Paper Group ANR 481
Unsupervised Domain Adaptation using Feature-Whitening and Consensus Loss. GANCoder: An Automatic Natural Language-to-Programming Language Translation Approach based on GAN. A Compositional Model of Multi-faceted Trust for Personalized Item Recommendation. Hybrid-FL for Wireless Networks: Cooperative Learning Mechanism Using Non-IID Data. Spectral …
Unsupervised Domain Adaptation using Feature-Whitening and Consensus Loss
| Title | Unsupervised Domain Adaptation using Feature-Whitening and Consensus Loss |
| Authors | Subhankar Roy, Aliaksandr Siarohin, Enver Sangineto, Samuel Rota Bulo, Nicu Sebe, Elisa Ricci |
| Abstract | A classifier trained on a dataset seldom works on other datasets obtained under different conditions due to domain shift. This problem is commonly addressed by domain adaptation methods. In this work we introduce a novel deep learning framework which unifies different paradigms in unsupervised domain adaptation. Specifically, we propose domain alignment layers which implement feature whitening for the purpose of matching source and target feature distributions. Additionally, we leverage the unlabeled target data by proposing the Min-Entropy Consensus loss, which regularizes training while avoiding the adoption of many user-defined hyper-parameters. We report results on publicly available datasets, considering both digit classification and object recognition tasks. We show that, in most of our experiments, our approach improves upon previous methods, setting new state-of-the-art performances. |
| Tasks | Domain Adaptation, Object Recognition, Unsupervised Domain Adaptation |
| Published | 2019-03-07 |
| URL | https://arxiv.org/abs/1903.03215v2 |
| https://arxiv.org/pdf/1903.03215v2.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-domain-adaptation-using-feature |
| Repo | |
| Framework | |
GANCoder: An Automatic Natural Language-to-Programming Language Translation Approach based on GAN
| Title | GANCoder: An Automatic Natural Language-to-Programming Language Translation Approach based on GAN |
| Authors | Yabing Zhu, Yanfeng Zhang, Huili Yang, Fangjing Wang |
| Abstract | We propose GANCoder, an automatic programming approach based on Generative Adversarial Networks (GAN), which can generate the same functional and logical programming language codes conditioned on the given natural language utterances. The adversarial training between generator and discriminator helps generator learn distribution of dataset and improve code generation quality. Our experimental results show that GANCoder can achieve comparable accuracy with the state-of-the-art methods and is more stable when programming languages. |
| Tasks | Code Generation |
| Published | 2019-12-02 |
| URL | https://arxiv.org/abs/1912.00609v1 |
| https://arxiv.org/pdf/1912.00609v1.pdf | |
| PWC | https://paperswithcode.com/paper/gancoder-an-automatic-natural-language-to |
| Repo | |
| Framework | |
A Compositional Model of Multi-faceted Trust for Personalized Item Recommendation
| Title | A Compositional Model of Multi-faceted Trust for Personalized Item Recommendation |
| Authors | Liliana Ardissono, Noemi Mauro |
| Abstract | Trust-based recommender systems improve rating prediction with respect to Collaborative Filtering by leveraging the additional information provided by a trust network among users to deal with the cold start problem. However, they are challenged by recent studies according to which people generally perceive the usage of data about social relations as a violation of their own privacy. In order to address this issue, we extend trust-based recommender systems with additional evidence about trust, based on public anonymous information, and we make them configurable with respect to the data that can be used in the given application domain: 1 - We propose the Multi-faceted Trust Model (MTM) to define trust among users in a compositional way, possibly including or excluding the types of information it contains. MTM flexibly integrates social links with public anonymous feedback received by user profiles and user contributions in social networks. 2 - We propose LOCABAL+, based on MTM, which extends the LOCABAL trust-based recommender system with multi-faceted trust and trust-based social regularization. Experiments carried out on two public datasets of item reviews show that, with a minor loss of user coverage, LOCABAL+ outperforms state-of-the art trust-based recommender systems and Collaborative Filtering in accuracy, ranking of items and error minimization both when it uses complete information about trust and when it ignores social relations. The combination of MTM with LOCABAL+ thus represents a promising alternative to state-of-the-art trust-based recommender systems. |
| Tasks | Recommendation Systems |
| Published | 2019-09-04 |
| URL | https://arxiv.org/abs/1909.01601v1 |
| https://arxiv.org/pdf/1909.01601v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-compositional-model-of-multi-faceted-trust |
| Repo | |
| Framework | |
Hybrid-FL for Wireless Networks: Cooperative Learning Mechanism Using Non-IID Data
| Title | Hybrid-FL for Wireless Networks: Cooperative Learning Mechanism Using Non-IID Data |
| Authors | Naoya Yoshida, Takayuki Nishio, Masahiro Morikura, Koji Yamamoto, Ryo Yonetani |
| Abstract | This paper proposes a cooperative mechanism for mitigating the performance degradation due to non-independent-and-identically-distributed (non-IID) data in collaborative machine learning (ML), namely federated learning (FL), which trains an ML model using the rich data and computational resources of mobile clients without gathering their data to central systems. The data of mobile clients is typically non-IID owing to diversity among mobile clients’ interests and usage, and FL with non-IID data could degrade the model performance. Therefore, to mitigate the degradation induced by non-IID data, we assume that a limited number (e.g., less than 1%) of clients allow their data to be uploaded to a server, and we propose a hybrid learning mechanism referred to as Hybrid-FL, wherein the server updates the model using the data gathered from the clients and aggregates the model with the models trained by clients. The Hybrid-FL solves both client- and data-selection problems via heuristic algorithms, which try to select the optimal sets of clients who train models with their own data, clients who upload their data to the server, and data uploaded to the server. The algorithms increase the number of clients participating in FL and make more data gather in the server IID, thereby improving the prediction accuracy of the aggregated model. Evaluations, which consist of network simulations and ML experiments, demonstrate that the proposed scheme achieves a 13.5% higher classification accuracy than those of the previously proposed schemes for the non-IID case. |
| Tasks | |
| Published | 2019-05-17 |
| URL | https://arxiv.org/abs/1905.07210v3 |
| https://arxiv.org/pdf/1905.07210v3.pdf | |
| PWC | https://paperswithcode.com/paper/hybrid-fl-cooperative-learning-mechanism |
| Repo | |
| Framework | |
Spectral Properties of Radial Kernels and Clustering in High Dimensions
| Title | Spectral Properties of Radial Kernels and Clustering in High Dimensions |
| Authors | David Cohen-Steiner, Alba Chiara de Vitis |
| Abstract | In this paper, we study the spectrum and the eigenvectors of radial kernels for mixtures of distributions in $\mathbb{R}^n$. Our approach focuses on high dimensions and relies solely on the concentration properties of the components in the mixture. We give several results describing of the structure of kernel matrices for a sample drawn from such a mixture. Based on these results, we analyze the ability of kernel PCA to cluster high dimensional mixtures. In particular, we exhibit a specific kernel leading to a simple spectral algorithm for clustering mixtures with possibly common means but different covariance matrices. We show that the minimum angular separation between the covariance matrices that is required for the algorithm to succeed tends to $0$ as $n$ goes to infinity. |
| Tasks | |
| Published | 2019-06-25 |
| URL | https://arxiv.org/abs/1906.10583v4 |
| https://arxiv.org/pdf/1906.10583v4.pdf | |
| PWC | https://paperswithcode.com/paper/spectral-properties-of-radial-kernels-and |
| Repo | |
| Framework | |
Adaptive Control for Marine Vessels Against Harsh Environmental Variation
| Title | Adaptive Control for Marine Vessels Against Harsh Environmental Variation |
| Authors | Fangwen Tu, Shuzhi Sam Ge, Yoo Sang Choo, Chang Chieh Hang |
| Abstract | In this paper, robust control with sea state observer and dynamic thrust allocation is proposed for the Dynamic Positioning (DP) of an accommodation vessel in the presence of unknown hydrodynamic force variation and the input time delay. In order to overcome the huge force variation due to the adjoining Floating Production Storage and Offloading (FPSO) and accommodation vessel, a novel sea state observer is designed. The sea observer can effectively monitor the variation of the drift wave-induced force on the vessel and activate Neural Network (NN) compensator in the controller when large wave force is identified. Moreover, the wind drag coefficients can be adaptively approximated in the sea observer so that a feedforward control can be achieved. Based on this, a robust constrained control is developed to guarantee a safe operation. The time delay inside the control input is also considered. Dynamic thrust allocation module is presented to distribute the generalized control input among azimuth thrusters. Under the proposed sea observer and control, the boundedness of all the closed-loop signals are demonstrated via rigorous Lyapunov analysis. A set of simulation studies are conducted to verify the effectiveness of the proposed control scheme. |
| Tasks | |
| Published | 2019-09-29 |
| URL | https://arxiv.org/abs/1909.13265v1 |
| https://arxiv.org/pdf/1909.13265v1.pdf | |
| PWC | https://paperswithcode.com/paper/adaptive-control-for-marine-vessels-against |
| Repo | |
| Framework | |
Large-Scale Object Mining for Object Discovery from Unlabeled Video
| Title | Large-Scale Object Mining for Object Discovery from Unlabeled Video |
| Authors | Aljosa Osep, Paul Voigtlaender, Jonathon Luiten, Stefan Breuers, Bastian Leibe |
| Abstract | This paper addresses the problem of object discovery from unlabeled driving videos captured in a realistic automotive setting. Identifying recurring object categories in such raw video streams is a very challenging problem. Not only do object candidates first have to be localized in the input images, but many interesting object categories occur relatively infrequently. Object discovery will therefore have to deal with the difficulties of operating in the long tail of the object distribution. We demonstrate the feasibility of performing fully automatic object discovery in such a setting by mining object tracks using a generic object tracker. In order to facilitate further research in object discovery, we release a collection of more than 360,000 automatically mined object tracks from 10+ hours of video data (560,000 frames). We use this dataset to evaluate the suitability of different feature representations and clustering strategies for object discovery. |
| Tasks | |
| Published | 2019-02-28 |
| URL | http://arxiv.org/abs/1903.00362v2 |
| http://arxiv.org/pdf/1903.00362v2.pdf | |
| PWC | https://paperswithcode.com/paper/large-scale-object-mining-for-object |
| Repo | |
| Framework | |
Learning Preferences and Demands in Visual Recommendation
| Title | Learning Preferences and Demands in Visual Recommendation |
| Authors | Qiang Liu, Shu Wu, Liang Wang |
| Abstract | Visual information is an important factor in recommender systems, in which users’ selections consist of two components: \emph{preferences} and \emph{demands}. Some studies has been done for modeling users’ preferences in visual recommendation. However, conventional methods models items in a common visual feature space, which may fail in capturing \emph{styles} of items. We propose a DeepStyle method for learning style features of items. DeepStyle eliminates the categorical information of items, which is dominant in the original visual feature space, based on a Convolutional Neural Networks (CNN) architecture. For modeling users’ demands on different categories of items, the problem can be formulated as recommendation with contextual and sequential information. To solve this problem, we propose a Context-Aware Gated Recurrent Unit (CA-GRU) method, which can capture sequential and contextual information simultaneously. Furthermore, the aggregation of prediction on preferences and demands, i.e., prediction generated by DeepStyle and CA-GRU, can model users’ selection behaviors more completely. Experiments conducted on real-world datasets illustrates the effectiveness of our proposed methods in visual recommendation. |
| Tasks | Recommendation Systems |
| Published | 2019-11-11 |
| URL | https://arxiv.org/abs/1911.04229v1 |
| https://arxiv.org/pdf/1911.04229v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-preferences-and-demands-in-visual |
| Repo | |
| Framework | |
Towards A Logical Account of Epistemic Causality
| Title | Towards A Logical Account of Epistemic Causality |
| Authors | Shakil M. Khan, Mikhail Soutchanski |
| Abstract | Reasoning about observed effects and their causes is important in multi-agent contexts. While there has been much work on causality from an objective standpoint, causality from the point of view of some particular agent has received much less attention. In this paper, we address this issue by incorporating an epistemic dimension to an existing formal model of causality. We define what it means for an agent to know the causes of an effect. Then using a counterexample, we prove that epistemic causality is a different notion from its objective counterpart. |
| Tasks | |
| Published | 2019-10-31 |
| URL | https://arxiv.org/abs/1910.14217v1 |
| https://arxiv.org/pdf/1910.14217v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-a-logical-account-of-epistemic |
| Repo | |
| Framework | |
Advancing Speech Recognition With No Speech Or With Noisy Speech
| Title | Advancing Speech Recognition With No Speech Or With Noisy Speech |
| Authors | Gautam Krishna, Co Tran, Mason Carnahan, Ahmed H Tewfik |
| Abstract | In this paper we demonstrate end-to-end continuous speech recognition (CSR) using electroencephalography (EEG) signals with no speech signal as input. An attention model based automatic speech recognition (ASR) and connectionist temporal classification (CTC) based ASR systems were implemented for performing recognition. We further demonstrate CSR for noisy speech by fusing with EEG features. |
| Tasks | EEG, Speech Recognition |
| Published | 2019-06-17 |
| URL | https://arxiv.org/abs/1906.08871v9 |
| https://arxiv.org/pdf/1906.08871v9.pdf | |
| PWC | https://paperswithcode.com/paper/advancing-speech-recognition-with-no-speech |
| Repo | |
| Framework | |
Convergence analysis of beetle antennae search algorithm and its applications
| Title | Convergence analysis of beetle antennae search algorithm and its applications |
| Authors | Yinyan Zhang, Shuai Li, Bin Xu |
| Abstract | The beetle antennae search algorithm was recently proposed and investigated for solving global optimization problems. Although the performance of the algorithm and its variants were shown to be better than some existing meta-heuristic algorithms, there is still a lack of convergence analysis. In this paper, we provide theoretical analysis on the convergence of the beetle antennae search algorithm. We test the performance of the BAS algorithm via some representative benchmark functions. Meanwhile, some applications of the BAS algorithm are also presented. |
| Tasks | |
| Published | 2019-04-04 |
| URL | http://arxiv.org/abs/1904.02397v1 |
| http://arxiv.org/pdf/1904.02397v1.pdf | |
| PWC | https://paperswithcode.com/paper/convergence-analysis-of-beetle-antennae |
| Repo | |
| Framework | |
Patch-based Output Space Adversarial Learning for Joint Optic Disc and Cup Segmentation
| Title | Patch-based Output Space Adversarial Learning for Joint Optic Disc and Cup Segmentation |
| Authors | Shujun Wang, Lequan Yu, Xin Yang, Chi-Wing Fu, Pheng-Ann Heng |
| Abstract | Glaucoma is a leading cause of irreversible blindness. Accurate segmentation of the optic disc (OD) and cup (OC) from fundus images is beneficial to glaucoma screening and diagnosis. Recently, convolutional neural networks demonstrate promising progress in joint OD and OC segmentation. However, affected by the domain shift among different datasets, deep networks are severely hindered in generalizing across different scanners and institutions. In this paper, we present a novel patchbased Output Space Adversarial Learning framework (pOSAL) to jointly and robustly segment the OD and OC from different fundus image datasets. We first devise a lightweight and efficient segmentation network as a backbone. Considering the specific morphology of OD and OC, a novel morphology-aware segmentation loss is proposed to guide the network to generate accurate and smooth segmentation. Our pOSAL framework then exploits unsupervised domain adaptation to address the domain shift challenge by encouraging the segmentation in the target domain to be similar to the source ones. Since the whole-segmentationbased adversarial loss is insufficient to drive the network to capture segmentation details, we further design the pOSAL in a patch-based fashion to enable fine-grained discrimination on local segmentation details. We extensively evaluate our pOSAL framework and demonstrate its effectiveness in improving the segmentation performance on three public retinal fundus image datasets, i.e., Drishti-GS, RIM-ONE-r3, and REFUGE. Furthermore, our pOSAL framework achieved the first place in the OD and OC segmentation tasks in MICCAI 2018 Retinal Fundus Glaucoma Challenge. |
| Tasks | Domain Adaptation, Unsupervised Domain Adaptation |
| Published | 2019-02-20 |
| URL | http://arxiv.org/abs/1902.07519v1 |
| http://arxiv.org/pdf/1902.07519v1.pdf | |
| PWC | https://paperswithcode.com/paper/patch-based-output-space-adversarial-learning |
| Repo | |
| Framework | |
A Comprehensive Overview of Biometric Fusion
| Title | A Comprehensive Overview of Biometric Fusion |
| Authors | Maneet Singh, Richa Singh, Arun Ross |
| Abstract | The performance of a biometric system that relies on a single biometric modality (e.g., fingerprints only) is often stymied by various factors such as poor data quality or limited scalability. Multibiometric systems utilize the principle of fusion to combine information from multiple sources in order to improve recognition accuracy whilst addressing some of the limitations of single-biometric systems. The past two decades have witnessed the development of a large number of biometric fusion schemes. This paper presents an overview of biometric fusion with specific focus on three questions: what to fuse, when to fuse, and how to fuse. A comprehensive review of techniques incorporating ancillary information in the biometric recognition pipeline is also presented. In this regard, the following topics are discussed: (i) incorporating data quality in the biometric recognition pipeline; (ii) combining soft biometric attributes with primary biometric identifiers; (iii) utilizing contextual information to improve biometric recognition accuracy; and (iv) performing continuous authentication using ancillary information. In addition, the use of information fusion principles for presentation attack detection and multibiometric cryptosystems is also discussed. Finally, some of the research challenges in biometric fusion are enumerated. The purpose of this article is to provide readers a comprehensive overview of the role of information fusion in biometrics. |
| Tasks | |
| Published | 2019-02-08 |
| URL | http://arxiv.org/abs/1902.02919v1 |
| http://arxiv.org/pdf/1902.02919v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-comprehensive-overview-of-biometric-fusion |
| Repo | |
| Framework | |
Size of Interventional Markov Equivalence Classes in Random DAG Models
| Title | Size of Interventional Markov Equivalence Classes in Random DAG Models |
| Authors | Dmitriy Katz, Karthikeyan Shanmugam, Chandler Squires, Caroline Uhler |
| Abstract | Directed acyclic graph (DAG) models are popular for capturing causal relationships. From observational and interventional data, a DAG model can only be determined up to its \emph{interventional Markov equivalence class} (I-MEC). We investigate the size of MECs for random DAG models generated by uniformly sampling and ordering an Erd\H{o}s-R'{e}nyi graph. For constant density, we show that the expected $\log$ observational MEC size asymptotically (in the number of vertices) approaches a constant. We characterize I-MEC size in a similar fashion in the above settings with high precision. We show that the asymptotic expected number of interventions required to fully identify a DAG is a constant. These results are obtained by exploiting Meek rules and coupling arguments to provide sharp upper and lower bounds on the asymptotic quantities, which are then calculated numerically up to high precision. Our results have important consequences for experimental design of interventions and the development of algorithms for causal inference. |
| Tasks | Causal Inference |
| Published | 2019-03-05 |
| URL | http://arxiv.org/abs/1903.02054v1 |
| http://arxiv.org/pdf/1903.02054v1.pdf | |
| PWC | https://paperswithcode.com/paper/size-of-interventional-markov-equivalence |
| Repo | |
| Framework | |
Likelihood Assignment for Out-of-Distribution Inputs in Deep Generative Models is Sensitive to Prior Distribution Choice
| Title | Likelihood Assignment for Out-of-Distribution Inputs in Deep Generative Models is Sensitive to Prior Distribution Choice |
| Authors | Ryo Kamoi, Kei Kobayashi |
| Abstract | Recent work has shown that deep generative models assign higher likelihood to out-of-distribution inputs than to training data. We show that a factor underlying this phenomenon is a mismatch between the nature of the prior distribution and that of the data distribution, a problem found in widely used deep generative models such as VAEs and Glow. While a typical choice for a prior distribution is a standard Gaussian distribution, properties of distributions of real data sets may not be consistent with a unimodal prior distribution. This paper focuses on the relationship between the choice of a prior distribution and the likelihoods assigned to out-of-distribution inputs. We propose the use of a mixture distribution as a prior to make likelihoods assigned by deep generative models sensitive to out-of-distribution inputs. Furthermore, we explain the theoretical advantages of adopting a mixture distribution as the prior, and we present experimental results to support our claims. Finally, we demonstrate that a mixture prior lowers the out-of-distribution likelihood with respect to two pairs of real image data sets: Fashion-MNIST vs. MNIST and CIFAR10 vs. SVHN. |
| Tasks | |
| Published | 2019-11-15 |
| URL | https://arxiv.org/abs/1911.06515v1 |
| https://arxiv.org/pdf/1911.06515v1.pdf | |
| PWC | https://paperswithcode.com/paper/likelihood-assignment-for-out-of-distribution |
| Repo | |
| Framework | |
