Paper Group ANR 429
Error Metrics for Learning Reliable Manifolds from Streaming Data. Confidence-aware Levenberg-Marquardt optimization for joint motion estimation and super-resolution. Proactive Message Passing on Memory Factor Networks. Testing APSyn against Vector Cosine on Similarity Estimation. Lightweight Unsupervised Domain Adaptation by Convolutional Filter R …
Error Metrics for Learning Reliable Manifolds from Streaming Data
| Title | Error Metrics for Learning Reliable Manifolds from Streaming Data |
| Authors | Frank Schoeneman, Suchismit Mahapatra, Varun Chandola, Nils Napp, Jaroslaw Zola |
| Abstract | Spectral dimensionality reduction is frequently used to identify low-dimensional structure in high-dimensional data. However, learning manifolds, especially from the streaming data, is computationally and memory expensive. In this paper, we argue that a stable manifold can be learned using only a fraction of the stream, and the remaining stream can be mapped to the manifold in a significantly less costly manner. Identifying the transition point at which the manifold is stable is the key step. We present error metrics that allow us to identify the transition point for a given stream by quantitatively assessing the quality of a manifold learned using Isomap. We further propose an efficient mapping algorithm, called S-Isomap, that can be used to map new samples onto the stable manifold. We describe experiments on a variety of data sets that show that the proposed approach is computationally efficient without sacrificing accuracy. |
| Tasks | Dimensionality Reduction |
| Published | 2016-11-13 |
| URL | http://arxiv.org/abs/1611.04067v2 |
| http://arxiv.org/pdf/1611.04067v2.pdf | |
| PWC | https://paperswithcode.com/paper/error-metrics-for-learning-reliable-manifolds |
| Repo | |
| Framework | |
Confidence-aware Levenberg-Marquardt optimization for joint motion estimation and super-resolution
| Title | Confidence-aware Levenberg-Marquardt optimization for joint motion estimation and super-resolution |
| Authors | Cosmin Bercea, Andreas Maier, Thomas Köhler |
| Abstract | Motion estimation across low-resolution frames and the reconstruction of high-resolution images are two coupled subproblems of multi-frame super-resolution. This paper introduces a new joint optimization approach for motion estimation and image reconstruction to address this interdependence. Our method is formulated via non-linear least squares optimization and combines two principles of robust super-resolution. First, to enhance the robustness of the joint estimation, we propose a confidence-aware energy minimization framework augmented with sparse regularization. Second, we develop a tailor-made Levenberg-Marquardt iteration scheme to jointly estimate motion parameters and the high-resolution image along with the corresponding model confidence parameters. Our experiments on simulated and real images confirm that the proposed approach outperforms decoupled motion estimation and image reconstruction as well as related state-of-the-art joint estimation algorithms. |
| Tasks | Image Reconstruction, Motion Estimation, Multi-Frame Super-Resolution, Super-Resolution |
| Published | 2016-09-06 |
| URL | http://arxiv.org/abs/1609.01524v1 |
| http://arxiv.org/pdf/1609.01524v1.pdf | |
| PWC | https://paperswithcode.com/paper/confidence-aware-levenberg-marquardt |
| Repo | |
| Framework | |
Proactive Message Passing on Memory Factor Networks
| Title | Proactive Message Passing on Memory Factor Networks |
| Authors | Patrick Eschenfeldt, Dan Schmidt, Stark Draper, Jonathan Yedidia |
| Abstract | We introduce a new type of graphical model that we call a “memory factor network” (MFN). We show how to use MFNs to model the structure inherent in many types of data sets. We also introduce an associated message-passing style algorithm called “proactive message passing”’ (PMP) that performs inference on MFNs. PMP comes with convergence guarantees and is efficient in comparison to competing algorithms such as variants of belief propagation. We specialize MFNs and PMP to a number of distinct types of data (discrete, continuous, labelled) and inference problems (interpolation, hypothesis testing), provide examples, and discuss approaches for efficient implementation. |
| Tasks | |
| Published | 2016-01-18 |
| URL | http://arxiv.org/abs/1601.04667v1 |
| http://arxiv.org/pdf/1601.04667v1.pdf | |
| PWC | https://paperswithcode.com/paper/proactive-message-passing-on-memory-factor |
| Repo | |
| Framework | |
Testing APSyn against Vector Cosine on Similarity Estimation
| Title | Testing APSyn against Vector Cosine on Similarity Estimation |
| Authors | Enrico Santus, Emmanuele Chersoni, Alessandro Lenci, Chu-Ren Huang, Philippe Blache |
| Abstract | In Distributional Semantic Models (DSMs), Vector Cosine is widely used to estimate similarity between word vectors, although this measure was noticed to suffer from several shortcomings. The recent literature has proposed other methods which attempt to mitigate such biases. In this paper, we intend to investigate APSyn, a measure that computes the extent of the intersection between the most associated contexts of two target words, weighting it by context relevance. We evaluated this metric in a similarity estimation task on several popular test sets, and our results show that APSyn is in fact highly competitive, even with respect to the results reported in the literature for word embeddings. On top of it, APSyn addresses some of the weaknesses of Vector Cosine, performing well also on genuine similarity estimation. |
| Tasks | Word Embeddings |
| Published | 2016-08-27 |
| URL | http://arxiv.org/abs/1608.07738v2 |
| http://arxiv.org/pdf/1608.07738v2.pdf | |
| PWC | https://paperswithcode.com/paper/testing-apsyn-against-vector-cosine-on |
| Repo | |
| Framework | |
Lightweight Unsupervised Domain Adaptation by Convolutional Filter Reconstruction
| Title | Lightweight Unsupervised Domain Adaptation by Convolutional Filter Reconstruction |
| Authors | Rahaf Aljundi, Tinne Tuytelaars |
| Abstract | End-to-end learning methods have achieved impressive results in many areas of computer vision. At the same time, these methods still suffer from a degradation in performance when testing on new datasets that stem from a different distribution. This is known as the domain shift effect. Recently proposed adaptation methods focus on retraining the network parameters. However, this requires access to all (labeled) source data, a large amount of (unlabeled) target data, and plenty of computational resources. In this work, we propose a lightweight alternative, that allows adapting to the target domain based on a limited number of target samples in a matter of minutes rather than hours, days or even weeks. To this end, we first analyze the output of each convolutional layer from a domain adaptation perspective. Surprisingly, we find that already at the very first layer, domain shift effects pop up. We then propose a new domain adaptation method, where first layer convolutional filters that are badly affected by the domain shift are reconstructed based on less affected ones. This improves the performance of the deep network on various benchmark datasets. |
| Tasks | Domain Adaptation, Unsupervised Domain Adaptation |
| Published | 2016-03-23 |
| URL | http://arxiv.org/abs/1603.07234v1 |
| http://arxiv.org/pdf/1603.07234v1.pdf | |
| PWC | https://paperswithcode.com/paper/lightweight-unsupervised-domain-adaptation-by |
| Repo | |
| Framework | |
Proceedings of the 2016 ICML Workshop on #Data4Good: Machine Learning in Social Good Applications
| Title | Proceedings of the 2016 ICML Workshop on #Data4Good: Machine Learning in Social Good Applications |
| Authors | Kush R. Varshney |
| Abstract | This is the Proceedings of the ICML Workshop on #Data4Good: Machine Learning in Social Good Applications, which was held on June 24, 2016 in New York. |
| Tasks | |
| Published | 2016-07-08 |
| URL | http://arxiv.org/abs/1607.02450v2 |
| http://arxiv.org/pdf/1607.02450v2.pdf | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-2016-icml-workshop-on-1 |
| Repo | |
| Framework | |
Play and Learn: Using Video Games to Train Computer Vision Models
| Title | Play and Learn: Using Video Games to Train Computer Vision Models |
| Authors | Alireza Shafaei, James J. Little, Mark Schmidt |
| Abstract | Video games are a compelling source of annotated data as they can readily provide fine-grained groundtruth for diverse tasks. However, it is not clear whether the synthetically generated data has enough resemblance to the real-world images to improve the performance of computer vision models in practice. We present experiments assessing the effectiveness on real-world data of systems trained on synthetic RGB images that are extracted from a video game. We collected over 60000 synthetic samples from a modern video game with similar conditions to the real-world CamVid and Cityscapes datasets. We provide several experiments to demonstrate that the synthetically generated RGB images can be used to improve the performance of deep neural networks on both image segmentation and depth estimation. These results show that a convolutional network trained on synthetic data achieves a similar test error to a network that is trained on real-world data for dense image classification. Furthermore, the synthetically generated RGB images can provide similar or better results compared to the real-world datasets if a simple domain adaptation technique is applied. Our results suggest that collaboration with game developers for an accessible interface to gather data is potentially a fruitful direction for future work in computer vision. |
| Tasks | Depth Estimation, Domain Adaptation, Image Classification, Semantic Segmentation |
| Published | 2016-08-05 |
| URL | http://arxiv.org/abs/1608.01745v2 |
| http://arxiv.org/pdf/1608.01745v2.pdf | |
| PWC | https://paperswithcode.com/paper/play-and-learn-using-video-games-to-train |
| Repo | |
| Framework | |
SaberLDA: Sparsity-Aware Learning of Topic Models on GPUs
| Title | SaberLDA: Sparsity-Aware Learning of Topic Models on GPUs |
| Authors | Kaiwei Li, Jianfei Chen, Wenguang Chen, Jun Zhu |
| Abstract | Latent Dirichlet Allocation (LDA) is a popular tool for analyzing discrete count data such as text and images. Applications require LDA to handle both large datasets and a large number of topics. Though distributed CPU systems have been used, GPU-based systems have emerged as a promising alternative because of the high computational power and memory bandwidth of GPUs. However, existing GPU-based LDA systems cannot support a large number of topics because they use algorithms on dense data structures whose time and space complexity is linear to the number of topics. In this paper, we propose SaberLDA, a GPU-based LDA system that implements a sparsity-aware algorithm to achieve sublinear time complexity and scales well to learn a large number of topics. To address the challenges introduced by sparsity, we propose a novel data layout, a new warp-based sampling kernel, and an efficient sparse count matrix updating algorithm that improves locality, makes efficient utilization of GPU warps, and reduces memory consumption. Experiments show that SaberLDA can learn from billions-token-scale data with up to 10,000 topics, which is almost two orders of magnitude larger than that of the previous GPU-based systems. With a single GPU card, SaberLDA is able to learn 10,000 topics from a dataset of billions of tokens in a few hours, which is only achievable with clusters with tens of machines before. |
| Tasks | Topic Models |
| Published | 2016-10-08 |
| URL | http://arxiv.org/abs/1610.02496v2 |
| http://arxiv.org/pdf/1610.02496v2.pdf | |
| PWC | https://paperswithcode.com/paper/saberlda-sparsity-aware-learning-of-topic |
| Repo | |
| Framework | |
Sequential Principal Curves Analysis
| Title | Sequential Principal Curves Analysis |
| Authors | Valero Laparra, Jesus Malo |
| Abstract | This work includes all the technical details of the Sequential Principal Curves Analysis (SPCA) in a single document. SPCA is an unsupervised nonlinear and invertible feature extraction technique. The identified curvilinear features can be interpreted as a set of nonlinear sensors: the response of each sensor is the projection onto the corresponding feature. Moreover, it can be easily tuned for different optimization criteria; e.g. infomax, error minimization, decorrelation; by choosing the right way to measure distances along each curvilinear feature. Even though proposed in [Laparra et al. Neural Comp. 12] and shown to work in multiple modalities in [Laparra and Malo Frontiers Hum. Neuro. 15], the SPCA framework has its original roots in the nonlinear ICA algorithm in [Malo and Gutierrez Network 06]. Later on, the SPCA philosophy for nonlinear generalization of PCA originated substantially faster alternatives at the cost of introducing different constraints in the model. Namely, the Principal Polynomial Analysis (PPA) [Laparra et al. IJNS 14], and the Dimensionality Reduction via Regression (DRR) [Laparra et al. IEEE TGRS 15]. This report illustrates the reasons why we developed such family and is the appropriate technical companion for the missing details in [Laparra et al., NeCo 12, Laparra and Malo, Front.Hum.Neuro. 15]. See also the data, code and examples in the dedicated sites http://isp.uv.es/spca.html and http://isp.uv.es/after effects.html |
| Tasks | Dimensionality Reduction |
| Published | 2016-06-02 |
| URL | http://arxiv.org/abs/1606.00856v1 |
| http://arxiv.org/pdf/1606.00856v1.pdf | |
| PWC | https://paperswithcode.com/paper/sequential-principal-curves-analysis |
| Repo | |
| Framework | |
Towards Learning and Verifying Invariants of Cyber-Physical Systems by Code Mutation
| Title | Towards Learning and Verifying Invariants of Cyber-Physical Systems by Code Mutation |
| Authors | Yuqi Chen, Christopher M. Poskitt, Jun Sun |
| Abstract | Cyber-physical systems (CPS), which integrate algorithmic control with physical processes, often consist of physically distributed components communicating over a network. A malfunctioning or compromised component in such a CPS can lead to costly consequences, especially in the context of public infrastructure. In this short paper, we argue for the importance of constructing invariants (or models) of the physical behaviour exhibited by CPS, motivated by their applications to the control, monitoring, and attestation of components. To achieve this despite the inherent complexity of CPS, we propose a new technique for learning invariants that combines machine learning with ideas from mutation testing. We present a preliminary study on a water treatment system that suggests the efficacy of this approach, propose strategies for establishing confidence in the correctness of invariants, then summarise some research questions and the steps we are taking to investigate them. |
| Tasks | |
| Published | 2016-09-06 |
| URL | http://arxiv.org/abs/1609.01491v1 |
| http://arxiv.org/pdf/1609.01491v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-learning-and-verifying-invariants-of |
| Repo | |
| Framework | |
Multilingual Visual Sentiment Concept Matching
| Title | Multilingual Visual Sentiment Concept Matching |
| Authors | Nikolaos Pappas, Miriam Redi, Mercan Topkara, Brendan Jou, Hongyi Liu, Tao Chen, Shih-Fu Chang |
| Abstract | The impact of culture in visual emotion perception has recently captured the attention of multimedia research. In this study, we pro- vide powerful computational linguistics tools to explore, retrieve and browse a dataset of 16K multilingual affective visual concepts and 7.3M Flickr images. First, we design an effective crowdsourc- ing experiment to collect human judgements of sentiment connected to the visual concepts. We then use word embeddings to repre- sent these concepts in a low dimensional vector space, allowing us to expand the meaning around concepts, and thus enabling insight about commonalities and differences among different languages. We compare a variety of concept representations through a novel evaluation task based on the notion of visual semantic relatedness. Based on these representations, we design clustering schemes to group multilingual visual concepts, and evaluate them with novel metrics based on the crowdsourced sentiment annotations as well as visual semantic relatedness. The proposed clustering framework enables us to analyze the full multilingual dataset in-depth and also show an application on a facial data subset, exploring cultural in- sights of portrait-related affective visual concepts. |
| Tasks | Word Embeddings |
| Published | 2016-06-07 |
| URL | http://arxiv.org/abs/1606.02276v1 |
| http://arxiv.org/pdf/1606.02276v1.pdf | |
| PWC | https://paperswithcode.com/paper/multilingual-visual-sentiment-concept |
| Repo | |
| Framework | |
Human-Agent Decision-making: Combining Theory and Practice
| Title | Human-Agent Decision-making: Combining Theory and Practice |
| Authors | Sarit Kraus |
| Abstract | Extensive work has been conducted both in game theory and logic to model strategic interaction. An important question is whether we can use these theories to design agents for interacting with people? On the one hand, they provide a formal design specification for agent strategies. On the other hand, people do not necessarily adhere to playing in accordance with these strategies, and their behavior is affected by a multitude of social and psychological factors. In this paper we will consider the question of whether strategies implied by theories of strategic behavior can be used by automated agents that interact proficiently with people. We will focus on automated agents that we built that need to interact with people in two negotiation settings: bargaining and deliberation. For bargaining we will study game-theory based equilibrium agents and for argumentation we will discuss logic-based argumentation theory. We will also consider security games and persuasion games and will discuss the benefits of using equilibrium based agents. |
| Tasks | Decision Making |
| Published | 2016-06-24 |
| URL | http://arxiv.org/abs/1606.07514v1 |
| http://arxiv.org/pdf/1606.07514v1.pdf | |
| PWC | https://paperswithcode.com/paper/human-agent-decision-making-combining-theory |
| Repo | |
| Framework | |
Modeling Missing Data in Clinical Time Series with RNNs
| Title | Modeling Missing Data in Clinical Time Series with RNNs |
| Authors | Zachary C. Lipton, David C. Kale, Randall Wetzel |
| Abstract | We demonstrate a simple strategy to cope with missing data in sequential inputs, addressing the task of multilabel classification of diagnoses given clinical time series. Collected from the pediatric intensive care unit (PICU) at Children’s Hospital Los Angeles, our data consists of multivariate time series of observations. The measurements are irregularly spaced, leading to missingness patterns in temporally discretized sequences. While these artifacts are typically handled by imputation, we achieve superior predictive performance by treating the artifacts as features. Unlike linear models, recurrent neural networks can realize this improvement using only simple binary indicators of missingness. For linear models, we show an alternative strategy to capture this signal. Training models on missingness patterns only, we show that for some diseases, what tests are run can be as predictive as the results themselves. |
| Tasks | Imputation, Time Series |
| Published | 2016-06-13 |
| URL | http://arxiv.org/abs/1606.04130v5 |
| http://arxiv.org/pdf/1606.04130v5.pdf | |
| PWC | https://paperswithcode.com/paper/modeling-missing-data-in-clinical-time-series |
| Repo | |
| Framework | |
Fuzzy Maximum Satisfiability
| Title | Fuzzy Maximum Satisfiability |
| Authors | Mohamed El Halaby, Areeg Abdalla |
| Abstract | In this paper, we extend the Maximum Satisfiability (MaxSAT) problem to {\L}ukasiewicz logic. The MaxSAT problem for a set of formulae {\Phi} is the problem of finding an assignment to the variables in {\Phi} that satisfies the maximum number of formulae. Three possible solutions (encodings) are proposed to the new problem: (1) Disjunctive Linear Relations (DLRs), (2) Mixed Integer Linear Programming (MILP) and (3) Weighted Constraint Satisfaction Problem (WCSP). Like its Boolean counterpart, the extended fuzzy MaxSAT will have numerous applications in optimization problems that involve vagueness. |
| Tasks | |
| Published | 2016-02-06 |
| URL | http://arxiv.org/abs/1602.02211v1 |
| http://arxiv.org/pdf/1602.02211v1.pdf | |
| PWC | https://paperswithcode.com/paper/fuzzy-maximum-satisfiability |
| Repo | |
| Framework | |
De-Hashing: Server-Side Context-Aware Feature Reconstruction for Mobile Visual Search
| Title | De-Hashing: Server-Side Context-Aware Feature Reconstruction for Mobile Visual Search |
| Authors | Yin-Hsi Kuo, Winston H. Hsu |
| Abstract | Due to the prevalence of mobile devices, mobile search becomes a more convenient way than desktop search. Different from the traditional desktop search, mobile visual search needs more consideration for the limited resources on mobile devices (e.g., bandwidth, computing power, and memory consumption). The state-of-the-art approaches show that bag-of-words (BoW) model is robust for image and video retrieval; however, the large vocabulary tree might not be able to be loaded on the mobile device. We observe that recent works mainly focus on designing compact feature representations on mobile devices for bandwidth-limited network (e.g., 3G) and directly adopt feature matching on remote servers (cloud). However, the compact (binary) representation might fail to retrieve target objects (images, videos). Based on the hashed binary codes, we propose a de-hashing process that reconstructs BoW by leveraging the computing power of remote servers. To mitigate the information loss from binary codes, we further utilize contextual information (e.g., GPS) to reconstruct a context-aware BoW for better retrieval results. Experiment results show that the proposed method can achieve competitive retrieval accuracy as BoW while only transmitting few bits from mobile devices. |
| Tasks | Video Retrieval |
| Published | 2016-06-29 |
| URL | http://arxiv.org/abs/1606.08999v1 |
| http://arxiv.org/pdf/1606.08999v1.pdf | |
| PWC | https://paperswithcode.com/paper/de-hashing-server-side-context-aware-feature |
| Repo | |
| Framework | |
