Paper Group ANR 226
DROGON: A Causal Reasoning Framework for Future Trajectory Forecast. Multi-Layer Softmaxing during Training Neural Machine Translation for Flexible Decoding with Fewer Layers. Dictionary learning approach to monitoring of wind turbine drivetrain bearings. Speech Sentiment Analysis via Pre-trained Features from End-to-end ASR Models. PhysGAN: Genera …
DROGON: A Causal Reasoning Framework for Future Trajectory Forecast
| Title | DROGON: A Causal Reasoning Framework for Future Trajectory Forecast |
| Authors | Chiho Choi, Abhishek Patil, Srikanth Malla |
| Abstract | We propose DROGON (Deep RObust Goal-Oriented trajectory prediction Network) for accurate vehicle trajectory forecast by considering behavioral intention of vehicles in traffic scenes. Our main insight is that a causal relationship between intention and behavior of drivers can be reasoned from the observation of their relational interactions toward an environment. To succeed in causal reasoning, we build a conditional prediction model to forecast goal-oriented trajectories, which is trained with the following stages: (i) relational inference where we encode relational interactions of vehicles using the perceptual context; (ii) intention estimation to compute the probability distribution of intentional goals based on the inferred relations; and (iii) causal reasoning where we reason about the behavior of vehicles as future locations conditioned on the intention. To properly evaluate the performance of our approach, we present a new large-scale dataset collected at road intersections with diverse interactions of vehicles. The experiments demonstrate the efficacy of DROGON as it consistently outperforms state-of-the-art techniques. |
| Tasks | Trajectory Prediction |
| Published | 2019-07-31 |
| URL | https://arxiv.org/abs/1908.00024v2 |
| https://arxiv.org/pdf/1908.00024v2.pdf | |
| PWC | https://paperswithcode.com/paper/drogon-a-causal-reasoning-framework-for |
| Repo | |
| Framework | |
Multi-Layer Softmaxing during Training Neural Machine Translation for Flexible Decoding with Fewer Layers
| Title | Multi-Layer Softmaxing during Training Neural Machine Translation for Flexible Decoding with Fewer Layers |
| Authors | Raj Dabre, Atsushi Fujita |
| Abstract | This paper proposes a novel procedure for training an encoder-decoder based deep neural network which compresses NxM models into a single model enabling us to dynamically choose the number of encoder and decoder layers for decoding. Usually, the output of the last layer of the N-layer encoder is fed to the M-layer decoder, and the output of the last decoder layer is used to compute softmax loss. Instead, our method computes a single loss consisting of NxM losses: the softmax loss for the output of each of the M decoder layers derived using the output of each of the N encoder layers. A single model trained by our method can be used for decoding with an arbitrary fewer number of encoder and decoder layers. In practical scenarios, this (a) enables faster decoding with insignificant losses in translation quality and (b) alleviates the need to train NxM models, thereby saving space. We take a case study of neural machine translation and show the advantage and give a cost-benefit analysis of our approach. |
| Tasks | Machine Translation |
| Published | 2019-08-27 |
| URL | https://arxiv.org/abs/1908.10118v2 |
| https://arxiv.org/pdf/1908.10118v2.pdf | |
| PWC | https://paperswithcode.com/paper/multi-layer-softmaxing-during-training-neural |
| Repo | |
| Framework | |
Dictionary learning approach to monitoring of wind turbine drivetrain bearings
| Title | Dictionary learning approach to monitoring of wind turbine drivetrain bearings |
| Authors | Sergio Martin-del-Campo, Fredrik Sandin, Daniel Strömbergsson |
| Abstract | Condition monitoring is central to the efficient operation of wind farms due to the challenging operating conditions, rapid technology development and large number of aging wind turbines. In particular, predictive maintenance planning requires the early detection of faults with few false positives. Achieving this type of detection is a challenging problem due to the complex and weak signatures of some faults, particularly the faults that occur in some of the drivetrain bearings. Here, we investigate recently proposed condition monitoring methods based on unsupervised dictionary learning using vibration data recorded over 46 months under typical industrial operations. Thus, we contribute novel test results and real world data that are made publicly available. The results of former studies addressing condition monitoring tasks using dictionary learning indicate that unsupervised feature learning is useful for diagnosis and anomaly detection purposes. However, these studies are based on small sets of labeled data from test rigs operating under controlled conditions that focus on classification tasks, which are useful for quantitative method comparisons but gives little insight into how useful these approaches are in practice. In this study, dictionaries are learned from gearbox vibrations in six different turbines, and the dictionaries are subsequently propagated over a few years of monitoring data when faults are known to occur. We perform the experiment using two different sparse coding algorithms to investigate if the algorithm selected affects the features of abnormal conditions. We calculate the dictionary distance between the initial and propagated dictionaries and find the time periods of abnormal dictionary adaptation starting six months before a drivetrain bearing replacement and one year before the resulting gearbox replacement. |
| Tasks | Anomaly Detection, Dictionary Learning |
| Published | 2019-02-04 |
| URL | https://arxiv.org/abs/1902.01426v2 |
| https://arxiv.org/pdf/1902.01426v2.pdf | |
| PWC | https://paperswithcode.com/paper/dictionary-learning-approach-to-monitoring-of |
| Repo | |
| Framework | |
Speech Sentiment Analysis via Pre-trained Features from End-to-end ASR Models
| Title | Speech Sentiment Analysis via Pre-trained Features from End-to-end ASR Models |
| Authors | Zhiyun Lu, Liangliang Cao, Yu Zhang, Chung-Cheng Chiu, James Fan |
| Abstract | In this paper, we propose to use pre-trained features from end-to-end ASR models to solve speech sentiment analysis as a down-stream task. We show that end-to-end ASR features, which integrate both acoustic and text information from speech, achieve promising results. We use RNN with self-attention as the sentiment classifier, which also provides an easy visualization through attention weights to help interpret model predictions. We use well benchmarked IEMOCAP dataset and a new large-scale speech sentiment dataset SWBD-sentiment for evaluation. Our approach improves the-state-of-the-art accuracy on IEMOCAP from 66.6% to 71.7%, and achieves an accuracy of 70.10% on SWBD-sentiment with more than 49,500 utterances. |
| Tasks | End-To-End Speech Recognition, Sentiment Analysis |
| Published | 2019-11-21 |
| URL | https://arxiv.org/abs/1911.09762v2 |
| https://arxiv.org/pdf/1911.09762v2.pdf | |
| PWC | https://paperswithcode.com/paper/speech-sentiment-analysis-via-pre-trained |
| Repo | |
| Framework | |
PhysGAN: Generating Physical-World-Resilient Adversarial Examples for Autonomous Driving
| Title | PhysGAN: Generating Physical-World-Resilient Adversarial Examples for Autonomous Driving |
| Authors | Zelun Kong, Junfeng Guo, Ang Li, Cong Liu |
| Abstract | Although Deep neural networks (DNNs) are being pervasively used in vision-based autonomous driving systems, they are found vulnerable to adversarial attacks where small-magnitude perturbations into the inputs during test time cause dramatic changes to the outputs. While most of the recent attack methods target at digital-world adversarial scenarios, it is unclear how they perform in the physical world, and more importantly, the generated perturbations under such methods would cover a whole driving scene including those fixed background imagery such as the sky, making them inapplicable to physical world implementation. We present PhysGAN, which generates physical-world-resilient adversarial examples for mislead-ing autonomous driving systems in a continuous manner. We show the effectiveness and robustness of PhysGAN via extensive digital and real-world evaluations. Digital experiments show that PhysGAN is effective for various steer-ing models and scenes, which misleads the average steer-ing angle by up to 23.06 degrees under various scenarios. The real-world studies further demonstrate that PhysGAN is sufficiently resilient in practice, which misleads the average steering angle by up to 19.17 degrees. We compare PhysGAN with a set of state-of-the-art baseline methods including several of our self-designed ones, which further demonstrate the robustness and efficacy of our approach. We also show that PhysGAN outperforms state-of-the-art baseline methods To the best of our knowledge, PhysGANis probably the first technique of generating realistic and physical-world-resilient adversarial examples for attacking common autonomous driving scenarios. |
| Tasks | Autonomous Driving, Image Classification |
| Published | 2019-07-09 |
| URL | https://arxiv.org/abs/1907.04449v2 |
| https://arxiv.org/pdf/1907.04449v2.pdf | |
| PWC | https://paperswithcode.com/paper/generating-adversarial-fragments-with |
| Repo | |
| Framework | |
Contextual Recurrent Units for Cloze-style Reading Comprehension
| Title | Contextual Recurrent Units for Cloze-style Reading Comprehension |
| Authors | Yiming Cui, Wei-Nan Zhang, Wanxiang Che, Ting Liu, Zhipeng Chen, Shijin Wang, Guoping Hu |
| Abstract | Recurrent Neural Networks (RNN) are known as powerful models for handling sequential data, and especially widely utilized in various natural language processing tasks. In this paper, we propose Contextual Recurrent Units (CRU) for enhancing local contextual representations in neural networks. The proposed CRU injects convolutional neural networks (CNN) into the recurrent units to enhance the ability to model the local context and reducing word ambiguities even in bi-directional RNNs. We tested our CRU model on sentence-level and document-level modeling NLP tasks: sentiment classification and reading comprehension. Experimental results show that the proposed CRU model could give significant improvements over traditional CNN or RNN models, including bidirectional conditions, as well as various state-of-the-art systems on both tasks, showing its promising future of extensibility to other NLP tasks as well. |
| Tasks | Reading Comprehension, Sentiment Analysis |
| Published | 2019-11-14 |
| URL | https://arxiv.org/abs/1911.05960v1 |
| https://arxiv.org/pdf/1911.05960v1.pdf | |
| PWC | https://paperswithcode.com/paper/contextual-recurrent-units-for-cloze-style |
| Repo | |
| Framework | |
A deterministic and computable Bernstein-von Mises theorem
| Title | A deterministic and computable Bernstein-von Mises theorem |
| Authors | Guillaume P. Dehaene |
| Abstract | Bernstein-von Mises results (BvM) establish that the Laplace approximation is asymptotically correct in the large-data limit. However, these results are inappropriate for computational purposes since they only hold over most, and not all, datasets and involve hard-to-estimate constants. In this article, I present a new BvM theorem which bounds the Kullback-Leibler (KL) divergence between a fixed log-concave density $f\left(\boldsymbol{\theta}\right)$ and its Laplace approximation. The bound goes to $0$ as the higher-derivatives of $f\left(\boldsymbol{\theta}\right)$ tend to $0$ and $f\left(\boldsymbol{\theta}\right)$ becomes increasingly Gaussian. The classical BvM theorem in the IID large-data asymptote is recovered as a corollary. Critically, this theorem further suggests a number of computable approximations of the KL divergence with the most promising being: [ KL\left(g_{LAP},f\right)\approx\frac{1}{2}\text{Var}_{\boldsymbol{\theta}\sim g\left(\boldsymbol{\theta}\right)}\left(\log\left[f\left(\boldsymbol{\theta}\right)\right]-\log\left[g_{LAP}\left(\boldsymbol{\theta}\right)\right]\right) ] An empirical investigation of these bounds in the logistic classification model reveals that these approximations are great surrogates for the KL divergence. This result, and future results of a similar nature, could provide a path towards rigorously controlling the error due to the Laplace approximation and more modern approximation methods. |
| Tasks | |
| Published | 2019-04-04 |
| URL | http://arxiv.org/abs/1904.02505v2 |
| http://arxiv.org/pdf/1904.02505v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-deterministic-and-computable-bernstein-von |
| Repo | |
| Framework | |
TGAN: Deep Tensor Generative Adversarial Nets for Large Image Generation
| Title | TGAN: Deep Tensor Generative Adversarial Nets for Large Image Generation |
| Authors | Zihan Ding, Xiao-Yang Liu, Miao Yin, Linghe Kong |
| Abstract | Deep generative models have been successfully applied to many applications. However, existing works experience limitations when generating large images (the literature usually generates small images, e.g. 32 * 32 or 128 * 128). In this paper, we propose a novel scheme, called deep tensor adversarial generative nets (TGAN), that generates large high-quality images by exploring tensor structures. Essentially, the adversarial process of TGAN takes place in a tensor space. First, we impose tensor structures for concise image representation, which is superior in capturing the pixel proximity information and the spatial patterns of elementary objects in images, over the vectorization preprocess in existing works. Secondly, we propose TGAN that integrates deep convolutional generative adversarial networks and tensor super-resolution in a cascading manner, to generate high-quality images from random distributions. More specifically, we design a tensor super-resolution process that consists of tensor dictionary learning and tensor coefficients learning. Finally, on three datasets, the proposed TGAN generates images with more realistic textures, compared with state-of-the-art adversarial autoencoders. The size of the generated images is increased by over 8.5 times, namely 374 * 374 in PASCAL2. |
| Tasks | Dictionary Learning, Image Generation, Super-Resolution |
| Published | 2019-01-28 |
| URL | http://arxiv.org/abs/1901.09953v2 |
| http://arxiv.org/pdf/1901.09953v2.pdf | |
| PWC | https://paperswithcode.com/paper/tgan-deep-tensor-generative-adversarial-nets |
| Repo | |
| Framework | |
Teaching Perception
| Title | Teaching Perception |
| Authors | Jonathan Connell |
| Abstract | The visual world is very rich and generally too complex to perceive in its entirety. Yet only certain features are typically required to adequately perform some task in a given situation. Rather than hardwire-in decisions about when and what to sense, this paper describes a robotic system whose behavioral policy can be set by verbal instructions it receives. These capabilities are demonstrated in an associated video showing the fully implemented system guiding the perception of a physical robot in simple scenario. The structure and functioning of the underlying natural language based symbolic reasoning system is also discussed. |
| Tasks | |
| Published | 2019-11-21 |
| URL | https://arxiv.org/abs/1911.11620v1 |
| https://arxiv.org/pdf/1911.11620v1.pdf | |
| PWC | https://paperswithcode.com/paper/teaching-perception |
| Repo | |
| Framework | |
BERTs of a feather do not generalize together: Large variability in generalization across models with similar test set performance
| Title | BERTs of a feather do not generalize together: Large variability in generalization across models with similar test set performance |
| Authors | R. Thomas McCoy, Junghyun Min, Tal Linzen |
| Abstract | If the same neural architecture is trained multiple times on the same dataset, will it make similar linguistic generalizations across runs? To study this question, we fine-tuned 100 instances of BERT on the Multi-genre Natural Language Inference (MNLI) dataset and evaluated them on the HANS dataset, which measures syntactic generalization in natural language inference. On the MNLI development set, the behavior of all instances was remarkably consistent, with accuracy ranging between 83.6% and 84.8%. In stark contrast, the same models varied widely in their generalization performance. For example, on the simple case of subject-object swap (e.g., knowing that “the doctor visited the lawyer” does not entail “the lawyer visited the doctor”), accuracy ranged from 0.00% to 66.2%. Such variation likely arises from the presence of many local minima that are equally attractive to a low-bias learner such as a neural network; decreasing the variability may therefore require models with stronger inductive biases. |
| Tasks | Natural Language Inference |
| Published | 2019-11-07 |
| URL | https://arxiv.org/abs/1911.02969v1 |
| https://arxiv.org/pdf/1911.02969v1.pdf | |
| PWC | https://paperswithcode.com/paper/berts-of-a-feather-do-not-generalize-together |
| Repo | |
| Framework | |
On the Global Geometry of Sphere-Constrained Sparse Blind Deconvolution
| Title | On the Global Geometry of Sphere-Constrained Sparse Blind Deconvolution |
| Authors | Yuqian Zhang, Yenson Lau, Han-Wen Kuo, Sky Cheung, Abhay Pasupathy, John Wright |
| Abstract | Blind deconvolution is the problem of recovering a convolutional kernel $\boldsymbol a_0$ and an activation signal $\boldsymbol x_0$ from their convolution $\boldsymbol y = \boldsymbol a_0 \circledast \boldsymbol x_0$. This problem is ill-posed without further constraints or priors. This paper studies the situation where the nonzero entries in the activation signal are sparsely and randomly populated. We normalize the convolution kernel to have unit Frobenius norm and cast the sparse blind deconvolution problem as a nonconvex optimization problem over the sphere. With this spherical constraint, every spurious local minimum turns out to be close to some signed shift truncation of the ground truth, under certain hypotheses. This benign property motivates an effective two stage algorithm that recovers the ground truth from the partial information offered by a suboptimal local minimum. This geometry-inspired algorithm recovers the ground truth for certain microscopy problems, also exhibits promising performance in the more challenging image deblurring problem. Our insights into the global geometry and the two stage algorithm extend to the convolutional dictionary learning problem, where a superposition of multiple convolution signals is observed. |
| Tasks | Deblurring, Dictionary Learning |
| Published | 2019-01-07 |
| URL | http://arxiv.org/abs/1901.01913v1 |
| http://arxiv.org/pdf/1901.01913v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-global-geometry-of-sphere-constrained |
| Repo | |
| Framework | |
Query-Specific Knowledge Summarization with Entity Evolutionary Networks
| Title | Query-Specific Knowledge Summarization with Entity Evolutionary Networks |
| Authors | Carl Yang, Lingrui Gan, Zongyi Wang, Jiaming Shen, Jinfeng Xiao, Jiawei Han |
| Abstract | Given a query, unlike traditional IR that finds relevant documents or entities, in this work, we focus on retrieving both entities and their connections for insightful knowledge summarization. For example, given a query “computer vision” on a CS literature corpus, rather than returning a list of relevant entities like “cnn”, “imagenet” and “svm”, we are interested in the connections among them, and furthermore, the evolution patterns of such connections along particular ordinal dimensions such as time. Particularly, we hope to provide structural knowledge relevant to the query, such as “svm” is related to “imagenet” but not “cnn”. Moreover, we aim to model the changing trends of the connections, such as “cnn” becomes highly related to “imagenet” after 2010, which enables the tracking of knowledge evolutions. In this work, to facilitate such a novel insightful search system, we propose \textsc{SetEvolve}, which is a unified framework based on nonparanomal graphical models for evolutionary network construction from large text corpora. Systematic experiments on synthetic data and insightful case studies on real-world corpora demonstrate the utility of \textsc{SetEvolve}. |
| Tasks | |
| Published | 2019-09-29 |
| URL | https://arxiv.org/abs/1909.13183v1 |
| https://arxiv.org/pdf/1909.13183v1.pdf | |
| PWC | https://paperswithcode.com/paper/query-specific-knowledge-summarization-with |
| Repo | |
| Framework | |
Integrated analysis of the urban water-electricity demand nexus in the Midwestern United States
| Title | Integrated analysis of the urban water-electricity demand nexus in the Midwestern United States |
| Authors | Renee Obringer, Rohini Kumar, Roshanak Nateghi |
| Abstract | Considering the interdependencies between water and electricity use is critical for ensuring conservation measures are successful in lowering the net water and electricity use in a city. This water-electricity demand nexus will become even more important as cities continue to grow, causing water and electricity utilities additional stress, especially given the likely impacts of future global climatic and socioeconomic changes. Here, we propose a modeling framework based in statistical learning theory for predicting the climate-sensitive portion of the coupled water-electricity demand nexus. The predictive models were built and tested on six Midwestern cities. The results showed that water use was better predicted than electricity use, indicating that water use is slightly more sensitive to climate than electricity use. Additionally, the results demonstrated the importance of the variability in the El Nino/Southern Oscillation index, which explained the majority of the covariance in the water-electricity nexus. Our modeling results suggest that stronger El Ninos lead to an overall increase in water and electricity use in these cities. The integrated modeling framework presented here can be used to characterize the climate-related sensitivity of the water-electricity demand nexus, accounting for the coupled water and electricity use rather than modeling them separately, as independent variables. |
| Tasks | |
| Published | 2019-02-26 |
| URL | http://arxiv.org/abs/1902.10697v1 |
| http://arxiv.org/pdf/1902.10697v1.pdf | |
| PWC | https://paperswithcode.com/paper/integrated-analysis-of-the-urban-water |
| Repo | |
| Framework | |
Method and Dataset Mining in Scientific Papers
| Title | Method and Dataset Mining in Scientific Papers |
| Authors | Rujing Yao, Linlin Hou, Yingchun Ye, Ou Wu, Ji Zhang, Jian Wu |
| Abstract | Literature analysis facilitates researchers better understanding the development of science and technology. The conventional literature analysis focuses on the topics, authors, abstracts, keywords, references, etc., and rarely pays attention to the content of papers. In the field of machine learning, the involved methods (M) and datasets (D) are key information in papers. The extraction and mining of M and D are useful for discipline analysis and algorithm recommendation. In this paper, we propose a novel entity recognition model, called MDER, and constructe datasets from the papers of the PAKDD conferences (2009-2019). Some preliminary experiments are conducted to assess the extraction performance and the mining results are visualized. |
| Tasks | |
| Published | 2019-11-29 |
| URL | https://arxiv.org/abs/1911.13096v1 |
| https://arxiv.org/pdf/1911.13096v1.pdf | |
| PWC | https://paperswithcode.com/paper/method-and-dataset-mining-in-scientific |
| Repo | |
| Framework | |
Automated Lane Change Decision Making using Deep Reinforcement Learning in Dynamic and Uncertain Highway Environment
| Title | Automated Lane Change Decision Making using Deep Reinforcement Learning in Dynamic and Uncertain Highway Environment |
| Authors | Ali Alizadeh, Majid Moghadam, Yunus Bicer, Nazim Kemal Ure, Ugur Yavas, Can Kurtulus |
| Abstract | Autonomous lane changing is a critical feature for advanced autonomous driving systems, that involves several challenges such as uncertainty in other driver’s behaviors and the trade-off between safety and agility. In this work, we develop a novel simulation environment that emulates these challenges and train a deep reinforcement learning agent that yields consistent performance in a variety of dynamic and uncertain traffic scenarios. Results show that the proposed data-driven approach performs significantly better in noisy environments compared to methods that rely solely on heuristics. |
| Tasks | Autonomous Driving, Decision Making |
| Published | 2019-09-18 |
| URL | https://arxiv.org/abs/1909.11538v1 |
| https://arxiv.org/pdf/1909.11538v1.pdf | |
| PWC | https://paperswithcode.com/paper/automated-lane-change-decision-making-using |
| Repo | |
| Framework | |
