Paper Group AWR 119
Structured Interpretation of Temporal Relations. Scene Text Detection and Recognition: The Deep Learning Era. On the Dimensionality of Word Embedding. CFENet: An Accurate and Efficient Single-Shot Object Detector for Autonomous Driving. Simulation-based Adversarial Test Generation for Autonomous Vehicles with Machine Learning Components. Lovasz Con …
Structured Interpretation of Temporal Relations
Title | Structured Interpretation of Temporal Relations |
Authors | Yuchen Zhang, Nianwen Xue |
Abstract | Temporal relations between events and time expressions in a document are often modeled in an unstructured manner where relations between individual pairs of time expressions and events are considered in isolation. This often results in inconsistent and incomplete annotation and computational modeling. We propose a novel annotation approach where events and time expressions in a document form a dependency tree in which each dependency relation corresponds to an instance of temporal anaphora where the antecedent is the parent and the anaphor is the child. We annotate a corpus of 235 documents using this approach in the two genres of news and narratives, with 48 documents doubly annotated. We report a stable and high inter-annotator agreement on the doubly annotated subset, validating our approach, and perform a quantitative comparison between the two genres of the entire corpus. We make this corpus publicly available. |
Tasks | |
Published | 2018-08-23 |
URL | http://arxiv.org/abs/1808.07599v1 |
http://arxiv.org/pdf/1808.07599v1.pdf | |
PWC | https://paperswithcode.com/paper/structured-interpretation-of-temporal |
Repo | https://github.com/yuchenz/structured_temporal_relations_corpus |
Framework | none |
Scene Text Detection and Recognition: The Deep Learning Era
Title | Scene Text Detection and Recognition: The Deep Learning Era |
Authors | Shangbang Long, Xin He, Cong Yao |
Abstract | With the rise and development of deep learning, computer vision has been tremendously transformed and reshaped. As an important research area in computer vision, scene text detection and recognition has been inescapably influenced by this wave of revolution, consequentially entering the era of deep learning. In recent years, the community has witnessed substantial advancements in mindset, approach and performance. This survey is aimed at summarizing and analyzing the major changes and significant progresses of scene text detection and recognition in the deep learning era. Through this article, we devote to: (1) introduce new insights and ideas; (2) highlight recent techniques and benchmarks; (3) look ahead into future trends. Specifically, we will emphasize the dramatic differences brought by deep learning and the grand challenges still remained. We expect that this review paper would serve as a reference book for researchers in this field. Related resources are also collected and compiled in our Github repository: https://github.com/Jyouhou/SceneTextPapers. |
Tasks | Scene Text Detection |
Published | 2018-11-10 |
URL | https://arxiv.org/abs/1811.04256v4 |
https://arxiv.org/pdf/1811.04256v4.pdf | |
PWC | https://paperswithcode.com/paper/scene-text-detection-and-recognition-the-deep |
Repo | https://github.com/Jyouhou/SceneTextPapers |
Framework | none |
On the Dimensionality of Word Embedding
Title | On the Dimensionality of Word Embedding |
Authors | Zi Yin, Yuanyuan Shen |
Abstract | In this paper, we provide a theoretical understanding of word embedding and its dimensionality. Motivated by the unitary-invariance of word embedding, we propose the Pairwise Inner Product (PIP) loss, a novel metric on the dissimilarity between word embeddings. Using techniques from matrix perturbation theory, we reveal a fundamental bias-variance trade-off in dimensionality selection for word embeddings. This bias-variance trade-off sheds light on many empirical observations which were previously unexplained, for example the existence of an optimal dimensionality. Moreover, new insights and discoveries, like when and how word embeddings are robust to over-fitting, are revealed. By optimizing over the bias-variance trade-off of the PIP loss, we can explicitly answer the open question of dimensionality selection for word embedding. |
Tasks | Word Embeddings |
Published | 2018-12-11 |
URL | http://arxiv.org/abs/1812.04224v1 |
http://arxiv.org/pdf/1812.04224v1.pdf | |
PWC | https://paperswithcode.com/paper/on-the-dimensionality-of-word-embedding |
Repo | https://github.com/aaaasssddf/word-embedding-dimensionality-selection |
Framework | none |
CFENet: An Accurate and Efficient Single-Shot Object Detector for Autonomous Driving
Title | CFENet: An Accurate and Efficient Single-Shot Object Detector for Autonomous Driving |
Authors | Qijie Zhao, Tao Sheng, Yongtao Wang, Feng Ni, Ling Cai |
Abstract | The ability to detect small objects and the speed of the object detector are very important for the application of autonomous driving, and in this paper, we propose an effective yet efficient one-stage detector, which gained the second place in the Road Object Detection competition of CVPR2018 workshop - Workshop of Autonomous Driving(WAD). The proposed detector inherits the architecture of SSD and introduces a novel Comprehensive Feature Enhancement(CFE) module into it. Experimental results on this competition dataset as well as the MSCOCO dataset demonstrate that the proposed detector (named CFENet) performs much better than the original SSD and the state-of-the-art method RefineDet especially for small objects, while keeping high efficiency close to the original SSD. Specifically, the single scale version of the proposed detector can run at the speed of 21 fps, while the multi-scale version with larger input size achieves the mAP 29.69, ranking second on the leaderboard |
Tasks | Autonomous Driving, Object Detection |
Published | 2018-06-26 |
URL | http://arxiv.org/abs/1806.09790v2 |
http://arxiv.org/pdf/1806.09790v2.pdf | |
PWC | https://paperswithcode.com/paper/cfenet-an-accurate-and-efficient-single-shot |
Repo | https://github.com/siddhanthaldar/PyTorch_Object_Detection |
Framework | pytorch |
Simulation-based Adversarial Test Generation for Autonomous Vehicles with Machine Learning Components
Title | Simulation-based Adversarial Test Generation for Autonomous Vehicles with Machine Learning Components |
Authors | Cumhur Erkan Tuncali, Georgios Fainekos, Hisahiro Ito, James Kapinski |
Abstract | Many organizations are developing autonomous driving systems, which are expected to be deployed at a large scale in the near future. Despite this, there is a lack of agreement on appropriate methods to test, debug, and certify the performance of these systems. One of the main challenges is that many autonomous driving systems have machine learning components, such as deep neural networks, for which formal properties are difficult to characterize. We present a testing framework that is compatible with test case generation and automatic falsification methods, which are used to evaluate cyber-physical systems. We demonstrate how the framework can be used to evaluate closed-loop properties of an autonomous driving system model that includes the ML components, all within a virtual environment. We demonstrate how to use test case generation methods, such as covering arrays, as well as requirement falsification methods to automatically identify problematic test scenarios. The resulting framework can be used to increase the reliability of autonomous driving systems. |
Tasks | Autonomous Driving, Autonomous Vehicles |
Published | 2018-04-18 |
URL | http://arxiv.org/abs/1804.06760v4 |
http://arxiv.org/pdf/1804.06760v4.pdf | |
PWC | https://paperswithcode.com/paper/simulation-based-adversarial-test-generation |
Repo | https://github.com/SahilDhull/autonomous |
Framework | tf |
Lovasz Convolutional Networks
Title | Lovasz Convolutional Networks |
Authors | Prateek Yadav, Madhav Nimishakavi, Naganand Yadati, Shikhar Vashishth, Arun Rajkumar, Partha Talukdar |
Abstract | Semi-supervised learning on graph structured data has received significant attention with the recent introduction of Graph Convolution Networks (GCN). While traditional methods have focused on optimizing a loss augmented with Laplacian regularization framework, GCNs perform an implicit Laplacian type regularization to capture local graph structure. In this work, we propose Lovasz Convolutional Network (LCNs) which are capable of incorporating global graph properties. LCNs achieve this by utilizing Lovasz’s orthonormal embeddings of the nodes. We analyse local and global properties of graphs and demonstrate settings where LCNs tend to work better than GCNs. We validate the proposed method on standard random graph models such as stochastic block models (SBM) and certain community structure based graphs where LCNs outperform GCNs and learn more intuitive embeddings. We also perform extensive binary and multi-class classification experiments on real world datasets to demonstrate LCN’s effectiveness. In addition to simple graphs, we also demonstrate the use of LCNs on hyper-graphs by identifying settings where they are expected to work better than GCNs. |
Tasks | |
Published | 2018-05-29 |
URL | http://arxiv.org/abs/1805.11365v3 |
http://arxiv.org/pdf/1805.11365v3.pdf | |
PWC | https://paperswithcode.com/paper/lovasz-convolutional-networks |
Repo | https://github.com/malllabiisc/lcn |
Framework | tf |
Do deep reinforcement learning agents model intentions?
Title | Do deep reinforcement learning agents model intentions? |
Authors | Tambet Matiisen, Aqeel Labash, Daniel Majoral, Jaan Aru, Raul Vicente |
Abstract | Inferring other agents’ mental states such as their knowledge, beliefs and intentions is thought to be essential for effective interactions with other agents. Recently, multiagent systems trained via deep reinforcement learning have been shown to succeed in solving different tasks, but it remains unclear how each agent modeled or represented other agents in their environment. In this work we test whether deep reinforcement learning agents explicitly represent other agents’ intentions (their specific aims or goals) during a task in which the agents had to coordinate the covering of different spots in a 2D environment. In particular, we tracked over time the performance of a linear decoder trained to predict the final goal of all agents from the hidden state of each agent’s neural network controller. We observed that the hidden layers of agents represented explicit information about other agents’ goals, i.e. the target landmark they ended up covering. We also performed a series of experiments, in which some agents were replaced by others with fixed goals, to test the level of generalization of the trained agents. We noticed that during the training phase the agents developed a differential preference for each goal, which hindered generalization. To alleviate the above problem, we propose simple changes to the MADDPG training algorithm which leads to better generalization against unseen agents. We believe that training protocols promoting more active intention reading mechanisms, e.g. by preventing simple symmetry-breaking solutions, is a promising direction towards achieving a more robust generalization in different cooperative and competitive tasks. |
Tasks | |
Published | 2018-05-15 |
URL | http://arxiv.org/abs/1805.06020v2 |
http://arxiv.org/pdf/1805.06020v2.pdf | |
PWC | https://paperswithcode.com/paper/do-deep-reinforcement-learning-agents-model |
Repo | https://github.com/NeuroCSUT/intentions |
Framework | tf |
Trellis Networks for Sequence Modeling
Title | Trellis Networks for Sequence Modeling |
Authors | Shaojie Bai, J. Zico Kolter, Vladlen Koltun |
Abstract | We present trellis networks, a new architecture for sequence modeling. On the one hand, a trellis network is a temporal convolutional network with special structure, characterized by weight tying across depth and direct injection of the input into deep layers. On the other hand, we show that truncated recurrent networks are equivalent to trellis networks with special sparsity structure in their weight matrices. Thus trellis networks with general weight matrices generalize truncated recurrent networks. We leverage these connections to design high-performing trellis networks that absorb structural and algorithmic elements from both recurrent and convolutional models. Experiments demonstrate that trellis networks outperform the current state of the art methods on a variety of challenging benchmarks, including word-level language modeling and character-level language modeling tasks, and stress tests designed to evaluate long-term memory retention. The code is available at https://github.com/locuslab/trellisnet . |
Tasks | Language Modelling, Sequential Image Classification |
Published | 2018-10-15 |
URL | http://arxiv.org/abs/1810.06682v2 |
http://arxiv.org/pdf/1810.06682v2.pdf | |
PWC | https://paperswithcode.com/paper/trellis-networks-for-sequence-modeling |
Repo | https://github.com/locuslab/trellisnet |
Framework | pytorch |
Meta-Learning with Hessian-Free Approach in Deep Neural Nets Training
Title | Meta-Learning with Hessian-Free Approach in Deep Neural Nets Training |
Authors | Boyu Chen, Wenlian Lu, Ernest Fokoue |
Abstract | Meta-learning is a promising method to achieve efficient training method towards deep neural net and has been attracting increases interests in recent years. But most of the current methods are still not capable to train complex neuron net model with long-time training process. In this paper, a novel second-order meta-optimizer, named Meta-learning with Hessian-Free(MLHF) approach, is proposed based on the Hessian-Free approach. Two recurrent neural networks are established to generate the damping and the precondition matrix of this Hessian-Free framework. A series of techniques to meta-train the MLHF towards stable and reinforce the meta-training of this optimizer, including the gradient calculation of $H$. Numerical experiments on deep convolution neural nets, including CUDA-convnet and ResNet18(v2), with datasets of CIFAR10 and ILSVRC2012, indicate that the MLHF shows good and continuous training performance during the whole long-time training process, i.e., both the rapid-decreasing early stage and the steadily-deceasing later stage, and so is a promising meta-learning framework towards elevating the training efficiency in real-world deep neural nets. |
Tasks | Meta-Learning |
Published | 2018-05-22 |
URL | http://arxiv.org/abs/1805.08462v2 |
http://arxiv.org/pdf/1805.08462v2.pdf | |
PWC | https://paperswithcode.com/paper/meta-learning-with-hessian-free-approach-in |
Repo | https://github.com/ozzzp/MLHF |
Framework | tf |
Adaptive Performance Assessment For Drivers Through Behavioral Advantage
Title | Adaptive Performance Assessment For Drivers Through Behavioral Advantage |
Authors | Dicong Qiu, Karthik Paga |
Abstract | The potential positive impact of autonomous driving and driver assistance technolo- gies have been a major impetus over the last decade. On the flip side, it has been a challenging problem to analyze the performance of human drivers or autonomous driving agents quantitatively. In this work, we propose a generic method that compares the performance of drivers or autonomous driving agents even if the environmental conditions are different, by using the driver behavioral advantage instead of absolute metrics, which efficiently removes the environmental factors. A concrete application of the method is also presented, where the performance of more than 100 truck drivers was evaluated and ranked in terms of fuel efficiency, covering more than 90,000 trips spanning an average of 300 miles in a variety of driving conditions and environments. |
Tasks | Autonomous Driving |
Published | 2018-04-23 |
URL | http://arxiv.org/abs/1804.08219v2 |
http://arxiv.org/pdf/1804.08219v2.pdf | |
PWC | https://paperswithcode.com/paper/adaptive-performance-assessment-for-drivers |
Repo | https://github.com/davidqiu1993/Hackauton2018_DolanWins |
Framework | none |
Approximate message-passing for convex optimization with non-separable penalties
Title | Approximate message-passing for convex optimization with non-separable penalties |
Authors | Andre Manoel, Florent Krzakala, Gaël Varoquaux, Bertrand Thirion, Lenka Zdeborová |
Abstract | We introduce an iterative optimization scheme for convex objectives consisting of a linear loss and a non-separable penalty, based on the expectation-consistent approximation and the vector approximate message-passing (VAMP) algorithm. Specifically, the penalties we approach are convex on a linear transformation of the variable to be determined, a notable example being total variation (TV). We describe the connection between message-passing algorithms – typically used for approximate inference – and proximal methods for optimization, and show that our scheme is, as VAMP, similar in nature to the Peaceman-Rachford splitting, with the important difference that stepsizes are set adaptively. Finally, we benchmark the performance of our VAMP-like iteration in problems where TV penalties are useful, namely classification in task fMRI and reconstruction in tomography, and show faster convergence than that of state-of-the-art approaches such as FISTA and ADMM in most settings. |
Tasks | |
Published | 2018-09-17 |
URL | http://arxiv.org/abs/1809.06304v1 |
http://arxiv.org/pdf/1809.06304v1.pdf | |
PWC | https://paperswithcode.com/paper/approximate-message-passing-for-convex |
Repo | https://github.com/ndrmnl/twamp |
Framework | none |
Query and Output: Generating Words by Querying Distributed Word Representations for Paraphrase Generation
Title | Query and Output: Generating Words by Querying Distributed Word Representations for Paraphrase Generation |
Authors | Shuming Ma, Xu Sun, Wei Li, Sujian Li, Wenjie Li, Xuancheng Ren |
Abstract | Most recent approaches use the sequence-to-sequence model for paraphrase generation. The existing sequence-to-sequence model tends to memorize the words and the patterns in the training dataset instead of learning the meaning of the words. Therefore, the generated sentences are often grammatically correct but semantically improper. In this work, we introduce a novel model based on the encoder-decoder framework, called Word Embedding Attention Network (WEAN). Our proposed model generates the words by querying distributed word representations (i.e. neural word embeddings), hoping to capturing the meaning of the according words. Following previous work, we evaluate our model on two paraphrase-oriented tasks, namely text simplification and short text abstractive summarization. Experimental results show that our model outperforms the sequence-to-sequence baseline by the BLEU score of 6.3 and 5.5 on two English text simplification datasets, and the ROUGE-2 F1 score of 5.7 on a Chinese summarization dataset. Moreover, our model achieves state-of-the-art performances on these three benchmark datasets. |
Tasks | Abstractive Text Summarization, Paraphrase Generation, Text Simplification, Word Embeddings |
Published | 2018-03-05 |
URL | http://arxiv.org/abs/1803.01465v3 |
http://arxiv.org/pdf/1803.01465v3.pdf | |
PWC | https://paperswithcode.com/paper/query-and-output-generating-words-by-querying |
Repo | https://github.com/lancopku/WEAN |
Framework | pytorch |
Deep Adversarial Training for Multi-Organ Nuclei Segmentation in Histopathology Images
Title | Deep Adversarial Training for Multi-Organ Nuclei Segmentation in Histopathology Images |
Authors | Faisal Mahmood, Daniel Borders, Richard Chen, Gregory N. McKay, Kevan J. Salimian, Alexander Baras, Nicholas J. Durr |
Abstract | Nuclei segmentation is a fundamental task that is critical for various computational pathology applications including nuclei morphology analysis, cell type classification, and cancer grading. Conventional vision-based methods for nuclei segmentation struggle in challenging cases and deep learning approaches have proven to be more robust and generalizable. However, CNNs require large amounts of labeled histopathology data. Moreover, conventional CNN-based approaches lack structured prediction capabilities which are required to distinguish overlapping and clumped nuclei. Here, we present an approach to nuclei segmentation that overcomes these challenges by utilizing a conditional generative adversarial network (cGAN) trained with synthetic and real data. We generate a large dataset of H&E training images with perfect nuclei segmentation labels using an unpaired GAN framework. This synthetic data along with real histopathology data from six different organs are used to train a conditional GAN with spectral normalization and gradient penalty for nuclei segmentation. This adversarial regression framework enforces higher order consistency when compared to conventional CNN models. We demonstrate that this nuclei segmentation approach generalizes across different organs, sites, patients and disease states, and outperforms conventional approaches, especially in isolating individual and overlapping nuclei. |
Tasks | Structured Prediction |
Published | 2018-09-29 |
URL | http://arxiv.org/abs/1810.00236v2 |
http://arxiv.org/pdf/1810.00236v2.pdf | |
PWC | https://paperswithcode.com/paper/deep-adversarial-training-for-multi-organ |
Repo | https://github.com/faisalml/NucleiSegmentation |
Framework | pytorch |
HoVer-Net: Simultaneous Segmentation and Classification of Nuclei in Multi-Tissue Histology Images
Title | HoVer-Net: Simultaneous Segmentation and Classification of Nuclei in Multi-Tissue Histology Images |
Authors | Simon Graham, Quoc Dang Vu, Shan E Ahmed Raza, Ayesha Azam, Yee Wah Tsang, Jin Tae Kwak, Nasir Rajpoot |
Abstract | Nuclear segmentation and classification within Haematoxylin & Eosin stained histology images is a fundamental prerequisite in the digital pathology work-flow. The development of automated methods for nuclear segmentation and classification enables the quantitative analysis of tens of thousands of nuclei within a whole-slide pathology image, opening up possibilities of further analysis of large-scale nuclear morphometry. However, automated nuclear segmentation and classification is faced with a major challenge in that there are several different types of nuclei, some of them exhibiting large intra-class variability such as the tumour cells. Additionally, some of the nuclei are often clustered together. To address these challenges, we present a novel convolutional neural network for simultaneous nuclear segmentation and classification that leverages the instance-rich information encoded within the vertical and horizontal distances of nuclear pixels to their centres of mass. These distances are then utilised to separate clustered nuclei, resulting in an accurate segmentation, particularly in areas with overlapping instances. Then for each segmented instance, the network predicts the type of nucleus via a devoted up-sampling branch. We demonstrate state-of-the-art performance compared to other methods on multiple independent multi-tissue histology image datasets. As part of this work, we introduce a new dataset of Haematoxylin & Eosin stained colorectal adenocarcinoma image tiles, containing 24,319 exhaustively annotated nuclei with associated class labels. |
Tasks | Nuclear Segmentation |
Published | 2018-12-16 |
URL | https://arxiv.org/abs/1812.06499v5 |
https://arxiv.org/pdf/1812.06499v5.pdf | |
PWC | https://paperswithcode.com/paper/xy-network-for-nuclear-segmentation-in-multi |
Repo | https://github.com/vqdang/xy_net |
Framework | tf |
Nesterov Acceleration of Alternating Least Squares for Canonical Tensor Decomposition: Momentum Step Size Selection and Restart Mechanisms
Title | Nesterov Acceleration of Alternating Least Squares for Canonical Tensor Decomposition: Momentum Step Size Selection and Restart Mechanisms |
Authors | Drew Mitchell, Nan Ye, Hans De Sterck |
Abstract | We present Nesterov-type acceleration techniques for Alternating Least Squares (ALS) methods applied to canonical tensor decomposition. While Nesterov acceleration turns gradient descent into an optimal first-order method for convex problems by adding a momentum term with a specific weight sequence, a direct application of this method and weight sequence to ALS results in erratic convergence behaviour. This is so because the tensor decomposition problem is non-convex and ALS is accelerated instead of gradient descent. Instead, we consider various restart mechanisms and suitable choices of momentum weights that enable effective acceleration. Our extensive empirical results show that the Nesterov-accelerated ALS methods with restart can be dramatically more efficient than the stand-alone ALS or Nesterov accelerated gradient methods, when problems are ill-conditioned or accurate solutions are desired. The resulting methods perform competitively with or superior to existing acceleration methods for ALS, including ALS acceleration by NCG, NGMRES, or LBFGS, and additionally enjoy the benefit of being much easier to implement. We also compare with Nesterov-type updates where the momentum weight is determined by a line search, which are equivalent or closely related to existing line search methods for ALS. On a large and ill-conditioned 71$\times$1000$\times$900 tensor consisting of readings from chemical sensors to track hazardous gases, the restarted Nesterov-ALS method shows desirable robustness properties and outperforms any of the existing methods by a large factor. There is clear potential for extending our Nesterov-type acceleration approach to accelerating other optimization algorithms than ALS applied to other non-convex problems, such as Tucker tensor decomposition. Our Matlab code is available at https://github.com/hansdesterck/nonlinear-preconditioning-for-optimization. |
Tasks | |
Published | 2018-10-13 |
URL | https://arxiv.org/abs/1810.05846v3 |
https://arxiv.org/pdf/1810.05846v3.pdf | |
PWC | https://paperswithcode.com/paper/nesterov-acceleration-of-alternating-least |
Repo | https://github.com/hansdesterck/nonlinear-preconditioning-for-optimization |
Framework | none |