Paper Group ANR 1777
An overlapping-free leaf segmentation method for plant point clouds. Modular Deep Learning Analysis of Galaxy-Scale Strong Lensing Images. Densely Connected Graph Convolutional Networks for Graph-to-Sequence Learning. Estimating People Flows to Better Count Them in Crowded Scenes. Evolutionary Computation, Optimization and Learning Algorithms for D …
An overlapping-free leaf segmentation method for plant point clouds
| Title | An overlapping-free leaf segmentation method for plant point clouds |
| Authors | Dawei Li, Yan Cao, Guoliang Shi, Xin Cai, Yang Chen, Sifan Wang, Siyuan Yan |
| Abstract | Automatic leaf segmentation, as well as identification and classification methods that built upon it, are able to provide immediate monitoring for plant growth status to guarantee the output. Although 3D plant point clouds contain abundant phenotypic features, plant leaves are usually distributed in clusters and are sometimes seriously overlapped in the canopy. Therefore, it is still a big challenge to automatically segment each individual leaf from a highly crowded plant canopy in 3D for plant phenotyping purposes. In this work, we propose an overlapping-free individual leaf segmentation method for plant point clouds using the 3D filtering and facet region growing. In order to separate leaves with different overlapping situations, we develop a new 3D joint filtering operator, which integrates a Radius-based Outlier Filter (RBOF) and a Surface Boundary Filter (SBF) to help to separate occluded leaves. By introducing the facet over-segmentation and facet-based region growing, the noise in segmentation is suppressed and labeled leaf centers can expand to their whole leaves, respectively. Our method can work on point clouds generated from three types of 3D imaging platforms, and also suitable for different kinds of plant species. In experiments, it obtains a point-level cover rate of 97% for Epipremnum aureum, 99% for Monstera deliciosa, 99% for Calathea makoyana, and 87% for Hedera nepalensis sample plants. At the leaf level, our method reaches an average Recall at 100.00%, a Precision at 99.33%, and an average F-measure at 99.66%, respectively. The proposed method can also facilitate the automatic traits estimation of each single leaf (such as the leaf area, length, and width), which has potential to become a highly effective tool for plant research and agricultural engineering. |
| Tasks | |
| Published | 2019-08-12 |
| URL | https://arxiv.org/abs/1908.04018v1 |
| https://arxiv.org/pdf/1908.04018v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-overlapping-free-leaf-segmentation-method |
| Repo | |
| Framework | |
Modular Deep Learning Analysis of Galaxy-Scale Strong Lensing Images
| Title | Modular Deep Learning Analysis of Galaxy-Scale Strong Lensing Images |
| Authors | Sandeep Madireddy, Nan Li, Nesar Ramachandra, Prasanna Balaprakash, Salman Habib |
| Abstract | Strong gravitational lensing of astrophysical sources by foreground galaxies is a powerful cosmological tool. While such lens systems are relatively rare in the Universe, the number of detectable galaxy-scale strong lenses is expected to grow dramatically with next-generation optical surveys, numbering in the hundreds of thousands, out of tens of billions of candidate images. Automated and efficient approaches will be necessary in order to find and analyze these strong lens systems. To this end, we implement a novel, modular, end-to-end deep learning pipeline for denoising, deblending, searching, and modeling galaxy-galaxy strong lenses (GGSLs). To train and quantify the performance of our pipeline, we create a dataset of 1 million synthetic strong lensing images using state-of-the-art simulations for next-generation sky surveys. When these pretrained modules were used as a pipeline for inference, we found that the classification (searching GGSL) accuracy improved significantly—from 82% with the baseline to 90%, while the regression (modeling GGSL) accuracy improved by 25% over the baseline. |
| Tasks | Denoising |
| Published | 2019-11-10 |
| URL | https://arxiv.org/abs/1911.03867v1 |
| https://arxiv.org/pdf/1911.03867v1.pdf | |
| PWC | https://paperswithcode.com/paper/modular-deep-learning-analysis-of-galaxy |
| Repo | |
| Framework | |
Densely Connected Graph Convolutional Networks for Graph-to-Sequence Learning
| Title | Densely Connected Graph Convolutional Networks for Graph-to-Sequence Learning |
| Authors | Zhijiang Guo, Yan Zhang, Zhiyang Teng, Wei Lu |
| Abstract | We focus on graph-to-sequence learning, which can be framed as transducing graph structures to sequences for text generation. To capture structural information associated with graphs, we investigate the problem of encoding graphs using graph convolutional networks (GCNs). Unlike various existing approaches where shallow architectures were used for capturing local structural information only, we introduce a dense connection strategy, proposing a novel Densely Connected Graph Convolutional Networks (DCGCNs). Such a deep architecture is able to integrate both local and non-local features to learn a better structural representation of a graph. Our model outperforms the state-of-the-art neural models significantly on AMRto-text generation and syntax-based neural machine translation. |
| Tasks | Graph-to-Sequence, Machine Translation, Text Generation |
| Published | 2019-08-16 |
| URL | https://arxiv.org/abs/1908.05957v2 |
| https://arxiv.org/pdf/1908.05957v2.pdf | |
| PWC | https://paperswithcode.com/paper/densely-connected-graph-convolutional-1 |
| Repo | |
| Framework | |
Estimating People Flows to Better Count Them in Crowded Scenes
| Title | Estimating People Flows to Better Count Them in Crowded Scenes |
| Authors | Weizhe Liu, Mathieu Salzmann, Pascal Fua |
| Abstract | Modern methods for counting people in crowded scenes rely on deep networks to estimate people densities in individual images. As such, only very few take advantage of temporal consistency in video sequences, and those that do only impose weak smoothness constraints across consecutive frames. In this paper, we advocate estimating people flows across image locations between consecutive images and inferring the people densities from these flows instead of directly regressing. This enables us to impose much stronger constraints encoding the conservation of the number of people. As a result, it significantly boosts performance without requiring a more complex architecture. Furthermore, it also enables us to exploit the correlation between people flow and optical flow to further improve the results. We will demonstrate that we consistently outperform state-of-the-art methods on five benchmark datasets. |
| Tasks | Optical Flow Estimation |
| Published | 2019-11-25 |
| URL | https://arxiv.org/abs/1911.10782v2 |
| https://arxiv.org/pdf/1911.10782v2.pdf | |
| PWC | https://paperswithcode.com/paper/estimating-people-flows-to-better-count-them |
| Repo | |
| Framework | |
Evolutionary Computation, Optimization and Learning Algorithms for Data Science
| Title | Evolutionary Computation, Optimization and Learning Algorithms for Data Science |
| Authors | Farid Ghareh Mohammadi, M. Hadi Amini, Hamid R. Arabnia |
| Abstract | A large number of engineering, science and computational problems have yet to be solved in a computationally efficient way. One of the emerging challenges is how evolving technologies grow towards autonomy and intelligent decision making. This leads to collection of large amounts of data from various sensing and measurement technologies, e.g., cameras, smart phones, health sensors, smart electricity meters, and environment sensors. Hence, it is imperative to develop efficient algorithms for generation, analysis, classification, and illustration of data. Meanwhile, data is structured purposefully through different representations, such as large-scale networks and graphs. We focus on data science as a crucial area, specifically focusing on a curse of dimensionality (CoD) which is due to the large amount of generated/sensed/collected data. This motivates researchers to think about optimization and to apply nature-inspired algorithms, such as evolutionary algorithms (EAs) to solve optimization problems. Although these algorithms look un-deterministic, they are robust enough to reach an optimal solution. Researchers do not adopt evolutionary algorithms unless they face a problem which is suffering from placement in local optimal solution, rather than global optimal solution. In this chapter, we first develop a clear and formal definition of the CoD problem, next we focus on feature extraction techniques and categories, then we provide a general overview of meta-heuristic algorithms, its terminology, and desirable properties of evolutionary algorithms. |
| Tasks | Decision Making |
| Published | 2019-08-16 |
| URL | https://arxiv.org/abs/1908.08006v1 |
| https://arxiv.org/pdf/1908.08006v1.pdf | |
| PWC | https://paperswithcode.com/paper/190808006 |
| Repo | |
| Framework | |
From User-independent to Personal Human Activity Recognition Models Exploiting the Sensors of a Smartphone
| Title | From User-independent to Personal Human Activity Recognition Models Exploiting the Sensors of a Smartphone |
| Authors | Pekka Siirtola, Heli Koskimäki, Juha Röning |
| Abstract | In this study, a novel method to obtain user-dependent human activity recognition models unobtrusively by exploiting the sensors of a smartphone is presented. The recognition consists of two models: sensor fusion-based user-independent model for data labeling and single sensor-based user-dependent model for final recognition. The functioning of the presented method is tested with human activity data set, including data from accelerometer and magnetometer, and with two classifiers. Comparison of the detection accuracies of the proposed method to traditional user-independent model shows that the presented method has potential, in nine cases out of ten it is better than the traditional method, but more experiments using different sensor combinations should be made to show the full potential of the method. |
| Tasks | Activity Recognition, Human Activity Recognition, Sensor Fusion |
| Published | 2019-05-29 |
| URL | https://arxiv.org/abs/1905.12285v1 |
| https://arxiv.org/pdf/1905.12285v1.pdf | |
| PWC | https://paperswithcode.com/paper/from-user-independent-to-personal-human |
| Repo | |
| Framework | |
Low-Resource Syntactic Transfer with Unsupervised Source Reordering
| Title | Low-Resource Syntactic Transfer with Unsupervised Source Reordering |
| Authors | Mohammad Sadegh Rasooli, Michael Collins |
| Abstract | We describe a cross-lingual transfer method for dependency parsing that takes into account the problem of word order differences between source and target languages. Our model only relies on the Bible, a considerably smaller parallel data than the commonly used parallel data in transfer methods. We use the concatenation of projected trees from the Bible corpus, and the gold-standard treebanks in multiple source languages along with cross-lingual word representations. We demonstrate that reordering the source treebanks before training on them for a target language improves the accuracy of languages outside the European language family. Our experiments on 68 treebanks (38 languages) in the Universal Dependencies corpus achieve a high accuracy for all languages. Among them, our experiments on 16 treebanks of 12 non-European languages achieve an average UAS absolute improvement of 3.3% over a state-of-the-art method. |
| Tasks | Cross-Lingual Transfer, Dependency Parsing |
| Published | 2019-03-13 |
| URL | http://arxiv.org/abs/1903.05683v1 |
| http://arxiv.org/pdf/1903.05683v1.pdf | |
| PWC | https://paperswithcode.com/paper/low-resource-syntactic-transfer-with |
| Repo | |
| Framework | |
Medical Diagnosis with a Novel SVM-CoDOA Based Hybrid Approach
| Title | Medical Diagnosis with a Novel SVM-CoDOA Based Hybrid Approach |
| Authors | M. Hanefi Calp |
| Abstract | Machine Learning is an important sub-field of the Artificial Intelligence and it has been become a very critical task to train Machine Learning techniques via effective method or techniques. Recently, researchers try to use alternative techniques to improve ability of Machine Learning techniques. Moving from the explanations, objective of this study is to introduce a novel SVM-CoDOA (Cognitive Development Optimization Algorithm trained Support Vector Machines) system for general medical diagnosis. In detail, the system consists of a SVM, which is trained by CoDOA, a newly developed optimization algorithm. As it is known, use of optimization algorithms is an essential task to train and improve Machine Learning techniques. In this sense, the study has provided a medical diagnosis oriented problem scope in order to show effectiveness of the SVM-CoDOA hybrid formation. |
| Tasks | Medical Diagnosis |
| Published | 2019-02-02 |
| URL | http://arxiv.org/abs/1902.00685v1 |
| http://arxiv.org/pdf/1902.00685v1.pdf | |
| PWC | https://paperswithcode.com/paper/medical-diagnosis-with-a-novel-svm-codoa |
| Repo | |
| Framework | |
Comparison of Lattice-Free and Lattice-Based Sequence Discriminative Training Criteria for LVCSR
| Title | Comparison of Lattice-Free and Lattice-Based Sequence Discriminative Training Criteria for LVCSR |
| Authors | Wilfried Michel, Ralf Schlüter, Hermann Ney |
| Abstract | Sequence discriminative training criteria have long been a standard tool in automatic speech recognition for improving the performance of acoustic models over their maximum likelihood / cross entropy trained counterparts. While previously a lattice approximation of the search space has been necessary to reduce computational complexity, recently proposed methods use other approximations to dispense of the need for the computationally expensive step of separate lattice creation. In this work we present a memory efficient implementation of the forward-backward computation that allows us to use uni-gram word-level language models in the denominator calculation while still doing a full summation on GPU. This allows for a direct comparison of lattice-based and lattice-free sequence discriminative training criteria such as MMI and sMBR, both using the same language model during training. We compared performance, speed of convergence, and stability on large vocabulary continuous speech recognition tasks like Switchboard and Quaero. We found that silence modeling seriously impacts the performance in the lattice-free case and needs special treatment. In our experiments lattice-free MMI comes on par with its lattice-based counterpart. Lattice-based sMBR still outperforms all lattice-free training criteria. |
| Tasks | Language Modelling, Large Vocabulary Continuous Speech Recognition, Speech Recognition |
| Published | 2019-07-01 |
| URL | https://arxiv.org/abs/1907.01409v1 |
| https://arxiv.org/pdf/1907.01409v1.pdf | |
| PWC | https://paperswithcode.com/paper/comparison-of-lattice-free-and-lattice-based |
| Repo | |
| Framework | |
A Deep Learning Approach for Similar Languages, Varieties and Dialects
| Title | A Deep Learning Approach for Similar Languages, Varieties and Dialects |
| Authors | Vidya Prasad K, Akarsh S, Vinayakumar R, Soman KP |
| Abstract | Deep learning mechanisms are prevailing approaches in recent days for the various tasks in natural language processing, speech recognition, image processing and many others. To leverage this we use deep learning based mechanism specifically Bidirectional- Long Short-Term Memory (B-LSTM) for the task of dialectic identification in Arabic and German broadcast speech and Long Short-Term Memory (LSTM) for discriminating between similar Languages. Two unique B-LSTM models are created using the Large-vocabulary Continuous Speech Recognition (LVCSR) based lexical features and a fixed length of 400 per utterance bottleneck features generated by i-vector framework. These models were evaluated on the VarDial 2017 datasets for the tasks Arabic, German dialect identification with dialects of Egyptian, Gulf, Levantine, North African, and MSA for Arabic and Basel, Bern, Lucerne, and Zurich for German. Also for the task of Discriminating between Similar Languages like Bosnian, Croatian and Serbian. The B-LSTM model showed accuracy of 0.246 on lexical features and accuracy of 0.577 bottleneck features of i-Vector framework. |
| Tasks | Large Vocabulary Continuous Speech Recognition, Speech Recognition |
| Published | 2019-01-02 |
| URL | http://arxiv.org/abs/1901.00297v1 |
| http://arxiv.org/pdf/1901.00297v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-deep-learning-approach-for-similar |
| Repo | |
| Framework | |
Syntax-Enhanced Self-Attention-Based Semantic Role Labeling
| Title | Syntax-Enhanced Self-Attention-Based Semantic Role Labeling |
| Authors | Yue Zhang, Rui Wang, Luo Si |
| Abstract | As a fundamental NLP task, semantic role labeling (SRL) aims to discover the semantic roles for each predicate within one sentence. This paper investigates how to incorporate syntactic knowledge into the SRL task effectively. We present different approaches of encoding the syntactic information derived from dependency trees of different quality and representations; we propose a syntax-enhanced self-attention model and compare it with other two strong baseline methods; and we conduct experiments with newly published deep contextualized word representations as well. The experiment results demonstrate that with proper incorporation of the high quality syntactic information, our model achieves a new state-of-the-art performance for the Chinese SRL task on the CoNLL-2009 dataset. |
| Tasks | Semantic Role Labeling |
| Published | 2019-10-24 |
| URL | https://arxiv.org/abs/1910.11204v1 |
| https://arxiv.org/pdf/1910.11204v1.pdf | |
| PWC | https://paperswithcode.com/paper/syntax-enhanced-self-attention-based-semantic |
| Repo | |
| Framework | |
Data Augmentation with Atomic Templates for Spoken Language Understanding
| Title | Data Augmentation with Atomic Templates for Spoken Language Understanding |
| Authors | Zijian Zhao, Su Zhu, Kai Yu |
| Abstract | Spoken Language Understanding (SLU) converts user utterances into structured semantic representations. Data sparsity is one of the main obstacles of SLU due to the high cost of human annotation, especially when domain changes or a new domain comes. In this work, we propose a data augmentation method with atomic templates for SLU, which involves minimum human efforts. The atomic templates produce exemplars for fine-grained constituents of semantic representations. We propose an encoder-decoder model to generate the whole utterance from atomic exemplars. Moreover, the generator could be transferred from source domains to help a new domain which has little data. Experimental results show that our method achieves significant improvements on DSTC 2&3 dataset which is a domain adaptation setting of SLU. |
| Tasks | Data Augmentation, Domain Adaptation, Spoken Language Understanding |
| Published | 2019-08-28 |
| URL | https://arxiv.org/abs/1908.10770v1 |
| https://arxiv.org/pdf/1908.10770v1.pdf | |
| PWC | https://paperswithcode.com/paper/data-augmentation-with-atomic-templates-for |
| Repo | |
| Framework | |
Stereo Event Lifetime and Disparity Estimation for Dynamic Vision Sensors
| Title | Stereo Event Lifetime and Disparity Estimation for Dynamic Vision Sensors |
| Authors | Antea Hadviger, Ivan Marković, Ivan Petrović |
| Abstract | Event-based cameras are biologically inspired sensors that output asynchronous pixel-wise brightness changes in the scene called events. They have a high dynamic range and temporal resolution of a microsecond, opposed to standard cameras that output frames at fixed frame rates and suffer from motion blur. Forming stereo pairs of such cameras can open novel application possibilities, since for each event depth can be readily estimated; however, to fully exploit asynchronous nature of the sensor and avoid fixed time interval event accumulation, stereo event lifetime estimation should be employed. In this paper, we propose a novel method for event lifetime estimation of stereo event-cameras, allowing generation of sharp gradient images of events that serve as input to disparity estimation methods. Since a single brightness change triggers events in both event-camera sensors, we propose a method for single shot event lifetime and disparity estimation, with association via stereo matching. The proposed method is approximately twice as fast and more accurate than if lifetimes were estimated separately for each sensor and then stereo matched. Results are validated on real-world data through multiple stereo event-camera experiments. |
| Tasks | Disparity Estimation, Stereo Matching, Stereo Matching Hand |
| Published | 2019-07-17 |
| URL | https://arxiv.org/abs/1907.07518v1 |
| https://arxiv.org/pdf/1907.07518v1.pdf | |
| PWC | https://paperswithcode.com/paper/stereo-event-lifetime-and-disparity |
| Repo | |
| Framework | |
An Iterative Polishing Framework based on Quality Aware Masked Language Model for Chinese Poetry Generation
| Title | An Iterative Polishing Framework based on Quality Aware Masked Language Model for Chinese Poetry Generation |
| Authors | Liming Deng, Jie Wang, Hangming Liang, Hui Chen, Zhiqiang Xie, Bojin Zhuang, Shaojun Wang, Jing Xiao |
| Abstract | Owing to its unique literal and aesthetical characteristics, automatic generation of Chinese poetry is still challenging in Artificial Intelligence, which can hardly be straightforwardly realized by end-to-end methods. In this paper, we propose a novel iterative polishing framework for highly qualified Chinese poetry generation. In the first stage, an encoder-decoder structure is utilized to generate a poem draft. Afterwards, our proposed Quality-Aware Masked Language Model (QAMLM) is employed to polish the draft towards higher quality in terms of linguistics and literalness. Based on a multi-task learning scheme, QA-MLM is able to determine whether polishing is needed based on the poem draft. Furthermore, QAMLM is able to localize improper characters of the poem draft and substitute with newly predicted ones accordingly. Benefited from the masked language model structure, QAMLM incorporates global context information into the polishing process, which can obtain more appropriate polishing results than the unidirectional sequential decoding. Moreover, the iterative polishing process will be terminated automatically when QA-MLM regards the processed poem as a qualified one. Both human and automatic evaluation have been conducted, and the results demonstrate that our approach is effective to improve the performance of encoder-decoder structure. |
| Tasks | Language Modelling, Multi-Task Learning |
| Published | 2019-11-29 |
| URL | https://arxiv.org/abs/1911.13182v1 |
| https://arxiv.org/pdf/1911.13182v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-iterative-polishing-framework-based-on |
| Repo | |
| Framework | |
On Convergence of Distributed Approximate Newton Methods: Globalization, Sharper Bounds and Beyond
| Title | On Convergence of Distributed Approximate Newton Methods: Globalization, Sharper Bounds and Beyond |
| Authors | Xiao-Tong Yuan, Ping Li |
| Abstract | The DANE algorithm is an approximate Newton method popularly used for communication-efficient distributed machine learning. Reasons for the interest in DANE include scalability and versatility. Convergence of DANE, however, can be tricky; its appealing convergence rate is only rigorous for quadratic objective, and for more general convex functions the known results are no stronger than those of the classic first-order methods. To remedy these drawbacks, we propose in this paper some new alternatives of DANE which are more suitable for analysis. We first introduce a simple variant of DANE equipped with backtracking line search, for which global asymptotic convergence and sharper local non-asymptotic convergence rate guarantees can be proved for both quadratic and non-quadratic strongly convex functions. Then we propose a heavy-ball method to accelerate the convergence of DANE, showing that nearly tight local rate of convergence can be established for strongly convex functions, and with proper modification of algorithm the same result applies globally to linear prediction models. Numerical evidence is provided to confirm the theoretical and practical advantages of our methods. |
| Tasks | |
| Published | 2019-08-06 |
| URL | https://arxiv.org/abs/1908.02246v1 |
| https://arxiv.org/pdf/1908.02246v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-convergence-of-distributed-approximate |
| Repo | |
| Framework | |
