-impact-of-blur-on-recognition |
| Repo | |
| Framework | |
The Minimum Cost Connected Subgraph Problem in Medical Image Analysis
| Title | The Minimum Cost Connected Subgraph Problem in Medical Image Analysis |
| Authors | Markus Rempfler, Bjoern Andres, Bjoern H. Menze |
| Abstract | Several important tasks in medical image analysis can be stated in the form of an optimization problem whose feasible solutions are connected subgraphs. Examples include the reconstruction of neural or vascular structures under connectedness constraints. We discuss the minimum cost connected subgraph (MCCS) problem and its approximations from the perspective of medical applications. We propose a) objective-dependent constraints and b) novel constraint generation schemes to solve this optimization problem exactly by means of a branch-and-cut algorithm. These are shown to improve scalability and allow us to solve instances of two medical benchmark datasets to optimality for the first time. This enables us to perform a quantitative comparison between exact and approximative algorithms, where we identify the geodesic tree algorithm as an excellent alternative to exact inference on the examined datasets. |
| Tasks | |
| Published | 2016-06-20 |
| URL | http://arxiv.org/abs/1606.06135v1 |
| http://arxiv.org/pdf/1606.06135v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-minimum-cost-connected-subgraph-problem |
| Repo | |
| Framework | |
Character Proposal Network for Robust Text Extraction
| Title | Character Proposal Network for Robust Text Extraction |
| Authors | Shuye Zhang, Mude Lin, Tianshui Chen, Lianwen Jin, Liang Lin |
| Abstract | Maximally stable extremal regions (MSER), which is a popular method to generate character proposals/candidates, has shown superior performance in scene text detection. However, the pixel-level operation limits its capability for handling some challenging cases (e.g., multiple connected characters, separated parts of one character and non-uniform illumination). To better tackle these cases, we design a character proposal network (CPN) by taking advantage of the high capacity and fast computing of fully convolutional network (FCN). Specifically, the network simultaneously predicts characterness scores and refines the corresponding locations. The characterness scores can be used for proposal ranking to reject non-character proposals and the refining process aims to obtain the more accurate locations. Furthermore, considering the situation that different characters have different aspect ratios, we propose a multi-template strategy, designing a refiner for each aspect ratio. The extensive experiments indicate our method achieves recall rates of 93.88%, 93.60% and 96.46% on ICDAR 2013, SVT and Chinese2k datasets respectively using less than 1000 proposals, demonstrating promising performance of our character proposal network. |
| Tasks | Scene Text Detection |
| Published | 2016-02-13 |
| URL | http://arxiv.org/abs/1602.04348v1 |
| http://arxiv.org/pdf/1602.04348v1.pdf | |
| PWC | https://paperswithcode.com/paper/character-proposal-network-for-robust-text |
| Repo | |
| Framework | |
Encapsulating models and approximate inference programs in probabilistic modules
| Title | Encapsulating models and approximate inference programs in probabilistic modules |
| Authors | Marco F. Cusumano-Towner, Vikash K. Mansinghka |
| Abstract | This paper introduces the probabilistic module interface, which allows encapsulation of complex probabilistic models with latent variables alongside custom stochastic approximate inference machinery, and provides a platform-agnostic abstraction barrier separating the model internals from the host probabilistic inference system. The interface can be seen as a stochastic generalization of a standard simulation and density interface for probabilistic primitives. We show that sound approximate inference algorithms can be constructed for networks of probabilistic modules, and we demonstrate that the interface can be implemented using learned stochastic inference networks and MCMC and SMC approximate inference programs. |
| Tasks | |
| Published | 2016-12-14 |
| URL | http://arxiv.org/abs/1612.04759v2 |
| http://arxiv.org/pdf/1612.04759v2.pdf | |
| PWC | https://paperswithcode.com/paper/encapsulating-models-and-approximate |
| Repo | |
| Framework | |
