Paper Group ANR 293
Learning partially ranked data based on graph regularization. Visualizing Semantic Structures of Sequential Data by Learning Temporal Dependencies. Efficient two step optimization for large embedded deformation graph based SLAM. Joint Segmentation and Path Classification of Curvilinear Structures. Confidence Regions in Wasserstein Distributionally …
Learning partially ranked data based on graph regularization
| Title | Learning partially ranked data based on graph regularization |
| Authors | Kento Nakamura, Keisuke Yano, Fumiyasu Komaki |
| Abstract | Ranked data appear in many different applications, including voting and consumer surveys. There often exhibits a situation in which data are partially ranked. Partially ranked data is thought of as missing data. This paper addresses parameter estimation for partially ranked data under a (possibly) non-ignorable missing mechanism. We propose estimators for both complete rankings and missing mechanisms together with a simple estimation procedure. Our estimation procedure leverages a graph regularization in conjunction with the Expectation-Maximization algorithm. Our estimation procedure is theoretically guaranteed to have the convergence properties. We reduce a modeling bias by allowing a non-ignorable missing mechanism. In addition, we avoid the inherent complexity within a non-ignorable missing mechanism by introducing a graph regularization. The experimental results demonstrate that the proposed estimators work well under non-ignorable missing mechanisms. |
| Tasks | |
| Published | 2019-02-28 |
| URL | http://arxiv.org/abs/1902.10963v1 |
| http://arxiv.org/pdf/1902.10963v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-partially-ranked-data-based-on-graph |
| Repo | |
| Framework | |
Visualizing Semantic Structures of Sequential Data by Learning Temporal Dependencies
| Title | Visualizing Semantic Structures of Sequential Data by Learning Temporal Dependencies |
| Authors | Kyoung-Woon On, Eun-Sol Kim, Yu-Jung Heo, Byoung-Tak Zhang |
| Abstract | While conventional methods for sequential learning focus on interaction between consecutive inputs, we suggest a new method which captures composite semantic flows with variable-length dependencies. In addition, the semantic structures within given sequential data can be interpreted by visualizing temporal dependencies learned from the method. The proposed method, called Temporal Dependency Network (TDN), represents a video as a temporal graph whose node represents a frame of the video and whose edge represents the temporal dependency between two frames of a variable distance. The temporal dependency structure of semantic is discovered by learning parameterized kernels of graph convolutional methods. We evaluate the proposed method on the large-scale video dataset, Youtube-8M. By visualizing the temporal dependency structures as experimental results, we show that the suggested method can find the temporal dependency structures of video semantic. |
| Tasks | |
| Published | 2019-01-20 |
| URL | http://arxiv.org/abs/1901.09066v1 |
| http://arxiv.org/pdf/1901.09066v1.pdf | |
| PWC | https://paperswithcode.com/paper/visualizing-semantic-structures-of-sequential |
| Repo | |
| Framework | |
Efficient two step optimization for large embedded deformation graph based SLAM
| Title | Efficient two step optimization for large embedded deformation graph based SLAM |
| Authors | Jingwei Song, Fang Bai, Liang Zhao, Shoudong Huang, Rong Xiong |
| Abstract | Embedded deformation nodes based formulation has been widely applied in deformable geometry and graphical problems. Though being promising in stereo (or RGBD) sensor based SLAM applications, it remains challenging to keep constant speed in deformation nodes parameter estimation when model grows larger. In practice, the processing time grows rapidly in accordance with the expansion of maps. In this paper, we propose an approach to decouple nodes of deformation graph in large scale dense deformable SLAM and keep the estimation time to be constant. We observe that only partial deformable nodes in the graph are connected to visible points. Based on this fact, sparsity of original Hessian matrix is utilized to split parameter estimation in two independent steps. With this new technique, we achieve faster parameter estimation with amortized computation complexity reduced from O(n^2) to closing O(1). As a result, the computation cost barely increases as the map keeps growing. Based on our strategy, computational bottleneck in large scale embedded deformation graph based applications will be greatly mitigated. The effectiveness is validated by experiments, featuring large scale deformation scenarios. |
| Tasks | |
| Published | 2019-06-20 |
| URL | https://arxiv.org/abs/1906.08477v2 |
| https://arxiv.org/pdf/1906.08477v2.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-two-step-optimization-for-large |
| Repo | |
| Framework | |
Joint Segmentation and Path Classification of Curvilinear Structures
| Title | Joint Segmentation and Path Classification of Curvilinear Structures |
| Authors | Agata Mosinska, Mateusz Kozinski, Pascal Fua |
| Abstract | Detection of curvilinear structures in images has long been of interest. One of the most challenging aspects of this problem is inferring the graph representation of the curvilinear network. Most existing delineation approaches first perform binary segmentation of the image and then refine it using either a set of hand-designed heuristics or a separate classifier that assigns likelihood to paths extracted from the pixel-wise prediction. In our work, we bridge the gap between segmentation and path classification by training a deep network that performs those two tasks simultaneously. We show that this approach is beneficial because it enforces consistency across the whole processing pipeline. We apply our approach on roads and neurons datasets. |
| Tasks | |
| Published | 2019-05-09 |
| URL | https://arxiv.org/abs/1905.03892v1 |
| https://arxiv.org/pdf/1905.03892v1.pdf | |
| PWC | https://paperswithcode.com/paper/joint-segmentation-and-path-classification-of |
| Repo | |
| Framework | |
Confidence Regions in Wasserstein Distributionally Robust Estimation
| Title | Confidence Regions in Wasserstein Distributionally Robust Estimation |
| Authors | Jose Blanchet, Karthyek Murthy, Nian Si |
| Abstract | Wasserstein distributionally robust optimization (DRO) estimators are obtained as solutions of min-max problems in which the statistician selects a parameter minimizing the worst-case loss among all probability models within a certain distance (in a Wasserstein sense) from the underlying empirical measure. While motivated by the need to identify model parameters (or) decision choices that are robust to model uncertainties and misspecification, the Wasserstein DRO estimators recover a wide range of regularized estimators, including square-root LASSO and support vector machines, among others, as particular cases. This paper studies the asymptotic normality of underlying DRO estimators as well as the properties of an optimal (in a suitable sense) confidence region induced by the Wasserstein DRO formulation. |
| Tasks | |
| Published | 2019-06-04 |
| URL | https://arxiv.org/abs/1906.01614v1 |
| https://arxiv.org/pdf/1906.01614v1.pdf | |
| PWC | https://paperswithcode.com/paper/confidence-regions-in-wasserstein |
| Repo | |
| Framework | |
Cascaded Structure Tensor Framework for Robust Identification of Heavily Occluded Baggage Items from Multi-Vendor X-ray Scans
| Title | Cascaded Structure Tensor Framework for Robust Identification of Heavily Occluded Baggage Items from Multi-Vendor X-ray Scans |
| Authors | Taimur Hassan, Salman H. Khan, Samet Akcay, Mohammed Bennamoun, Naoufel Werghi |
| Abstract | In the last two decades, luggage scanning has globally become one of the prime aviation security concerns. Manual screening of the baggage items is a cumbersome, subjective and inefficient process. Hence, many researchers have developed Xray imagery-based autonomous systems to address these shortcomings. However, to the best of our knowledge, there is no framework, up to now, that can recognize heavily occluded and cluttered baggage items from multi-vendor X-ray scans. This paper presents a cascaded structure tensor framework which can automatically extract and recognize suspicious items irrespective of their position and orientation in the multi-vendor X-ray scans. The proposed framework is unique, as it intelligently extracts each object by iteratively picking contour based transitional information from different orientations and uses only a single feedforward convolutional neural network for the recognition. The proposed framework has been rigorously tested on publicly available GDXray and SIXray datasets containing a total of 1,067,381 X-ray scans where it significantly outperformed the state-of-the-art solutions by achieving the mean average precision score of 0.9343 and 0.9595 for extracting and recognizing suspicious items from GDXray and SIXray scans, respectively. Furthermore, the proposed framework has achieved 15.78% better time |
| Tasks | |
| Published | 2019-12-09 |
| URL | https://arxiv.org/abs/1912.04251v2 |
| https://arxiv.org/pdf/1912.04251v2.pdf | |
| PWC | https://paperswithcode.com/paper/deep-cmst-framework-for-the-autonomous |
| Repo | |
| Framework | |
Suggestion Mining from Online Reviews using ULMFiT
| Title | Suggestion Mining from Online Reviews using ULMFiT |
| Authors | Sarthak Anand, Debanjan Mahata, Kartik Aggarwal, Laiba Mehnaz, Simra Shahid, Haimin Zhang, Yaman Kumar, Rajiv Ratn Shah, Karan Uppal |
| Abstract | In this paper we present our approach and the system description for Sub Task A of SemEval 2019 Task 9: Suggestion Mining from Online Reviews and Forums. Given a sentence, the task asks to predict whether the sentence consists of a suggestion or not. Our model is based on Universal Language Model Fine-tuning for Text Classification. We apply various pre-processing techniques before training the language and the classification model. We further provide detailed analysis of the results obtained using the trained model. Our team ranked 10th out of 34 participants, achieving an F1 score of 0.7011. We publicly share our implementation at https://github.com/isarth/SemEval9_MIDAS |
| Tasks | Language Modelling, Text Classification |
| Published | 2019-04-19 |
| URL | http://arxiv.org/abs/1904.09076v1 |
| http://arxiv.org/pdf/1904.09076v1.pdf | |
| PWC | https://paperswithcode.com/paper/suggestion-mining-from-online-reviews-using |
| Repo | |
| Framework | |
Low Resource Text Classification with ULMFit and Backtranslation
| Title | Low Resource Text Classification with ULMFit and Backtranslation |
| Authors | Sam Shleifer |
| Abstract | In computer vision, virtually every state-of-the-art deep learning system is trained with data augmentation. In text classification, however, data augmentation is less widely practiced because it must be performed before training and risks introducing label noise. We augment the IMDB movie reviews dataset with examples generated by two families of techniques: random token perturbations introduced by Wei and Zou [2019] and backtranslation – translating to a second language then back to English. In low resource environments, backtranslation generates significant improvement on top of the state of-the-art ULMFit model. A ULMFit model pretrained on wikitext103 and then fine-tuned on only 50 IMDB examples and 500 synthetic examples generated by backtranslation achieves 80.6% accuracy, an 8.1% improvement over the augmentation-free baseline with only 9 minutes of additional training time. Random token perturbations do not yield any improvements but incur equivalent computational cost. The benefits of training with backtranslated examples decreases with the size of the available training data. On the full dataset, neither augmentation technique improves upon ULMFit’s state of the art performance. We address this by using backtranslations as a form of test time augmentation as well as ensembling ULMFit with other models, and achieve small improvements. |
| Tasks | Data Augmentation, Text Classification |
| Published | 2019-03-21 |
| URL | http://arxiv.org/abs/1903.09244v2 |
| http://arxiv.org/pdf/1903.09244v2.pdf | |
| PWC | https://paperswithcode.com/paper/low-resource-text-classification-with-ulmfit |
| Repo | |
| Framework | |
Functional Bayesian Filter
| Title | Functional Bayesian Filter |
| Authors | Kan Li, Jose C. Principe |
| Abstract | We present a general nonlinear Bayesian filter for high-dimensional state estimation using the theory of reproducing kernel Hilbert space (RKHS). Applying kernel method and the representer theorem to perform linear quadratic estimation in a functional space, we derive a Bayesian recursive state estimator for a general nonlinear dynamical system in the original input space. Unlike existing nonlinear extensions of Kalman filter where the system dynamics are assumed known, the state-space representation for the Functional Bayesian Filter (FBF) is completely learned from measurement data in the form of an infinite impulse response (IIR) filter or recurrent network in the RKHS, with universal approximation property. Using positive definite kernel function satisfying Mercer’s conditions to compute and evolve information quantities, the FBF exploits both the statistical and time-domain information about the signal, extracts higher-order moments, and preserves the properties of covariances without the ill effects due to conventional arithmetic operations. This novel kernel adaptive filtering algorithm is applied to recurrent network training, chaotic time-series estimation and cooperative filtering using Gaussian and non-Gaussian noises, and inverse kinematics modeling. Simulation results show FBF outperforms existing Kalman-based algorithms. |
| Tasks | Time Series |
| Published | 2019-11-24 |
| URL | https://arxiv.org/abs/1911.10606v1 |
| https://arxiv.org/pdf/1911.10606v1.pdf | |
| PWC | https://paperswithcode.com/paper/functional-bayesian-filter |
| Repo | |
| Framework | |
3DRegNet: A Deep Neural Network for 3D Point Registration
| Title | 3DRegNet: A Deep Neural Network for 3D Point Registration |
| Authors | G. Dias Pais, Pedro Miraldo, Srikumar Ramalingam, Venu Madhav Govindu, Jacinto C. Nascimento, Rama Chellappa |
| Abstract | We present 3DRegNet, a deep learning algorithm for the registration of 3D scans. With the recent emergence of inexpensive 3D commodity sensors, it would be beneficial to develop a learning based 3D registration algorithm. Given a set of 3D point correspondences, we build a deep neural network using deep residual layers and convolutional layers to achieve two tasks: (1) classification of the point correspondences into correct/incorrect ones, and (2) regression of the motion parameters that can align the scans into a common reference frame. 3DRegNet has several advantages over classical methods. First, since 3DRegNet works on point correspondences and not on the original scans, our approach is significantly faster than many conventional approaches. Second, we show that the algorithm can be extended for multi-view scenarios, i.e., simultaneous handling of the registration for more than two scans. In contrast to pose regression networks that employ four variables to represent rotation using quaternions, we use Lie algebra to represent the rotation using only three variables. Extensive experiments on two challenging datasets (i.e. ICL-NUIM and SUN3D) demonstrate that we outperform other methods and achieve state-of-the-art results. The code will be made available. |
| Tasks | |
| Published | 2019-04-02 |
| URL | http://arxiv.org/abs/1904.01701v1 |
| http://arxiv.org/pdf/1904.01701v1.pdf | |
| PWC | https://paperswithcode.com/paper/3dregnet-a-deep-neural-network-for-3d-point |
| Repo | |
| Framework | |
[Re] Learning to Learn By Self-Critique
| Title | [Re] Learning to Learn By Self-Critique |
| Authors | Isac Arnekvist, Dmytro Kalpakchi |
| Abstract | This work is a reproducibility study of the paper of Antoniou and Storkey [2019], published at NeurIPS 2019. Our results are in parts similar to the ones reported in the original paper, supporting the central claim of the paper that the proposed novel method, called Self-Critique and Adapt (SCA), improves the performance of MAML++. The conducted additional experiments on the Caltech-UCSD Birds 200 dataset confirm the superiority of SCA compared to MAML++. In addition, the reproduced paper suggests a novel high-end version of MAML++ for which we could not reproduce the same results. We hypothesize that this is due to the many implementation details that were omitted in the original paper. |
| Tasks | |
| Published | 2019-11-30 |
| URL | https://arxiv.org/abs/1912.00183v2 |
| https://arxiv.org/pdf/1912.00183v2.pdf | |
| PWC | https://paperswithcode.com/paper/re-learning-to-learn-by-self-critique |
| Repo | |
| Framework | |
Invariant Representations through Adversarial Forgetting
| Title | Invariant Representations through Adversarial Forgetting |
| Authors | Ayush Jaiswal, Daniel Moyer, Greg Ver Steeg, Wael AbdAlmageed, Premkumar Natarajan |
| Abstract | We propose a novel approach to achieving invariance for deep neural networks in the form of inducing amnesia to unwanted factors of data through a new adversarial forgetting mechanism. We show that the forgetting mechanism serves as an information-bottleneck, which is manipulated by the adversarial training to learn invariance to unwanted factors. Empirical results show that the proposed framework achieves state-of-the-art performance at learning invariance in both nuisance and bias settings on a diverse collection of datasets and tasks. |
| Tasks | |
| Published | 2019-11-11 |
| URL | https://arxiv.org/abs/1911.04060v2 |
| https://arxiv.org/pdf/1911.04060v2.pdf | |
| PWC | https://paperswithcode.com/paper/invariant-representations-through-adversarial |
| Repo | |
| Framework | |
Cut-free Calculi and Relational Semantics for Temporal STIT Logics
| Title | Cut-free Calculi and Relational Semantics for Temporal STIT Logics |
| Authors | Kees van Berkel, Tim Lyon |
| Abstract | We present cut-free labelled sequent calculi for a central formalism in logics of agency: STIT logics with temporal operators. These include sequent systems for Ldm, Tstit and Xstit. All calculi presented possess essential structural properties such as contraction- and cut-admissibility. The labelled calculi G3Ldm and G3TSTIT are shown sound and complete relative to irreflexive temporal frames. Additionally, we extend current results by showing that also XSTIT can be characterized through relational frames, omitting the use of BT+AC frames. |
| Tasks | |
| Published | 2019-04-22 |
| URL | http://arxiv.org/abs/1904.09899v1 |
| http://arxiv.org/pdf/1904.09899v1.pdf | |
| PWC | https://paperswithcode.com/paper/cut-free-calculi-and-relational-semantics-for |
| Repo | |
| Framework | |
Max-C and Min-D Projection Autoassociative Fuzzy Morphological Memories: Theory and an Application for Face Recognition
| Title | Max-C and Min-D Projection Autoassociative Fuzzy Morphological Memories: Theory and an Application for Face Recognition |
| Authors | Alex Santana dos Santos, Marcos Eduardo Valle |
| Abstract | Max-C and min-D projection autoassociative fuzzy morphological memories (max-C and min-D PAFMMs) are two layer feedforward fuzzy morphological neural networks able to implement an associative memory designed for the storage and retrieval of finite fuzzy sets or vectors on a hypercube. In this paper we address the main features of these autoassociative memories, which include unlimited absolute storage capacity, fast retrieval of stored items, few spurious memories, and an excellent tolerance to either dilative noise or erosive noise. Particular attention is given to the so-called PAFMM of Zadeh which, besides performing no floating-point operations, exhibit the largest noise tolerance among max-C and min-D PAFMMs. Computational experiments reveal that Zadeh’s max-C PFAMM, combined with a noise masking strategy, yields a fast and robust classifier with strong potential for face recognition. |
| Tasks | Face Recognition |
| Published | 2019-02-11 |
| URL | https://arxiv.org/abs/1902.04144v2 |
| https://arxiv.org/pdf/1902.04144v2.pdf | |
| PWC | https://paperswithcode.com/paper/max-c-and-min-d-projection-autoassociative |
| Repo | |
| Framework | |
Reliable Multi-label Classification: Prediction with Partial Abstention
| Title | Reliable Multi-label Classification: Prediction with Partial Abstention |
| Authors | Vu-Linh Nguyen, Eyke Hüllermeier |
| Abstract | In contrast to conventional (single-label) classification, the setting of multilabel classification (MLC) allows an instance to belong to several classes simultaneously. Thus, instead of selecting a single class label, predictions take the form of a subset of all labels. In this paper, we study an extension of the setting of MLC, in which the learner is allowed to partially abstain from a prediction, that is, to deliver predictions on some but not necessarily all class labels. We propose a formalization of MLC with abstention in terms of a generalized loss minimization problem and present first results for the case of the Hamming loss, rank loss, and F-measure, both theoretical and experimental. |
| Tasks | Multi-Label Classification |
| Published | 2019-04-19 |
| URL | https://arxiv.org/abs/1904.09235v2 |
| https://arxiv.org/pdf/1904.09235v2.pdf | |
| PWC | https://paperswithcode.com/paper/reliable-multi-label-classification |
| Repo | |
| Framework | |
