Paper Group ANR 1271
SymmetricNet: A mesoscale eddy detection method based on multivariate fusion data. Translationese as a Language in “Multilingual” NMT. Accurate Robotic Pouring for Serving Drinks. ReNAS:Relativistic Evaluation of Neural Architecture Search. Riemannian joint dimensionality reduction and dictionary learning on symmetric positive definite manifold. A …
SymmetricNet: A mesoscale eddy detection method based on multivariate fusion data
| Title | SymmetricNet: A mesoscale eddy detection method based on multivariate fusion data |
| Authors | Zhenlin Fan, Guoqiang Zhong |
| Abstract | Mesoscale eddies play a significant role in marine energy transport, marine biological environment and marine climate. Due to their huge impact on the ocean, mesoscale eddy detection has become a hot research area in recent years. Therefore, more and more people are entering the field of mesoscale eddy detection. However, the existing detection methods mainly based on traditional detection methods typically only use Sea Surface Height (SSH) as a variable to detect, resulting in inaccurate performance. In this paper, we propose a mesoscale eddy detection method based on multivariate fusion data to solve this problem. We not only use the SSH variable, but also add the two variables: Sea Surface Temperature (SST) and velocity of flow, achieving a multivariate information fusion input. We design a novel symmetric network, which merges low-level feature maps from the downsampling pathway and high-level feature maps from the upsampling pathway by lateral connection. In addition, we apply dilated convolutions to network structure to increase the receptive field and obtain more contextual information in the case of constant parameter. In the end, we demonstrate the effectiveness of our method on dataset provided by us, achieving the test set performance of 97.06% , greatly improved the performance of previous methods of mesoscale eddy detection. |
| Tasks | |
| Published | 2019-09-30 |
| URL | https://arxiv.org/abs/1909.13411v1 |
| https://arxiv.org/pdf/1909.13411v1.pdf | |
| PWC | https://paperswithcode.com/paper/symmetricnet-a-mesoscale-eddy-detection |
| Repo | |
| Framework | |
Translationese as a Language in “Multilingual” NMT
| Title | Translationese as a Language in “Multilingual” NMT |
| Authors | Parker Riley, Isaac Caswell, Markus Freitag, David Grangier |
| Abstract | Machine translation has an undesirable propensity to produce “translationese” artifacts, which can lead to higher BLEU scores while being liked less by human raters. Motivated by this, we model translationese and original (i.e. natural) text as separate languages in a multilingual model, and pose the question: can we perform zero-shot translation between original source text and original target text? There is no data with original source and original target, so we train sentence-level classifiers to distinguish translationese from original target text, and use this classifier to tag the training data for an NMT model. Using this technique we bias the model to produce more natural outputs at test time, yielding gains in human evaluation scores on both accuracy and fluency. Additionally, we demonstrate that it is possible to bias the model to produce translationese and game the BLEU score, increasing it while decreasing human-rated quality. We analyze these models using metrics to measure the degree of translationese in the output, and present an analysis of the capriciousness of heuristically-based train-data tagging. |
| Tasks | Machine Translation |
| Published | 2019-11-10 |
| URL | https://arxiv.org/abs/1911.03823v1 |
| https://arxiv.org/pdf/1911.03823v1.pdf | |
| PWC | https://paperswithcode.com/paper/translationese-as-a-language-in-multilingual |
| Repo | |
| Framework | |
Accurate Robotic Pouring for Serving Drinks
| Title | Accurate Robotic Pouring for Serving Drinks |
| Authors | Yongqiang Huang, Yu Sun |
| Abstract | Pouring is the second most frequently executed motion in cooking scenarios. In this work, we present our system of accurate pouring that generates the angular velocities of the source container using recurrent neural networks. We collected demonstrations of human pouring water. We made a physical system on which the velocities of the source container were generated at each time step and executed by a motor. We tested our system on pouring water from containers that are not used for training and achieved an error of as low as 4 milliliters. We also used the system to pour oil and syrup. The accuracy achieved with oil is slightly lower than but comparable with that of water. |
| Tasks | |
| Published | 2019-06-21 |
| URL | https://arxiv.org/abs/1906.12264v1 |
| https://arxiv.org/pdf/1906.12264v1.pdf | |
| PWC | https://paperswithcode.com/paper/accurate-robotic-pouring-for-serving-drinks |
| Repo | |
| Framework | |
ReNAS:Relativistic Evaluation of Neural Architecture Search
| Title | ReNAS:Relativistic Evaluation of Neural Architecture Search |
| Authors | Yixing Xu, Yunhe Wang, Kai Han, Shangling Jui, Chunjing Xu, Qi Tian, Chang Xu |
| Abstract | An effective and efficient architecture performance evaluation scheme is essential for the success of Neural Architecture Search (NAS). To save computational cost, most of existing NAS algorithms often train and evaluate intermediate neural architectures on a small proxy dataset with limited training epochs. But it is difficult to expect an accurate performance estimation of an architecture in such a coarse evaluation way. This paper advocates a new neural architecture evaluation scheme, which aims to determine which architecture would perform better instead of accurately predict the absolute architecture performance. Therefore, we propose a \textbf{relativistic} architecture performance predictor in NAS (ReNAS). We encode neural architectures into feature tensors, and further refining the representations with the predictor. The proposed relativistic performance predictor can be deployed in discrete searching methods to search for the desired architectures without additional evaluation. Experimental results on the NASBench dataset suggests that, sampling 424 ($0.1%$ of the entire search space) neural architectures and their corresponding validation performance is already enough for learning an accurate architecture performance predictor. The accuracy of our searched neural architecture is higher than that of the state-of-the-art methods and lies in the top $0.02%$ of the whole search space. |
| Tasks | Neural Architecture Search |
| Published | 2019-09-30 |
| URL | https://arxiv.org/abs/1910.01523v4 |
| https://arxiv.org/pdf/1910.01523v4.pdf | |
| PWC | https://paperswithcode.com/paper/rnas-architecture-ranking-for-powerful |
| Repo | |
| Framework | |
Riemannian joint dimensionality reduction and dictionary learning on symmetric positive definite manifold
| Title | Riemannian joint dimensionality reduction and dictionary learning on symmetric positive definite manifold |
| Authors | Hiroyuki Kasai, Bamdev Mishra |
| Abstract | Dictionary leaning (DL) and dimensionality reduction (DR) are powerful tools to analyze high-dimensional noisy signals. This paper presents a proposal of a novel Riemannian joint dimensionality reduction and dictionary learning (R-JDRDL) on symmetric positive definite (SPD) manifolds for classification tasks. The joint learning considers the interaction between dimensionality reduction and dictionary learning procedures by connecting them into a unified framework. We exploit a Riemannian optimization framework for solving DL and DR problems jointly. Finally, we demonstrate that the proposed R-JDRDL outperforms existing state-of-the-arts algorithms when used for image classification tasks. |
| Tasks | Dictionary Learning, Dimensionality Reduction, Image Classification |
| Published | 2019-02-11 |
| URL | http://arxiv.org/abs/1902.04186v1 |
| http://arxiv.org/pdf/1902.04186v1.pdf | |
| PWC | https://paperswithcode.com/paper/riemannian-joint-dimensionality-reduction-and |
| Repo | |
| Framework | |
A Stochastic Quasi-Newton Method with Nesterov’s Accelerated Gradient
| Title | A Stochastic Quasi-Newton Method with Nesterov’s Accelerated Gradient |
| Authors | S. Indrapriyadarsini, Shahrzad Mahboubi, Hiroshi Ninomiya, Hideki Asai |
| Abstract | Incorporating second order curvature information in gradient based methods have shown to improve convergence drastically despite its computational intensity. In this paper, we propose a stochastic (online) quasi-Newton method with Nesterov’s accelerated gradient in both its full and limited memory forms for solving large scale non-convex optimization problems in neural networks. The performance of the proposed algorithm is evaluated in Tensorflow on benchmark classification and regression problems. The results show improved performance compared to the classical second order oBFGS and oLBFGS methods and popular first order stochastic methods such as SGD and Adam. The performance with different momentum rates and batch sizes have also been illustrated. |
| Tasks | |
| Published | 2019-09-09 |
| URL | https://arxiv.org/abs/1909.03621v1 |
| https://arxiv.org/pdf/1909.03621v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-stochastic-quasi-newton-method-with |
| Repo | |
| Framework | |
Implicit Diversity in Image Summarization
| Title | Implicit Diversity in Image Summarization |
| Authors | L. Elisa Celis, Vijay Keswani |
| Abstract | Case studies, such as Kay et al., 2015 have shown that in image summarization, such as with Google Image Search, the people in the results presented for occupations are more imbalanced with respect to sensitive attributes such as gender and ethnicity than the ground truth. Most of the existing approaches to correct for this problem in image summarization assume that the images are labelled and use the labels for training the model and correcting for biases. However, these labels may not always be present. Furthermore, it is often not possible (nor even desirable) to automatically classify images by sensitive attributes such as gender or race. Moreover, balancing according to the labels does not guarantee that the diversity will be visibly apparent - arguably the only metric that matters when selecting diverse images. We develop a novel approach that takes as input a visibly diverse control set of images and uses this set to produce images in response to a query which is similarly visibly diverse. We implement this approach using pre-trained and modified Convolutional Neural Networks like VGG-16, and evaluate our approach empirically on the Image dataset compiled and used by Kay et al., 2015. We compare our results with the Google Image Search results from Kay et al., 2015 and natural baselines and observe that our algorithm produces images that are accurate with respect to their similarity to the query images (on par with that of the Google Image Search results), but significantly outperforms with respect to visible diversity as measured by their similarity to our diverse control set. |
| Tasks | Image Retrieval |
| Published | 2019-01-29 |
| URL | http://arxiv.org/abs/1901.10265v1 |
| http://arxiv.org/pdf/1901.10265v1.pdf | |
| PWC | https://paperswithcode.com/paper/implicit-diversity-in-image-summarization |
| Repo | |
| Framework | |
A Self-supervised Approach to Hierarchical Forecasting with Applications to Groupwise Synthetic Controls
| Title | A Self-supervised Approach to Hierarchical Forecasting with Applications to Groupwise Synthetic Controls |
| Authors | Konstantin Mishchenko, Mallory Montgomery, Federico Vaggi |
| Abstract | When forecasting time series with a hierarchical structure, the existing state of the art is to forecast each time series independently, and, in a post-treatment step, to reconcile the time series in a way that respects the hierarchy (Hyndman et al., 2011; Wickramasuriya et al., 2018). We propose a new loss function that can be incorporated into any maximum likelihood objective with hierarchical data, resulting in reconciled estimates with confidence intervals that correctly account for additional uncertainty due to imperfect reconciliation. We evaluate our method using a non-linear model and synthetic data on a counterfactual forecasting problem, where we have access to the ground truth and contemporaneous covariates, and show that we largely improve over the existing state-of-the-art method. |
| Tasks | Time Series |
| Published | 2019-06-25 |
| URL | https://arxiv.org/abs/1906.10586v1 |
| https://arxiv.org/pdf/1906.10586v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-self-supervised-approach-to-hierarchical |
| Repo | |
| Framework | |
Graph-augmented Convolutional Networks on Drug-Drug Interactions Prediction
| Title | Graph-augmented Convolutional Networks on Drug-Drug Interactions Prediction |
| Authors | Yi Zhong, Xueyu Chen, Yu Zhao, Xiaoming Chen, Tingfang Gao, Zuquan Weng |
| Abstract | We propose an end-to-end model to predict drug-drug interactions (DDIs) by employing graph-augmented convolutional networks. And this is implemented by combining graph CNN with an attentive pooling network to extract structural relations between drug pairs and make DDI predictions. The experiment results suggest a desirable performance achieving ROC at 0.988, F1-score at 0.956, and AUPR at 0.986. Besides, the model can tell how the two DDI drugs interact structurally by varying colored atoms. And this may be helpful for drug design during drug discovery. |
| Tasks | Drug Discovery |
| Published | 2019-12-08 |
| URL | https://arxiv.org/abs/1912.03702v1 |
| https://arxiv.org/pdf/1912.03702v1.pdf | |
| PWC | https://paperswithcode.com/paper/graph-augmented-convolutional-networks-on |
| Repo | |
| Framework | |
3D landmark detection for augmented reality based otologic procedures
| Title | 3D landmark detection for augmented reality based otologic procedures |
| Authors | Raabid Hussain, Alain Lalande, Kibrom Berihu Girum, Caroline Guigou, Alexis Bozorg Grayeli |
| Abstract | Ear consists of the smallest bones in the human body and does not contain significant amount of distinct landmark points that may be used to register a preoperative CT-scan with the surgical video in an augmented reality framework. Learning based algorithms may be used to help the surgeons to identify landmark points. This paper presents a convolutional neural network approach to landmark detection in preoperative ear CT images and then discusses an augmented reality system that can be used to visualize the cochlear axis on an otologic surgical video. |
| Tasks | |
| Published | 2019-09-04 |
| URL | https://arxiv.org/abs/1909.01647v1 |
| https://arxiv.org/pdf/1909.01647v1.pdf | |
| PWC | https://paperswithcode.com/paper/3d-landmark-detection-for-augmented-reality |
| Repo | |
| Framework | |
Unfolding the Structure of a Document using Deep Learning
| Title | Unfolding the Structure of a Document using Deep Learning |
| Authors | Muhammad Mahbubur Rahman, Tim Finin |
| Abstract | Understanding and extracting of information from large documents, such as business opportunities, academic articles, medical documents and technical reports, poses challenges not present in short documents. Such large documents may be multi-themed, complex, noisy and cover diverse topics. We describe a framework that can analyze large documents and help people and computer systems locate desired information in them. We aim to automatically identify and classify different sections of documents and understand their purpose within the document. A key contribution of our research is modeling and extracting the logical and semantic structure of electronic documents using deep learning techniques. We evaluate the effectiveness and robustness of our framework through extensive experiments on two collections: more than one million scholarly articles from arXiv and a collection of requests for proposal documents from government sources. |
| Tasks | |
| Published | 2019-09-29 |
| URL | https://arxiv.org/abs/1910.03678v1 |
| https://arxiv.org/pdf/1910.03678v1.pdf | |
| PWC | https://paperswithcode.com/paper/unfolding-the-structure-of-a-document-using |
| Repo | |
| Framework | |
Relative planar motion for vehicle-mounted cameras from a single affine correspondence
| Title | Relative planar motion for vehicle-mounted cameras from a single affine correspondence |
| Authors | Levente Hajder, Daniel Barath |
| Abstract | Two solvers are proposed for estimating the extrinsic camera parameters from a single affine correspondence assuming general planar motion. In this case, the camera movement is constrained to a plane and the image plane is orthogonal to the ground. The algorithms do not assume other constraints, e.g.\ the non-holonomic one, to hold. A new minimal solver is proposed for the semi-calibrated case, i.e. the camera parameters are known except a common focal length. Another method is proposed for the fully calibrated case. Due to requiring a single correspondence, robust estimation, e.g. histogram voting, leads to a fast and accurate procedure. The proposed methods are tested in our synthetic environment and on publicly available real datasets consisting of videos through tens of kilometres. They are superior to the state-of-the-art both in terms of accuracy and processing time. |
| Tasks | |
| Published | 2019-12-13 |
| URL | https://arxiv.org/abs/1912.06465v1 |
| https://arxiv.org/pdf/1912.06465v1.pdf | |
| PWC | https://paperswithcode.com/paper/relative-planar-motion-for-vehicle-mounted |
| Repo | |
| Framework | |
Pixel-Accurate Depth Evaluation in Realistic Driving Scenarios
| Title | Pixel-Accurate Depth Evaluation in Realistic Driving Scenarios |
| Authors | Tobias Gruber, Mario Bijelic, Felix Heide, Werner Ritter, Klaus Dietmayer |
| Abstract | This work introduces an evaluation benchmark for depth estimation and completion using high-resolution depth measurements with angular resolution of up to 25” (arcsecond), akin to a 50 megapixel camera with per-pixel depth available. Existing datasets, such as the KITTI benchmark, provide only sparse reference measurements with an order of magnitude lower angular resolution - these sparse measurements are treated as ground truth by existing depth estimation methods. We propose an evaluation methodology in four characteristic automotive scenarios recorded in varying weather conditions (day, night, fog, rain). As a result, our benchmark allows us to evaluate the robustness of depth sensing methods in adverse weather and different driving conditions. Using the proposed evaluation data, we demonstrate that current stereo approaches provide significantly more stable depth estimates than monocular methods and lidar completion in adverse weather. Data and code are available at https://github.com/gruberto/PixelAccurateDepthBenchmark.git. |
| Tasks | Depth Estimation |
| Published | 2019-06-21 |
| URL | https://arxiv.org/abs/1906.08953v2 |
| https://arxiv.org/pdf/1906.08953v2.pdf | |
| PWC | https://paperswithcode.com/paper/pixel-accurate-depth-evaluation-in-realistic |
| Repo | |
| Framework | |
Learning Portable Representations for High-Level Planning
| Title | Learning Portable Representations for High-Level Planning |
| Authors | Steven James, Benjamin Rosman, George Konidaris |
| Abstract | We present a framework for autonomously learning a portable representation that describes a collection of low-level continuous environments. We show that these abstract representations can be learned in a task-independent egocentric space specific to the agent that, when grounded with problem-specific information, are provably sufficient for planning. We demonstrate transfer in two different domains, where an agent learns a portable, task-independent symbolic vocabulary, as well as rules expressed in that vocabulary, and then learns to instantiate those rules on a per-task basis. This reduces the number of samples required to learn a representation of a new task. |
| Tasks | |
| Published | 2019-05-28 |
| URL | https://arxiv.org/abs/1905.12006v1 |
| https://arxiv.org/pdf/1905.12006v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-portable-representations-for-high |
| Repo | |
| Framework | |
Generalization to Novel Objects using Prior Relational Knowledge
| Title | Generalization to Novel Objects using Prior Relational Knowledge |
| Authors | Varun Kumar Vijay, Abhinav Ganesh, Hanlin Tang, Arjun Bansal |
| Abstract | To solve tasks in new environments involving objects unseen during training, agents must reason over prior information about those objects and their relations. We introduce the Prior Knowledge Graph network, an architecture for combining prior information, structured as a knowledge graph, with a symbolic parsing of the visual scene, and demonstrate that this approach is able to apply learned relations to novel objects whereas the baseline algorithms fail. Ablation experiments show that the agents ground the knowledge graph relations to semantically-relevant behaviors. In both a Sokoban game and the more complex Pacman environment, our network is also more sample efficient than the baselines, reaching the same performance in 5-10x fewer episodes. Once the agents are trained with our approach, we can manipulate agent behavior by modifying the knowledge graph in semantically meaningful ways. These results suggest that our network provides a framework for agents to reason over structured knowledge graphs while still leveraging gradient based learning approaches. |
| Tasks | Knowledge Graphs |
| Published | 2019-06-26 |
| URL | https://arxiv.org/abs/1906.11315v2 |
| https://arxiv.org/pdf/1906.11315v2.pdf | |
| PWC | https://paperswithcode.com/paper/generalization-to-novel-objects-using-prior |
| Repo | |
| Framework | |
