Paper Group ANR 354
A Quaternion-based Certifiably Optimal Solution to the Wahba Problem with Outliers. Improving Captioning for Low-Resource Languages by Cycle Consistency. Evolutionarily-Curated Curriculum Learning for Deep Reinforcement Learning Agents. A Novel method for IDC Prediction in Breast Cancer Histopathology images using Deep Residual Neural Networks. Inf …
A Quaternion-based Certifiably Optimal Solution to the Wahba Problem with Outliers
| Title | A Quaternion-based Certifiably Optimal Solution to the Wahba Problem with Outliers |
| Authors | Heng Yang, Luca Carlone |
| Abstract | The Wahba problem, also known as rotation search, seeks to find the best rotation to align two sets of vector observations given putative correspondences, and is a fundamental routine in many computer vision and robotics applications. This work proposes the first polynomial-time certifiably optimal approach for solving the Wahba problem when a large number of vector observations are outliers. Our first contribution is to formulate the Wahba problem using a Truncated Least Squares (TLS) cost that is insensitive to a large fraction of spurious correspondences. The second contribution is to rewrite the problem using unit quaternions and show that the TLS cost can be framed as a Quadratically-Constrained Quadratic Program (QCQP). Since the resulting optimization is still highly non-convex and hard to solve globally, our third contribution is to develop a convex Semidefinite Programming (SDP) relaxation. We show that while a naive relaxation performs poorly in general, our relaxation is tight even in the presence of large noise and outliers. We validate the proposed algorithm, named QUASAR (QUAternion-based Semidefinite relAxation for Robust alignment), in both synthetic and real datasets showing that the algorithm outperforms RANSAC, robust local optimization techniques, global outlier-removal procedures, and Branch-and-Bound methods. QUASAR is able to compute certifiably optimal solutions (i.e. the relaxation is exact) even in the case when 95% of the correspondences are outliers. |
| Tasks | |
| Published | 2019-05-29 |
| URL | https://arxiv.org/abs/1905.12536v4 |
| https://arxiv.org/pdf/1905.12536v4.pdf | |
| PWC | https://paperswithcode.com/paper/a-quaternion-based-certifiably-optimal |
| Repo | |
| Framework | |
Improving Captioning for Low-Resource Languages by Cycle Consistency
| Title | Improving Captioning for Low-Resource Languages by Cycle Consistency |
| Authors | Yike Wu, Shiwan Zhao, Jia Chen, Ying Zhang, Xiaojie Yuan, Zhong Su |
| Abstract | Improving the captioning performance on low-resource languages by leveraging English caption datasets has received increasing research interest in recent years. Existing works mainly fall into two categories: translation-based and alignment-based approaches. In this paper, we propose to combine the merits of both approaches in one unified architecture. Specifically, we use a pre-trained English caption model to generate high-quality English captions, and then take both the image and generated English captions to generate low-resource language captions. We improve the captioning performance by adding the cycle consistency constraint on the cycle of image regions, English words, and low-resource language words. Moreover, our architecture has a flexible design which enables it to benefit from large monolingual English caption datasets. Experimental results demonstrate that our approach outperforms the state-of-the-art methods on common evaluation metrics. The attention visualization also shows that the proposed approach really improves the fine-grained alignment between words and image regions. |
| Tasks | |
| Published | 2019-08-21 |
| URL | https://arxiv.org/abs/1908.07810v1 |
| https://arxiv.org/pdf/1908.07810v1.pdf | |
| PWC | https://paperswithcode.com/paper/190807810 |
| Repo | |
| Framework | |
Evolutionarily-Curated Curriculum Learning for Deep Reinforcement Learning Agents
| Title | Evolutionarily-Curated Curriculum Learning for Deep Reinforcement Learning Agents |
| Authors | Michael Cerny Green, Benjamin Sergent, Pushyami Shandilya, Vibhor Kumar |
| Abstract | In this paper we propose a new training loop for deep reinforcement learning agents with an evolutionary generator. Evolutionary procedural content generation has been used in the creation of maps and levels for games before. Our system incorporates an evolutionary map generator to construct a training curriculum that is evolved to maximize loss within the state-of-the-art Double Dueling Deep Q Network architecture with prioritized replay. We present a case-study in which we prove the efficacy of our new method on a game with a discrete, large action space we made called Attackers and Defenders. Our results demonstrate that training on an evolutionarily-curated curriculum (directed sampling) of maps both expedites training and improves generalization when compared to a network trained on an undirected sampling of maps. |
| Tasks | |
| Published | 2019-01-16 |
| URL | http://arxiv.org/abs/1901.05431v1 |
| http://arxiv.org/pdf/1901.05431v1.pdf | |
| PWC | https://paperswithcode.com/paper/evolutionarily-curated-curriculum-learning |
| Repo | |
| Framework | |
A Novel method for IDC Prediction in Breast Cancer Histopathology images using Deep Residual Neural Networks
| Title | A Novel method for IDC Prediction in Breast Cancer Histopathology images using Deep Residual Neural Networks |
| Authors | Chandra Churh Chatterjee, Gopal Krishna |
| Abstract | Invasive ductal carcinoma (IDC), which is also sometimes known as the infiltrating ductal carcinoma, is the most regular form of breast cancer. It accounts for about 80% of all breast cancers. According to the American Cancer Society, more than 180,000 women in the United States are diagnosed with invasive breast cancer each year. The survival rate associated with this form of cancer is about 77% to 93% depending on the stage at which they are being diagnosed. The invasiveness and the frequency of the occurrence of these disease makes it one of the difficult cancers to be diagnosed. Our proposed methodology involves diagnosing the invasive ductal carcinoma with a deep residual convolution network to classify the IDC affected histopathological images from the normal images. The dataset for the purpose used is a benchmark dataset known as the Breast Histopathology Images. The microscopic RGB images are converted into a seven channel image matrix, which is then fed to the network. The proposed model produces a 99.29% accurate approach towards the prediction of IDC in the histopathology images with an AUROC score of 0.9996. Classification ability of the model is tested using standard performance metrics. |
| Tasks | |
| Published | 2019-08-20 |
| URL | https://arxiv.org/abs/1908.07362v2 |
| https://arxiv.org/pdf/1908.07362v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-novel-method-for-idc-prediction-in-breast |
| Repo | |
| Framework | |
Information processing constraints in travel behaviour modelling: A generative learning approach
| Title | Information processing constraints in travel behaviour modelling: A generative learning approach |
| Authors | Melvin Wong, Bilal Farooq |
| Abstract | Travel decisions tend to exhibit sensitivity to uncertainty and information processing constraints. These behavioural conditions can be characterized by a generative learning process. We propose a data-driven generative model version of rational inattention theory to emulate these behavioural representations. We outline the methodology of the generative model and the associated learning process as well as provide an intuitive explanation of how this process captures the value of prior information in the choice utility specification. We demonstrate the effects of information heterogeneity on a travel choice, analyze the econometric interpretation, and explore the properties of our generative model. Our findings indicate a strong correlation with rational inattention behaviour theory, which suggest that individuals may ignore certain exogenous variables and rely on prior information for evaluating decisions under uncertainty. Finally, the principles demonstrated in this study can be formulated as a generalized entropy and utility based multinomial logit model. |
| Tasks | |
| Published | 2019-07-16 |
| URL | https://arxiv.org/abs/1907.07036v2 |
| https://arxiv.org/pdf/1907.07036v2.pdf | |
| PWC | https://paperswithcode.com/paper/information-processing-constraints-in-travel |
| Repo | |
| Framework | |
A Hidden Variables Approach to Multilabel Logistic Regression
| Title | A Hidden Variables Approach to Multilabel Logistic Regression |
| Authors | Jaemoon Lee, Hoda Shajari |
| Abstract | Multilabel classification is an important problem in a wide range of domains such as text categorization and music annotation. In this paper, we present a probabilistic model, Multilabel Logistic Regression with Hidden variables (MLRH), which extends the standard logistic regression by introducing hidden variables. Hidden variables make it possible to go beyond the conventional multiclass logistic regression by relaxing the one-hot-encoding constraint. We define a new joint distribution of labels and hidden variables which enables us to obtain one classifier for multilabel classification. Our experimental studies on a set of benchmark datasets demonstrate that the probabilistic model can achieve competitive performance compared with other multilabel learning algorithms. |
| Tasks | Text Categorization |
| Published | 2019-12-03 |
| URL | https://arxiv.org/abs/1912.01241v1 |
| https://arxiv.org/pdf/1912.01241v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-hidden-variables-approach-to-multilabel |
| Repo | |
| Framework | |
Learning Neural Sequence-to-Sequence Models from Weak Feedback with Bipolar Ramp Loss
| Title | Learning Neural Sequence-to-Sequence Models from Weak Feedback with Bipolar Ramp Loss |
| Authors | Laura Jehl, Carolin Lawrence, Stefan Riezler |
| Abstract | In many machine learning scenarios, supervision by gold labels is not available and consequently neural models cannot be trained directly by maximum likelihood estimation (MLE). In a weak supervision scenario, metric-augmented objectives can be employed to assign feedback to model outputs, which can be used to extract a supervision signal for training. We present several objectives for two separate weakly supervised tasks, machine translation and semantic parsing. We show that objectives should actively discourage negative outputs in addition to promoting a surrogate gold structure. This notion of bipolarity is naturally present in ramp loss objectives, which we adapt to neural models. We show that bipolar ramp loss objectives outperform other non-bipolar ramp loss objectives and minimum risk training (MRT) on both weakly supervised tasks, as well as on a supervised machine translation task. Additionally, we introduce a novel token-level ramp loss objective, which is able to outperform even the best sequence-level ramp loss on both weakly supervised tasks. |
| Tasks | Machine Translation, Semantic Parsing |
| Published | 2019-07-06 |
| URL | https://arxiv.org/abs/1907.03748v1 |
| https://arxiv.org/pdf/1907.03748v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-neural-sequence-to-sequence-models |
| Repo | |
| Framework | |
A Machine Learning Framework for Biometric Authentication using Electrocardiogram
| Title | A Machine Learning Framework for Biometric Authentication using Electrocardiogram |
| Authors | Song-Kyoo Kim, Chan Yeob Yeun, Ernesto Damiani, Nai-Wei Lo |
| Abstract | This paper introduces a framework for how to appropriately adopt and adjust Machine Learning (ML) techniques used to construct Electrocardiogram (ECG) based biometric authentication schemes. The proposed framework can help investigators and developers on ECG based biometric authentication mechanisms define the boundaries of required datasets and get training data with good quality. To determine the boundaries of datasets, use case analysis is adopted. Based on various application scenarios on ECG based authentication, three distinct use cases (or authentication categories) are developed. With more qualified training data given to corresponding machine learning schemes, the precision on ML-based ECG biometric authentication mechanisms is increased in consequence. ECG time slicing technique with the R-peak anchoring is utilized in this framework to acquire ML training data with good quality. In the proposed framework four new measure metrics are introduced to evaluate the quality of ML training and testing data. In addition, a Matlab toolbox, containing all proposed mechanisms, metrics and sample data with demonstrations using various ML techniques, is developed and made publicly available for further investigation. For developing ML-based ECG biometric authentication, the proposed framework can guide researchers to prepare the proper ML setups and the ML training datasets along with three identified user case scenarios. For researchers adopting ML techniques to design new schemes in other research domains, the proposed framework is still useful for generating ML-based training and testing datasets with good quality and utilizing new measure metrics. |
| Tasks | |
| Published | 2019-03-29 |
| URL | https://arxiv.org/abs/1903.12340v3 |
| https://arxiv.org/pdf/1903.12340v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-machine-learning-framework-for-biometric |
| Repo | |
| Framework | |
Usage of Decision Support Systems for Conflicts Modelling during Information Operations Recognition
| Title | Usage of Decision Support Systems for Conflicts Modelling during Information Operations Recognition |
| Authors | Oleh Andriichuk, Vitaliy Tsyganok, Dmitry Lande, Oleg Chertov, Yaroslava Porplenko |
| Abstract | Application of decision support systems for conflict modeling in information operations recognition is presented. An information operation is considered as a complex weakly structured system. The model of conflict between two subjects is proposed based on the second-order rank reflexive model. The method is described for construction of the design pattern for knowledge bases of decision support systems. In the talk, the methodology is proposed for using of decision support systems for modeling of conflicts in information operations recognition based on the use of expert knowledge and content monitoring. |
| Tasks | |
| Published | 2019-04-16 |
| URL | http://arxiv.org/abs/1904.08303v1 |
| http://arxiv.org/pdf/1904.08303v1.pdf | |
| PWC | https://paperswithcode.com/paper/usage-of-decision-support-systems-for |
| Repo | |
| Framework | |
Mitigate Parasitic Resistance in Resistive Crossbar-based Convolutional Neural Networks
| Title | Mitigate Parasitic Resistance in Resistive Crossbar-based Convolutional Neural Networks |
| Authors | Fan Zhang, Miao Hu |
| Abstract | Traditional computing hardware often encounters on-chip memory bottleneck on large scale Convolution Neural Networks (CNN) applications. With its unique in-memory computing feature, resistive crossbar-based computing attracts researchers’ attention as a promising solution to the memory bottleneck issue in von Neumann architectures. However, the parasitic resistances in the crossbar deviate its behavior from the ideal weighted summation operation. In large-scale implementations, the impact of parasitic resistances must be carefully considered and mitigated to ensure circuits’ functionality. In this work, we implemented and simulated CNNs on resistive crossbar circuits with consideration of parasitic resistances. Moreover, we carried out a new mapping scheme for high utilization of crossbar arrays on convolution, and a mitigation algorithm to mitigate parasitic resistances in CNN applications. The mitigation algorithm considers parasitic resistances as well as data/kernel patterns of each layer to minimize the computing error in crossbar-based convolutions of CNNs. We demonstrated the proposed methods with implementations of a 4-layer CNN on MNIST and ResNet(20, 32, and 56) on CIFAR-10. Simulation results show the proposed methods well mitigate the parasitic resistances in crossbars. With our methods, modern CNNs on crossbars can preserve ideal(software) level classification accuracy with 6-bit ADCs and DACs implementation. |
| Tasks | |
| Published | 2019-12-17 |
| URL | https://arxiv.org/abs/1912.08716v1 |
| https://arxiv.org/pdf/1912.08716v1.pdf | |
| PWC | https://paperswithcode.com/paper/mitigate-parasitic-resistance-in-resistive |
| Repo | |
| Framework | |
Multi-hypothesis classifier
| Title | Multi-hypothesis classifier |
| Authors | Sayantan Sengupta, Sudip Sanyal |
| Abstract | Accuracy is the most important parameter among few others which defines the effectiveness of a machine learning algorithm. Higher accuracy is always desirable. Now, there is a vast number of well established learning algorithms already present in the scientific domain. Each one of them has its own merits and demerits. Merits and demerits are evaluated in terms of accuracy, speed of convergence, complexity of the algorithm, generalization property, and robustness among many others. Also the learning algorithms are data-distribution dependent. Each learning algorithm is suitable for a particular distribution of data. Unfortunately, no dominant classifier exists for all the data distribution, and the data distribution task at hand is usually unknown. Not one classifier can be discriminative well enough if the number of classes are huge. So the underlying problem is that a single classifier is not enough to classify the whole sample space correctly. This thesis is about exploring the different techniques of combining the classifiers so as to obtain the optimal accuracy. Three classifiers are implemented namely plain old nearest neighbor on raw pixels, a structural feature extracted neighbor and Gabor feature extracted nearest neighbor. Five different combination strategies are devised and tested on Tibetan character images and analyzed |
| Tasks | |
| Published | 2019-08-20 |
| URL | https://arxiv.org/abs/1908.07857v1 |
| https://arxiv.org/pdf/1908.07857v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-hypothesis-classifier |
| Repo | |
| Framework | |
Maximum Entropy Models from Phase Harmonic Covariances
| Title | Maximum Entropy Models from Phase Harmonic Covariances |
| Authors | Sixin Zhang, Stéphane Mallat |
| Abstract | We define maximum entropy models of non-Gaussian stationary random vectors from covariances of non-linear representations. These representations are calculated by multiplying the phase of Fourier or wavelet coefficients with harmonic integers, which amounts to compute a windowed Fourier transform along their phase. Rectifiers in neural networks compute such phase windowing. The covariance of these harmonic coefficients capture dependencies of Fourier and wavelet coefficients across frequencies, by canceling their random phase. We introduce maximum entropy models conditioned by such covariances over a graph of local interactions. These models are approximated by transporting an initial maximum entropy measure with a gradient descent. The precision of wavelet phase harmonic models is numerically evaluated over turbulent flows and other non-Gaussian stationary processes. |
| Tasks | |
| Published | 2019-11-22 |
| URL | https://arxiv.org/abs/1911.10017v1 |
| https://arxiv.org/pdf/1911.10017v1.pdf | |
| PWC | https://paperswithcode.com/paper/maximum-entropy-models-from-phase-harmonic |
| Repo | |
| Framework | |
Inducing Relational Knowledge from BERT
| Title | Inducing Relational Knowledge from BERT |
| Authors | Zied Bouraoui, Jose Camacho-Collados, Steven Schockaert |
| Abstract | One of the most remarkable properties of word embeddings is the fact that they capture certain types of semantic and syntactic relationships. Recently, pre-trained language models such as BERT have achieved groundbreaking results across a wide range of Natural Language Processing tasks. However, it is unclear to what extent such models capture relational knowledge beyond what is already captured by standard word embeddings. To explore this question, we propose a methodology for distilling relational knowledge from a pre-trained language model. Starting from a few seed instances of a given relation, we first use a large text corpus to find sentences that are likely to express this relation. We then use a subset of these extracted sentences as templates. Finally, we fine-tune a language model to predict whether a given word pair is likely to be an instance of some relation, when given an instantiated template for that relation as input. |
| Tasks | Language Modelling, Word Embeddings |
| Published | 2019-11-28 |
| URL | https://arxiv.org/abs/1911.12753v1 |
| https://arxiv.org/pdf/1911.12753v1.pdf | |
| PWC | https://paperswithcode.com/paper/inducing-relational-knowledge-from-bert |
| Repo | |
| Framework | |
Joint Visual-Textual Embedding for Multimodal Style Search
| Title | Joint Visual-Textual Embedding for Multimodal Style Search |
| Authors | Gil Sadeh, Lior Fritz, Gabi Shalev, Eduard Oks |
| Abstract | We introduce a multimodal visual-textual search refinement method for fashion garments. Existing search engines do not enable intuitive, interactive, refinement of retrieved results based on the properties of a particular product. We propose a method to retrieve similar items, based on a query item image and textual refinement properties. We believe this method can be leveraged to solve many real-life customer scenarios, in which a similar item in a different color, pattern, length or style is desired. We employ a joint embedding training scheme in which product images and their catalog textual metadata are mapped closely in a shared space. This joint visual-textual embedding space enables manipulating catalog images semantically, based on textual refinement requirements. We propose a new training objective function, Mini-Batch Match Retrieval, and demonstrate its superiority over the commonly used triplet loss. Additionally, we demonstrate the feasibility of adding an attribute extraction module, trained on the same catalog data, and demonstrate how to integrate it within the multimodal search to boost its performance. We introduce an evaluation protocol with an associated benchmark, and compare several approaches. |
| Tasks | |
| Published | 2019-06-15 |
| URL | https://arxiv.org/abs/1906.06620v1 |
| https://arxiv.org/pdf/1906.06620v1.pdf | |
| PWC | https://paperswithcode.com/paper/joint-visual-textual-embedding-for-multimodal |
| Repo | |
| Framework | |
Imitation Learning from Video by Leveraging Proprioception
| Title | Imitation Learning from Video by Leveraging Proprioception |
| Authors | Faraz Torabi, Garrett Warnell, Peter Stone |
| Abstract | Classically, imitation learning algorithms have been developed for idealized situations, e.g., the demonstrations are often required to be collected in the exact same environment and usually include the demonstrator’s actions. Recently, however, the research community has begun to address some of these shortcomings by offering algorithmic solutions that enable imitation learning from observation (IfO), e.g., learning to perform a task from visual demonstrations that may be in a different environment and do not include actions. Motivated by the fact that agents often also have access to their own internal states (i.e., proprioception), we propose and study an IfO algorithm that leverages this information in the policy learning process. The proposed architecture learns policies over proprioceptive state representations and compares the resulting trajectories visually to the demonstration data. We experimentally test the proposed technique on several MuJoCo domains and show that it outperforms other imitation from observation algorithms by a large margin. |
| Tasks | Imitation Learning |
| Published | 2019-05-22 |
| URL | https://arxiv.org/abs/1905.09335v2 |
| https://arxiv.org/pdf/1905.09335v2.pdf | |
| PWC | https://paperswithcode.com/paper/imitation-learning-from-video-by-leveraging |
| Repo | |
| Framework | |
