Paper Group AWR 395
GeoTrackNet-A Maritime Anomaly Detector using Probabilistic Neural Network Representation of AIS Tracks and A Contrario Detection. Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables. Synergistic Image and Feature Adaptation: Towards Cross-Modality Domain Adaptation for Medical Image Segmentation. Scientific Stateme …
GeoTrackNet-A Maritime Anomaly Detector using Probabilistic Neural Network Representation of AIS Tracks and A Contrario Detection
| Title | GeoTrackNet-A Maritime Anomaly Detector using Probabilistic Neural Network Representation of AIS Tracks and A Contrario Detection |
| Authors | Duong Nguyen, Rodolphe Vadaine, Guillaume Hajduch, René Garello, Ronan Fablet |
| Abstract | Representing maritime traffic patterns and detecting anomalies from them are key to vessel monitoring and maritime situational awareness. We propose a novel approach-referred to as GeoTrackNet-for maritime anomaly detection from AIS data streams. Our model exploits state-of-the-art neural network schemes to learn a probabilistic representation of AIS tracks, then uses a contrario detection to detect abnormal events. The neural network helps us capture complex and heterogeneous patterns in vessels’ behaviors, while the a contrario detection takes into account the fact that the learned distribution may be location-dependent. Experiments on a real AIS dataset comprising more than 4.2 million AIS messages demonstrate the relevance of the proposed method. Keywords: AIS, maritime surveillance, deep learning, anomaly detection, variational recurrent neural networks, a contrario detection. |
| Tasks | Anomaly Detection |
| Published | 2019-12-02 |
| URL | https://arxiv.org/abs/1912.00682v1 |
| https://arxiv.org/pdf/1912.00682v1.pdf | |
| PWC | https://paperswithcode.com/paper/geotracknet-a-maritime-anomaly-detector-using |
| Repo | https://github.com/dnguyengithub/MultitaskAIS |
| Framework | tf |
Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables
| Title | Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables |
| Authors | Kate Rakelly, Aurick Zhou, Deirdre Quillen, Chelsea Finn, Sergey Levine |
| Abstract | Deep reinforcement learning algorithms require large amounts of experience to learn an individual task. While in principle meta-reinforcement learning (meta-RL) algorithms enable agents to learn new skills from small amounts of experience, several major challenges preclude their practicality. Current methods rely heavily on on-policy experience, limiting their sample efficiency. The also lack mechanisms to reason about task uncertainty when adapting to new tasks, limiting their effectiveness in sparse reward problems. In this paper, we address these challenges by developing an off-policy meta-RL algorithm that disentangles task inference and control. In our approach, we perform online probabilistic filtering of latent task variables to infer how to solve a new task from small amounts of experience. This probabilistic interpretation enables posterior sampling for structured and efficient exploration. We demonstrate how to integrate these task variables with off-policy RL algorithms to achieve both meta-training and adaptation efficiency. Our method outperforms prior algorithms in sample efficiency by 20-100X as well as in asymptotic performance on several meta-RL benchmarks. |
| Tasks | Efficient Exploration |
| Published | 2019-03-19 |
| URL | http://arxiv.org/abs/1903.08254v1 |
| http://arxiv.org/pdf/1903.08254v1.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-off-policy-meta-reinforcement |
| Repo | https://github.com/katerakelly/oyster |
| Framework | none |
Synergistic Image and Feature Adaptation: Towards Cross-Modality Domain Adaptation for Medical Image Segmentation
| Title | Synergistic Image and Feature Adaptation: Towards Cross-Modality Domain Adaptation for Medical Image Segmentation |
| Authors | Cheng Chen, Qi Dou, Hao Chen, Jing Qin, Pheng-Ann Heng |
| Abstract | This paper presents a novel unsupervised domain adaptation framework, called Synergistic Image and Feature Adaptation (SIFA), to effectively tackle the problem of domain shift. Domain adaptation has become an important and hot topic in recent studies on deep learning, aiming to recover performance degradation when applying the neural networks to new testing domains. Our proposed SIFA is an elegant learning diagram which presents synergistic fusion of adaptations from both image and feature perspectives. In particular, we simultaneously transform the appearance of images across domains and enhance domain-invariance of the extracted features towards the segmentation task. The feature encoder layers are shared by both perspectives to grasp their mutual benefits during the end-to-end learning procedure. Without using any annotation from the target domain, the learning of our unified model is guided by adversarial losses, with multiple discriminators employed from various aspects. We have extensively validated our method with a challenging application of cross-modality medical image segmentation of cardiac structures. Experimental results demonstrate that our SIFA model recovers the degraded performance from 17.2% to 73.0%, and outperforms the state-of-the-art methods by a significant margin. |
| Tasks | Domain Adaptation, Medical Image Segmentation, Semantic Segmentation, Unsupervised Domain Adaptation |
| Published | 2019-01-24 |
| URL | https://arxiv.org/abs/1901.08211v4 |
| https://arxiv.org/pdf/1901.08211v4.pdf | |
| PWC | https://paperswithcode.com/paper/synergistic-image-and-feature-adaptation |
| Repo | https://github.com/cchen-cc/SIFA |
| Framework | tf |
Scientific Statement Classification over arXiv.org
| Title | Scientific Statement Classification over arXiv.org |
| Authors | Deyan Ginev, Bruce R. Miller |
| Abstract | We introduce a new classification task for scientific statements and release a large-scale dataset for supervised learning. Our resource is derived from a machine-readable representation of the arXiv.org collection of preprint articles. We explore fifty author-annotated categories and empirically motivate a task design of grouping 10.5 million annotated paragraphs into thirteen classes. We demonstrate that the task setup aligns with known success rates from the state of the art, peaking at a 0.91 F1-score via a BiLSTM encoder-decoder model. Additionally, we introduce a lexeme serialization for mathematical formulas, and observe that context-aware models could improve when also trained on the symbolic modality. Finally, we discuss the limitations of both data and task design, and outline potential directions towards increasingly complex models of scientific discourse, beyond isolated statements. |
| Tasks | |
| Published | 2019-08-29 |
| URL | https://arxiv.org/abs/1908.10993v1 |
| https://arxiv.org/pdf/1908.10993v1.pdf | |
| PWC | https://paperswithcode.com/paper/scientific-statement-classification-over |
| Repo | https://github.com/dginev/arxiv-ams-paragraph-classification |
| Framework | tf |
Domain-independent Dominance of Adaptive Methods
| Title | Domain-independent Dominance of Adaptive Methods |
| Authors | Pedro Savarese, David McAllester, Sudarshan Babu, Michael Maire |
| Abstract | From a simplified analysis of adaptive methods, we derive AvaGrad, a new optimizer which outperforms SGD on vision tasks when its adaptability is properly tuned. We observe that the power of our method is partially explained by a decoupling of learning rate and adaptability, greatly simplifying hyperparameter search. In light of this observation, we demonstrate that, against conventional wisdom, Adam can also outperform SGD on vision tasks, as long as the coupling between its learning rate and adaptability is taken into account. In practice, AvaGrad matches the best results, as measured by generalization accuracy, delivered by any existing optimizer (SGD or adaptive) across image classification (CIFAR, ImageNet) and character-level language modelling (Penn Treebank) tasks. |
| Tasks | Image Classification, Language Modelling |
| Published | 2019-12-04 |
| URL | https://arxiv.org/abs/1912.01823v3 |
| https://arxiv.org/pdf/1912.01823v3.pdf | |
| PWC | https://paperswithcode.com/paper/domain-independent-dominance-of-adaptive-1 |
| Repo | https://github.com/lolemacs/avagrad |
| Framework | pytorch |
MIScnn: A Framework for Medical Image Segmentation with Convolutional Neural Networks and Deep Learning
| Title | MIScnn: A Framework for Medical Image Segmentation with Convolutional Neural Networks and Deep Learning |
| Authors | Dominik Müller, Frank Kramer |
| Abstract | The increased availability and usage of modern medical imaging induced a strong need for automatic medical image segmentation. Still, current image segmentation platforms do not provide the required functionalities for plain setup of medical image segmentation pipelines. Already implemented pipelines are commonly standalone software, optimized on a specific public data set. Therefore, this paper introduces the open-source Python library MIScnn. The aim of MIScnn is to provide an intuitive API allowing fast building of medical image segmentation pipelines including data I/O, preprocessing, data augmentation, patch-wise analysis, metrics, a library with state-of-the-art deep learning models and model utilization like training, prediction, as well as fully automatic evaluation (e.g. cross-validation). Similarly, high configurability and multiple open interfaces allow full pipeline customization. Running a cross-validation with MIScnn on the Kidney Tumor Segmentation Challenge 2019 data set (multi-class semantic segmentation with 300 CT scans) resulted into a powerful predictor based on the standard 3D U-Net model. With this experiment, we could show that the MIScnn framework enables researchers to rapidly set up a complete medical image segmentation pipeline by using just a few lines of code. The source code for MIScnn is available in the Git repository: https://github.com/frankkramer-lab/MIScnn. |
| Tasks | Data Augmentation, Medical Image Segmentation, Semantic Segmentation |
| Published | 2019-10-21 |
| URL | https://arxiv.org/abs/1910.09308v1 |
| https://arxiv.org/pdf/1910.09308v1.pdf | |
| PWC | https://paperswithcode.com/paper/miscnn-a-framework-for-medical-image |
| Repo | https://github.com/frankkramer-lab/MIScnn |
| Framework | tf |
Regularized HessELM and Inclined Entropy Measurement for Congestive Heart Failure Prediction
| Title | Regularized HessELM and Inclined Entropy Measurement for Congestive Heart Failure Prediction |
| Authors | Apdullah Yayık, Yakup Kutlu, Gökhan Altan |
| Abstract | Our study concerns with automated predicting of congestive heart failure (CHF) through the analysis of electrocardiography (ECG) signals. A novel machine learning approach, regularized hessenberg decomposition based extreme learning machine (R-HessELM), and feature models; squared, circled, inclined and grid entropy measurement were introduced and used for prediction of CHF. This study proved that inclined entropy measurements features well represent characteristics of ECG signals and together with R-HessELM approach overall accuracy of 98.49% was achieved. |
| Tasks | Electrocardiography (ECG) |
| Published | 2019-07-12 |
| URL | https://arxiv.org/abs/1907.05888v1 |
| https://arxiv.org/pdf/1907.05888v1.pdf | |
| PWC | https://paperswithcode.com/paper/regularized-hesselm-and-inclined-entropy |
| Repo | https://github.com/apdullahyayik/time-series-analysis |
| Framework | none |
Do Multi-hop Readers Dream of Reasoning Chains?
| Title | Do Multi-hop Readers Dream of Reasoning Chains? |
| Authors | Haoyu Wang, Mo Yu, Xiaoxiao Guo, Rajarshi Das, Wenhan Xiong, Tian Gao |
| Abstract | General Question Answering (QA) systems over texts require the multi-hop reasoning capability, i.e. the ability to reason with information collected from multiple passages to derive the answer. In this paper we conduct a systematic analysis to assess such an ability of various existing models proposed for multi-hop QA tasks. Specifically, our analysis investigates that whether providing the full reasoning chain of multiple passages, instead of just one final passage where the answer appears, could improve the performance of the existing QA models. Surprisingly, when using the additional evidence passages, the improvements of all the existing multi-hop reading approaches are rather limited, with the highest error reduction of 5.8% on F1 (corresponding to 1.3% absolute improvement) from the BERT model. To better understand whether the reasoning chains could indeed help find correct answers, we further develop a co-matching-based method that leads to 13.1% error reduction with passage chains when applied to two of our base readers (including BERT). Our results demonstrate the existence of the potential improvement using explicit multi-hop reasoning and the necessity to develop models with better reasoning abilities. |
| Tasks | Question Answering |
| Published | 2019-10-31 |
| URL | https://arxiv.org/abs/1910.14520v1 |
| https://arxiv.org/pdf/1910.14520v1.pdf | |
| PWC | https://paperswithcode.com/paper/do-multi-hop-readers-dream-of-reasoning |
| Repo | https://github.com/helloeve/bert-co-matching |
| Framework | tf |
Message Passing for Complex Question Answering over Knowledge Graphs
| Title | Message Passing for Complex Question Answering over Knowledge Graphs |
| Authors | Svitlana Vakulenko, Javier David Fernandez Garcia, Axel Polleres, Maarten de Rijke, Michael Cochez |
| Abstract | Question answering over knowledge graphs (KGQA) has evolved from simple single-fact questions to complex questions that require graph traversal and aggregation. We propose a novel approach for complex KGQA that uses unsupervised message passing, which propagates confidence scores obtained by parsing an input question and matching terms in the knowledge graph to a set of possible answers. First, we identify entity, relationship, and class names mentioned in a natural language question, and map these to their counterparts in the graph. Then, the confidence scores of these mappings propagate through the graph structure to locate the answer entities. Finally, these are aggregated depending on the identified question type. This approach can be efficiently implemented as a series of sparse matrix multiplications mimicking joins over small local subgraphs. Our evaluation results show that the proposed approach outperforms the state-of-the-art on the LC-QuAD benchmark. Moreover, we show that the performance of the approach depends only on the quality of the question interpretation results, i.e., given a correct relevance score distribution, our approach always produces a correct answer ranking. Our error analysis reveals correct answers missing from the benchmark dataset and inconsistencies in the DBpedia knowledge graph. Finally, we provide a comprehensive evaluation of the proposed approach accompanied with an ablation study and an error analysis, which showcase the pitfalls for each of the question answering components in more detail. |
| Tasks | Knowledge Graphs, Question Answering |
| Published | 2019-08-19 |
| URL | https://arxiv.org/abs/1908.06917v1 |
| https://arxiv.org/pdf/1908.06917v1.pdf | |
| PWC | https://paperswithcode.com/paper/message-passing-for-complex-question |
| Repo | https://github.com/svakulenk0/KBQA |
| Framework | tf |
Neural Attentive Bag-of-Entities Model for Text Classification
| Title | Neural Attentive Bag-of-Entities Model for Text Classification |
| Authors | Ikuya Yamada, Hiroyuki Shindo |
| Abstract | This study proposes a Neural Attentive Bag-of-Entities model, which is a neural network model that performs text classification using entities in a knowledge base. Entities provide unambiguous and relevant semantic signals that are beneficial for capturing semantics in texts. We combine simple high-recall entity detection based on a dictionary, to detect entities in a document, with a novel neural attention mechanism that enables the model to focus on a small number of unambiguous and relevant entities. We tested the effectiveness of our model using two standard text classification datasets (i.e., the 20 Newsgroups and R8 datasets) and a popular factoid question answering dataset based on a trivia quiz game. As a result, our model achieved state-of-the-art results on all datasets. The source code of the proposed model is available online at https://github.com/wikipedia2vec/wikipedia2vec. |
| Tasks | Question Answering, Text Classification |
| Published | 2019-09-03 |
| URL | https://arxiv.org/abs/1909.01259v2 |
| https://arxiv.org/pdf/1909.01259v2.pdf | |
| PWC | https://paperswithcode.com/paper/neural-attentive-bag-of-entities-model-for |
| Repo | https://github.com/studio-ousia/wikipedia2vec |
| Framework | none |
Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentation
| Title | Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentation |
| Authors | Qiming Zhang, Jing Zhang, Wei Liu, Dacheng Tao |
| Abstract | Unsupervised domain adaptation (UDA) aims to enhance the generalization capability of a certain model from a source domain to a target domain. UDA is of particular significance since no extra effort is devoted to annotating target domain samples. However, the different data distributions in the two domains, or \emph{domain shift/discrepancy}, inevitably compromise the UDA performance. Although there has been a progress in matching the marginal distributions between two domains, the classifier favors the source domain features and makes incorrect predictions on the target domain due to category-agnostic feature alignment. In this paper, we propose a novel category anchor-guided (CAG) UDA model for semantic segmentation, which explicitly enforces category-aware feature alignment to learn shared discriminative features and classifiers simultaneously. First, the category-wise centroids of the source domain features are used as guided anchors to identify the active features in the target domain and also assign them pseudo-labels. Then, we leverage an anchor-based pixel-level distance loss and a discriminative loss to drive the intra-category features closer and the inter-category features further apart, respectively. Finally, we devise a stagewise training mechanism to reduce the error accumulation and adapt the proposed model progressively. Experiments on both the GTA5$\rightarrow $Cityscapes and SYNTHIA$\rightarrow $Cityscapes scenarios demonstrate the superiority of our CAG-UDA model over the state-of-the-art methods. The code is available at \url{https://github.com/RogerZhangzz/CAG_UDA}. |
| Tasks | Domain Adaptation, Semantic Segmentation, Unsupervised Domain Adaptation |
| Published | 2019-10-29 |
| URL | https://arxiv.org/abs/1910.13049v2 |
| https://arxiv.org/pdf/1910.13049v2.pdf | |
| PWC | https://paperswithcode.com/paper/category-anchor-guided-unsupervised-domain |
| Repo | https://github.com/RogerZhangzz/CAG_UDA |
| Framework | pytorch |
EV-Action: Electromyography-Vision Multi-Modal Action Dataset
| Title | EV-Action: Electromyography-Vision Multi-Modal Action Dataset |
| Authors | Lichen Wang, Bin Sun, Joseph Robinson, Taotao Jing, Yun Fu |
| Abstract | Multi-modal human action analysis is a critical and attractive research topic. However, the majority of the existing datasets only provide visual modalities (i.e., RGB, depth and skeleton). To make up this, we introduce a new, large-scale EV-Action dataset in this work, which consists of RGB, depth, electromyography (EMG), and two skeleton modalities. Compared with the conventional datasets, EV-Action dataset has two major improvements: (1) we deploy a motion capturing system to obtain high quality skeleton modality, which provides more comprehensive motion information including skeleton, trajectory, acceleration with higher accuracy, sampling frequency, and more skeleton markers. (2) we introduce an EMG modality which is usually used as an effective indicator in the biomechanics area, also it has yet to be well explored in motion related research. To the best of our knowledge, this is the first action dataset with EMG modality. The details of EV-Action dataset are clarified, meanwhile, a simple yet effective framework for EMG-based action recognition is proposed. Moreover, state-of-the-art baselines are applied to evaluate the effectiveness of all the modalities. The obtained result clearly shows the validity of EMG modality in human action analysis tasks. We hope this dataset can make significant contributions to human motion analysis, computer vision, machine learning, biomechanics, and other interdisciplinary fields. |
| Tasks | Electromyography (EMG), Multimodal Activity Recognition, Temporal Action Localization |
| Published | 2019-04-20 |
| URL | https://arxiv.org/abs/1904.12602v2 |
| https://arxiv.org/pdf/1904.12602v2.pdf | |
| PWC | https://paperswithcode.com/paper/190412602 |
| Repo | https://github.com/wanglichenxj/EV-Action-Electromyography-Vision-Multi-Modal-Action-Dataset |
| Framework | none |
Multi-class Hierarchical Question Classification for Multiple Choice Science Exams
| Title | Multi-class Hierarchical Question Classification for Multiple Choice Science Exams |
| Authors | Dongfang Xu, Peter Jansen, Jaycie Martin, Zhengnan Xie, Vikas Yadav, Harish Tayyar Madabushi, Oyvind Tafjord, Peter Clark |
| Abstract | Prior work has demonstrated that question classification (QC), recognizing the problem domain of a question, can help answer it more accurately. However, developing strong QC algorithms has been hindered by the limited size and complexity of annotated data available. To address this, we present the largest challenge dataset for QC, containing 7,787 science exam questions paired with detailed classification labels from a fine-grained hierarchical taxonomy of 406 problem domains. We then show that a BERT-based model trained on this dataset achieves a large (+0.12 MAP) gain compared with previous methods, while also achieving state-of-the-art performance on benchmark open-domain and biomedical QC datasets. Finally, we show that using this model’s predictions of question topic significantly improves the accuracy of a question answering system by +1.7% P@1, with substantial future gains possible as QC performance improves. |
| Tasks | Question Answering |
| Published | 2019-08-15 |
| URL | https://arxiv.org/abs/1908.05441v1 |
| https://arxiv.org/pdf/1908.05441v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-class-hierarchical-question |
| Repo | https://github.com/cognitiveailab/questionclassification |
| Framework | tf |
Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules
| Title | Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules |
| Authors | Daniel Ho, Eric Liang, Ion Stoica, Pieter Abbeel, Xi Chen |
| Abstract | A key challenge in leveraging data augmentation for neural network training is choosing an effective augmentation policy from a large search space of candidate operations. Properly chosen augmentation policies can lead to significant generalization improvements; however, state-of-the-art approaches such as AutoAugment are computationally infeasible to run for the ordinary user. In this paper, we introduce a new data augmentation algorithm, Population Based Augmentation (PBA), which generates nonstationary augmentation policy schedules instead of a fixed augmentation policy. We show that PBA can match the performance of AutoAugment on CIFAR-10, CIFAR-100, and SVHN, with three orders of magnitude less overall compute. On CIFAR-10 we achieve a mean test error of 1.46%, which is a slight improvement upon the current state-of-the-art. The code for PBA is open source and is available at https://github.com/arcelien/pba. |
| Tasks | Data Augmentation, Image Augmentation |
| Published | 2019-05-14 |
| URL | https://arxiv.org/abs/1905.05393v1 |
| https://arxiv.org/pdf/1905.05393v1.pdf | |
| PWC | https://paperswithcode.com/paper/190505393 |
| Repo | https://github.com/arcelien/pba |
| Framework | tf |
One Network to Segment Them All: A General, Lightweight System for Accurate 3D Medical Image Segmentation
| Title | One Network to Segment Them All: A General, Lightweight System for Accurate 3D Medical Image Segmentation |
| Authors | Mathias Perslev, Erik Bjørnager Dam, Akshay Pai, Christian Igel |
| Abstract | Many recent medical segmentation systems rely on powerful deep learning models to solve highly specific tasks. To maximize performance, it is standard practice to evaluate numerous pipelines with varying model topologies, optimization parameters, pre- & postprocessing steps, and even model cascades. It is often not clear how the resulting pipeline transfers to different tasks. We propose a simple and thoroughly evaluated deep learning framework for segmentation of arbitrary medical image volumes. The system requires no task-specific information, no human interaction and is based on a fixed model topology and a fixed hyperparameter set, eliminating the process of model selection and its inherent tendency to cause method-level over-fitting. The system is available in open source and does not require deep learning expertise to use. Without task-specific modifications, the system performed better than or similar to highly specialized deep learning methods across 3 separate segmentation tasks. In addition, it ranked 5-th and 6-th in the first and second round of the 2018 Medical Segmentation Decathlon comprising another 10 tasks. The system relies on multi-planar data augmentation which facilitates the application of a single 2D architecture based on the familiar U-Net. Multi-planar training combines the parameter efficiency of a 2D fully convolutional neural network with a systematic train- and test-time augmentation scheme, which allows the 2D model to learn a representation of the 3D image volume that fosters generalization. |
| Tasks | Data Augmentation, Medical Image Segmentation, Model Selection, Semantic Segmentation |
| Published | 2019-11-05 |
| URL | https://arxiv.org/abs/1911.01764v1 |
| https://arxiv.org/pdf/1911.01764v1.pdf | |
| PWC | https://paperswithcode.com/paper/one-network-to-segment-them-all-a-general |
| Repo | https://github.com/perslev/MultiPlanarUNet |
| Framework | none |
