Paper Group ANR 472
OffWorld Gym: open-access physical robotics environment for real-world reinforcement learning benchmark and research. GrappaNet: Combining Parallel Imaging with Deep Learning for Multi-Coil MRI Reconstruction. Recognising Agreement and Disagreement between Stances with Reason Comparing Networks. Towards Integrating Formal Verification of Autonomous …
OffWorld Gym: open-access physical robotics environment for real-world reinforcement learning benchmark and research
| Title | OffWorld Gym: open-access physical robotics environment for real-world reinforcement learning benchmark and research |
| Authors | Ashish Kumar, Toby Buckley, Qiaozhi Wang, Alicia Kavelaars, Ilya Kuzovkin |
| Abstract | Success stories of applied machine learning can be traced back to the datasets and environments that were put forward as challenges for the community. The challenge that the community sets as a benchmark is usually the challenge that the community eventually solves. The ultimate challenge of reinforcement learning research is to train real agents to operate in the real environment, but until now there has not been a common real-world RL benchmark. In this work, we present a prototype real-world environment from OffWorld Gym – a collection of real-world environments for reinforcement learning in robotics with free public remote access. Close integration into existing ecosystem allows the community to start using OffWorld Gym without any prior experience in robotics and takes away the burden of managing a physical robotics system, abstracting it under a familiar API. We introduce a navigation task, where a robot has to reach a visual beacon on an uneven terrain using only the camera input and provide baseline results in both the real environment and the simulated replica. To start training, visit https://gym.offworld.ai. |
| Tasks | |
| Published | 2019-10-18 |
| URL | https://arxiv.org/abs/1910.08639v1 |
| https://arxiv.org/pdf/1910.08639v1.pdf | |
| PWC | https://paperswithcode.com/paper/offworld-gym-open-access-physical-robotics |
| Repo | |
| Framework | |
GrappaNet: Combining Parallel Imaging with Deep Learning for Multi-Coil MRI Reconstruction
| Title | GrappaNet: Combining Parallel Imaging with Deep Learning for Multi-Coil MRI Reconstruction |
| Authors | Anuroop Sriram, Jure Zbontar, Tullie Murrell, C. Lawrence Zitnick, Aaron Defazio, Daniel K. Sodickson |
| Abstract | Magnetic Resonance Image (MRI) acquisition is an inherently slow process which has spurred the development of two different acceleration methods: acquiring multiple correlated samples simultaneously (parallel imaging) and acquiring fewer samples than necessary for traditional signal processing methods (compressed sensing). Both methods provide complementary approaches to accelerating the speed of MRI acquisition. In this paper, we present a novel method to integrate traditional parallel imaging methods into deep neural networks that is able to generate high quality reconstructions even for high acceleration factors. The proposed method, called GrappaNet, performs progressive reconstruction by first mapping the reconstruction problem to a simpler one that can be solved by a traditional parallel imaging methods using a neural network, followed by an application of a parallel imaging method, and finally fine-tuning the output with another neural network. The entire network can be trained end-to-end. We present experimental results on the recently released fastMRI dataset and show that GrappaNet can generate higher quality reconstructions than competing methods for both $4\times$ and $8\times$ acceleration. |
| Tasks | |
| Published | 2019-10-27 |
| URL | https://arxiv.org/abs/1910.12325v4 |
| https://arxiv.org/pdf/1910.12325v4.pdf | |
| PWC | https://paperswithcode.com/paper/grappanet-combining-parallel-imaging-with |
| Repo | |
| Framework | |
Recognising Agreement and Disagreement between Stances with Reason Comparing Networks
| Title | Recognising Agreement and Disagreement between Stances with Reason Comparing Networks |
| Authors | Chang Xu, Cecile Paris, Surya Nepal, Ross Sparks |
| Abstract | We identify agreement and disagreement between utterances that express stances towards a topic of discussion. Existing methods focus mainly on conversational settings, where dialogic features are used for (dis)agreement inference. We extend this scope and seek to detect stance (dis)agreement in a broader setting, where independent stance-bearing utterances, which prevail in many stance corpora and real-world scenarios, are compared. To cope with such non-dialogic utterances, we find that the reasons uttered to back up a specific stance can help predict stance (dis)agreements. We propose a reason comparing network (RCN) to leverage reason information for stance comparison. Empirical results on a well-known stance corpus show that our method can discover useful reason information, enabling it to outperform several baselines in stance (dis)agreement detection. |
| Tasks | |
| Published | 2019-06-04 |
| URL | https://arxiv.org/abs/1906.01392v1 |
| https://arxiv.org/pdf/1906.01392v1.pdf | |
| PWC | https://paperswithcode.com/paper/recognising-agreement-and-disagreement |
| Repo | |
| Framework | |
Towards Integrating Formal Verification of Autonomous Robots with Battery Prognostics and Health Management
| Title | Towards Integrating Formal Verification of Autonomous Robots with Battery Prognostics and Health Management |
| Authors | Xingyu Zhao, Matt Osborne, Jenny Lantair, Valentin Robu, David Flynn, Xiaowei Huang, Michael Fisher, Fabio Papacchini, Angelo Ferrando |
| Abstract | The battery is a key component of autonomous robots. Its performance limits the robot’s safety and reliability. Unlike liquid-fuel, a battery, as a chemical device, exhibits complicated features, including (i) capacity fade over successive recharges and (ii) increasing discharge rate as the state of charge (SOC) goes down for a given power demand. Existing formal verification studies of autonomous robots, when considering energy constraints, formalise the energy component in a generic manner such that the battery features are overlooked. In this paper, we model an unmanned aerial vehicle (UAV) inspection mission on a wind farm and via probabilistic model checking in PRISM show (i) how the battery features may affect the verification results significantly in practical cases; and (ii) how the battery features, together with dynamic environments and battery safety strategies, jointly affect the verification results. Potential solutions to explicitly integrate battery prognostics and health management (PHM) with formal verification of autonomous robots are also discussed to motivate future work. |
| Tasks | |
| Published | 2019-08-22 |
| URL | https://arxiv.org/abs/1909.03019v1 |
| https://arxiv.org/pdf/1909.03019v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-integrating-formal-verification-of |
| Repo | |
| Framework | |
Blood Vessel Detection using Modified Multiscale MF-FDOG Filters for Diabetic Retinopathy
| Title | Blood Vessel Detection using Modified Multiscale MF-FDOG Filters for Diabetic Retinopathy |
| Authors | Debojyoti Mallick, Kundan Kumar, Sumanshu Agarwal |
| Abstract | Blindness in diabetic patients caused by retinopathy (characterized by an increase in the diameter and new branches of the blood vessels inside the retina) is a grave concern. Many efforts have been made for the early detection of the disease using various image processing techniques on retinal images. However, most of the methods are plagued with the false detection of the blood vessel pixels. Given that, here, we propose a modified matched filter with the first derivative of Gaussian. The method uses the top-hat transform and contrast limited histogram equalization. Further, we segment the modified multiscale matched filter response by using a binary threshold obtained from the first derivative of Gaussian. The method was assessed on a publicly available database (DRIVE database). As anticipated, the proposed method provides a higher accuracy compared to the literature. Moreover, a lesser false detection from the existing matched filters and its variants have been observed. |
| Tasks | |
| Published | 2019-10-26 |
| URL | https://arxiv.org/abs/1910.12028v1 |
| https://arxiv.org/pdf/1910.12028v1.pdf | |
| PWC | https://paperswithcode.com/paper/blood-vessel-detection-using-modified |
| Repo | |
| Framework | |
Meta-Learning Initializations for Image Segmentation
| Title | Meta-Learning Initializations for Image Segmentation |
| Authors | Sean M. Hendryx, Andrew B. Leach, Paul D. Hein, Clayton T. Morrison |
| Abstract | While meta-learning approaches that utilize neural network representations have made progress in few-shot image classification, reinforcement learning, and, more recently, image semantic segmentation, the training algorithms and model architectures have become increasingly specialized to the few-shot domain. A natural question that arises is how to develop learning systems that scale from few-shot to many-shot settings while yielding competitive performance in both. One scalable potential approach that does not require ensembling many models nor the computational costs of relation networks, is to meta-learn an initialization. In this work, we study first-order meta-learning of initializations for deep neural networks that must produce dense, structured predictions given an arbitrary amount of training data for a new task. Our primary contributions include (1), an extension and experimental analysis of first-order model agnostic meta-learning algorithms (including FOMAML and Reptile) to image segmentation, (2) a novel neural network architecture built for parameter efficiency and fast learning which we call EfficientLab, (3) a formalization of the generalization error of meta-learning algorithms, which we leverage to decrease error on unseen tasks, and (4) a small benchmark dataset, FP-k, for the empirical study of how meta-learning systems perform in both few- and many-shot settings. We show that meta-learned initializations for image segmentation provide value for both canonical few-shot learning problems and larger datasets, outperforming ImageNet-trained initializations for up to 400 densely labeled examples. We find that our network, with an empirically estimated optimal update procedure, yields state of the art results on the FSS-1000 dataset while only requiring one forward pass through a single model at evaluation time. |
| Tasks | Few-Shot Image Classification, Few-Shot Learning, Image Classification, Meta-Learning, Semantic Segmentation |
| Published | 2019-12-13 |
| URL | https://arxiv.org/abs/1912.06290v1 |
| https://arxiv.org/pdf/1912.06290v1.pdf | |
| PWC | https://paperswithcode.com/paper/meta-learning-initializations-for-image-1 |
| Repo | |
| Framework | |
Improving Adversarial Robustness via Attention and Adversarial Logit Pairing
| Title | Improving Adversarial Robustness via Attention and Adversarial Logit Pairing |
| Authors | Dou Goodman, Xingjian Li, Jun Huan, Tao Wei |
| Abstract | Though deep neural networks have achieved the state of the art performance in visual classification, recent studies have shown that they are all vulnerable to the attack of adversarial examples. In this paper, we develop improved techniques for defending against adversarial examples.First, we introduce enhanced defense using a technique we call \textbf{Attention and Adversarial Logit Pairing(AT+ALP)}, a method that encourages both attention map and logit for pairs of examples to be similar. When applied to clean examples and their adversarial counterparts, \textbf{AT+ALP} improves accuracy on adversarial examples over adversarial training.Next,We show that our \textbf{AT+ALP} can effectively increase the average activations of adversarial examples in the key area and demonstrate that it focuse on more discriminate features to improve the robustness of the model.Finally,we conducte extensive experiments using a wide range of datasets and the experiment results show that our \textbf{AT+ALP} achieves \textbf{the state of the art} defense.For example,on \textbf{17 Flower Category Database}, under strong 200-iteration \textbf{PGD} gray-box and black-box attacks where prior art has 34% and 39% accuracy, our method achieves \textbf{50%} and \textbf{51%}.Compared with previous work,our work is evaluated under highly challenging PGD attack:the maximum perturbation $\epsilon \in {0.25,0.5}$ i.e. $L_\infty \in {0.25,0.5}$ with 10 to 200 attack iterations.To our knowledge, such a strong attack has not been previously explored on a wide range of datasets. |
| Tasks | |
| Published | 2019-08-23 |
| URL | https://arxiv.org/abs/1908.11435v1 |
| https://arxiv.org/pdf/1908.11435v1.pdf | |
| PWC | https://paperswithcode.com/paper/improving-adversarial-robustness-via-1 |
| Repo | |
| Framework | |
Using Dynamic Embeddings to Improve Static Embeddings
| Title | Using Dynamic Embeddings to Improve Static Embeddings |
| Authors | Yile Wang, Leyang Cui, Yue Zhang |
| Abstract | How to build high-quality word embeddings is a fundamental research question in the field of natural language processing. Traditional methods such as Skip-Gram and Continuous Bag-of-Words learn {\it static} embeddings by training lookup tables that translate words into dense vectors. Static embeddings are directly useful for solving lexical semantics tasks, and can be used as input representations for downstream problems. Recently, contextualized embeddings such as BERT have been shown more effective than static embeddings as NLP input embeddings. Such embeddings are {\it dynamic}, calculated according to a sentential context using a network structure. One limitation of dynamic embeddings, however, is that they cannot be used without a sentence-level context. We explore the advantages of dynamic embeddings for training static embeddings, by using contextualized embeddings to facilitate training of static embedding lookup tables. Results show that the resulting embeddings outperform existing static embedding methods on various lexical semantics tasks. |
| Tasks | Word Embeddings |
| Published | 2019-11-07 |
| URL | https://arxiv.org/abs/1911.02929v1 |
| https://arxiv.org/pdf/1911.02929v1.pdf | |
| PWC | https://paperswithcode.com/paper/using-dynamic-embeddings-to-improve-static |
| Repo | |
| Framework | |
On Constructing Confidence Region for Model Parameters in Stochastic Gradient Descent via Batch Means
| Title | On Constructing Confidence Region for Model Parameters in Stochastic Gradient Descent via Batch Means |
| Authors | Yi Zhu, Jing Dong |
| Abstract | In this paper, we study a simple algorithm to construct asymptotically valid confidence regions for model parameters using the batch means method. The main idea is to cancel out the covariance matrix which is hard/costly to estimate. In the process of developing the algorithm, we establish process-level functional central limit theorem for Polyak-Ruppert averaging based stochastic gradient descent estimators. We also extend the batch means method to accommodate more general batch size specifications. |
| Tasks | |
| Published | 2019-11-04 |
| URL | https://arxiv.org/abs/1911.01483v2 |
| https://arxiv.org/pdf/1911.01483v2.pdf | |
| PWC | https://paperswithcode.com/paper/statistical-inference-for-model-parameters-in-1 |
| Repo | |
| Framework | |
Autonomous Goal Exploration using Learned Goal Spaces for Visuomotor Skill Acquisition in Robots
| Title | Autonomous Goal Exploration using Learned Goal Spaces for Visuomotor Skill Acquisition in Robots |
| Authors | Adrien Laversanne-Finot, Alexandre Péré, Pierre-Yves Oudeyer |
| Abstract | The automatic and efficient discovery of skills, without supervision, for long-living autonomous agents, remains a challenge of Artificial Intelligence. Intrinsically Motivated Goal Exploration Processes give learning agents a human-inspired mechanism to sequentially select goals to achieve. This approach gives a new perspective on the lifelong learning problem, with promising results on both simulated and real-world experiments. Until recently, those algorithms were restricted to domains with experimenter-knowledge, since the Goal Space used by the agents was built on engineered feature extractors. The recent advances of deep representation learning, enables new ways of designing those feature extractors, using directly the agent experience. Recent work has shown the potential of those methods on simple yet challenging simulated domains. In this paper, we present recent results showing the applicability of those principles on a real-world robotic setup, where a 6-joint robotic arm learns to manipulate a ball inside an arena, by choosing goals in a space learned from its past experience. |
| Tasks | Representation Learning |
| Published | 2019-06-10 |
| URL | https://arxiv.org/abs/1906.03967v1 |
| https://arxiv.org/pdf/1906.03967v1.pdf | |
| PWC | https://paperswithcode.com/paper/autonomous-goal-exploration-using-learned |
| Repo | |
| Framework | |
A Structured Learning Approach to Temporal Relation Extraction
| Title | A Structured Learning Approach to Temporal Relation Extraction |
| Authors | Qiang Ning, Zhili Feng, Dan Roth |
| Abstract | Identifying temporal relations between events is an essential step towards natural language understanding. However, the temporal relation between two events in a story depends on, and is often dictated by, relations among other events. Consequently, effectively identifying temporal relations between events is a challenging problem even for human annotators. This paper suggests that it is important to take these dependencies into account while learning to identify these relations and proposes a structured learning approach to address this challenge. As a byproduct, this provides a new perspective on handling missing relations, a known issue that hurts existing methods. As we show, the proposed approach results in significant improvements on the two commonly used data sets for this problem. |
| Tasks | Relation Extraction |
| Published | 2019-06-12 |
| URL | https://arxiv.org/abs/1906.04943v1 |
| https://arxiv.org/pdf/1906.04943v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-structured-learning-approach-to-temporal-1 |
| Repo | |
| Framework | |
Early Detection of Research Trends
| Title | Early Detection of Research Trends |
| Authors | Angelo Antonio Salatino |
| Abstract | Being able to rapidly recognise new research trends is strategic for many stakeholders, including universities, institutional funding bodies, academic publishers and companies. The literature presents several approaches to identifying the emergence of new research topics, which rely on the assumption that the topic is already exhibiting a certain degree of popularity and consistently referred to by a community of researchers. However, detecting the emergence of a new research area at an embryonic stage, i.e., before the topic has been consistently labelled by a community of researchers and associated with a number of publications, is still an open challenge. In this dissertation, we begin to address this challenge by performing a study of the dynamics preceding the creation of new topics. This study indicates that the emergence of a new topic is anticipated by a significant increase in the pace of collaboration between relevant research areas, which can be seen as the ‘ancestors’ of the new topic. Based on this understanding, we developed Augur, a novel approach to effectively detecting the emergence of new research topics. Augur analyses the diachronic relationships between research areas and is able to detect clusters of topics that exhibit dynamics correlated with the emergence of new research topics. Here we also present the Advanced Clique Percolation Method (ACPM), a new community detection algorithm developed specifically for supporting this task. Augur was evaluated on a gold standard of 1,408 debutant topics in the 2000-2011 timeframe and outperformed four alternative approaches in terms of both precision and recall. |
| Tasks | Community Detection |
| Published | 2019-11-20 |
| URL | https://arxiv.org/abs/1912.08928v1 |
| https://arxiv.org/pdf/1912.08928v1.pdf | |
| PWC | https://paperswithcode.com/paper/early-detection-of-research-trends |
| Repo | |
| Framework | |
Proposing a Localized Relevance Vector Machine for Pattern Classification
| Title | Proposing a Localized Relevance Vector Machine for Pattern Classification |
| Authors | Farhood Rismanchian, Karim Rahimian |
| Abstract | Relevance vector machine (RVM) can be seen as a probabilistic version of support vector machines which is able to produce sparse solutions by linearly weighting a small number of basis functions instead using all of them. Regardless of a few merits of RVM such as giving probabilistic predictions and relax of parameter tuning, it has poor prediction for test instances that are far away from the relevance vectors. As a solution, we propose a new combination of RVM and k-nearest neighbor (k-NN) rule which resolves this issue with regionally dealing with every test instance. In our settings, we obtain the relevance vectors for each test instance in the local area given by k-NN rule. In this way, relevance vectors are closer and more relevant to the test instance which results in a more accurate model. This can be seen as a piece-wise learner which locally classifies test instances. The model is hence called localized relevance vector machine (LRVM). The LRVM is examined on several datasets of the University of California, Irvine (UCI) repository. Results supported by statistical tests indicate that the performance of LRVM is competitive as compared with a few state-of-the-art classifiers. |
| Tasks | |
| Published | 2019-04-07 |
| URL | http://arxiv.org/abs/1904.03688v1 |
| http://arxiv.org/pdf/1904.03688v1.pdf | |
| PWC | https://paperswithcode.com/paper/proposing-a-localized-relevance-vector |
| Repo | |
| Framework | |
Restricted Boltzmann Stochastic Block Model: A Generative Model for Networks with Attributes
| Title | Restricted Boltzmann Stochastic Block Model: A Generative Model for Networks with Attributes |
| Authors | Shubham Gupta, Ambedkar Dukkipati, Rui M. Castro |
| Abstract | In most practical contexts network indexed data consists not only of a description about the presence/absence of links, but also attributes and information about the nodes and/or links. Building on success of Stochastic Block Models (SBM) we propose a simple yet powerful generalization of SBM for networks with node attributes. In a standard SBM the rows of latent community membership matrix are sampled from a multinomial. In RB-SBM, our proposed model, these rows are sampled from a Restricted Boltzmann Machine (RBM) that models a joint distribution over observed attributes and latent community membership. This model has the advantage of being simple while combining connectivity and attribute information, and it has very few tuning parameters. Furthermore, we show that inference can be done efficiently in linear time and it can be naturally extended to accommodate, for instance, overlapping communities. We demonstrate the performance of our model on multiple synthetic and real world networks with node attributes where we obtain state-of-the-art results on the task of community detection. |
| Tasks | Community Detection |
| Published | 2019-11-11 |
| URL | https://arxiv.org/abs/1911.04172v1 |
| https://arxiv.org/pdf/1911.04172v1.pdf | |
| PWC | https://paperswithcode.com/paper/restricted-boltzmann-stochastic-block-model-a |
| Repo | |
| Framework | |
A Simple but Effective Method to Incorporate Multi-turn Context with BERT for Conversational Machine Comprehension
| Title | A Simple but Effective Method to Incorporate Multi-turn Context with BERT for Conversational Machine Comprehension |
| Authors | Yasuhito Ohsugi, Itsumi Saito, Kyosuke Nishida, Hisako Asano, Junji Tomita |
| Abstract | Conversational machine comprehension (CMC) requires understanding the context of multi-turn dialogue. Using BERT, a pre-training language model, has been successful for single-turn machine comprehension, while modeling multiple turns of question answering with BERT has not been established because BERT has a limit on the number and the length of input sequences. In this paper, we propose a simple but effective method with BERT for CMC. Our method uses BERT to encode a paragraph independently conditioned with each question and each answer in a multi-turn context. Then, the method predicts an answer on the basis of the paragraph representations encoded with BERT. The experiments with representative CMC datasets, QuAC and CoQA, show that our method outperformed recently published methods (+0.8 F1 on QuAC and +2.1 F1 on CoQA). In addition, we conducted a detailed analysis of the effects of the number and types of dialogue history on the accuracy of CMC, and we found that the gold answer history, which may not be given in an actual conversation, contributed to the model performance most on both datasets. |
| Tasks | Language Modelling, Question Answering, Reading Comprehension |
| Published | 2019-05-30 |
| URL | https://arxiv.org/abs/1905.12848v1 |
| https://arxiv.org/pdf/1905.12848v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-simple-but-effective-method-to-incorporate |
| Repo | |
| Framework | |
