Paper Group AWR 74
Model-Based Reinforcement Learning via Meta-Policy Optimization. Neural-Davidsonian Semantic Proto-role Labeling. Deep Learning based Early Detection and Grading of Diabetic Retinopathy Using Retinal Fundus Images. Bi-Directional Block Self-Attention for Fast and Memory-Efficient Sequence Modeling. Generalized Cross Entropy Loss for Training Deep N …
Model-Based Reinforcement Learning via Meta-Policy Optimization
Title | Model-Based Reinforcement Learning via Meta-Policy Optimization |
Authors | Ignasi Clavera, Jonas Rothfuss, John Schulman, Yasuhiro Fujita, Tamim Asfour, Pieter Abbeel |
Abstract | Model-based reinforcement learning approaches carry the promise of being data efficient. However, due to challenges in learning dynamics models that sufficiently match the real-world dynamics, they struggle to achieve the same asymptotic performance as model-free methods. We propose Model-Based Meta-Policy-Optimization (MB-MPO), an approach that foregoes the strong reliance on accurate learned dynamics models. Using an ensemble of learned dynamic models, MB-MPO meta-learns a policy that can quickly adapt to any model in the ensemble with one policy gradient step. This steers the meta-policy towards internalizing consistent dynamics predictions among the ensemble while shifting the burden of behaving optimally w.r.t. the model discrepancies towards the adaptation step. Our experiments show that MB-MPO is more robust to model imperfections than previous model-based approaches. Finally, we demonstrate that our approach is able to match the asymptotic performance of model-free methods while requiring significantly less experience. |
Tasks | |
Published | 2018-09-14 |
URL | http://arxiv.org/abs/1809.05214v1 |
http://arxiv.org/pdf/1809.05214v1.pdf | |
PWC | https://paperswithcode.com/paper/model-based-reinforcement-learning-via-meta |
Repo | https://github.com/muupan/resume |
Framework | none |
Neural-Davidsonian Semantic Proto-role Labeling
Title | Neural-Davidsonian Semantic Proto-role Labeling |
Authors | Rachel Rudinger, Adam Teichert, Ryan Culkin, Sheng Zhang, Benjamin Van Durme |
Abstract | We present a model for semantic proto-role labeling (SPRL) using an adapted bidirectional LSTM encoding strategy that we call “Neural-Davidsonian”: predicate-argument structure is represented as pairs of hidden states corresponding to predicate and argument head tokens of the input sequence. We demonstrate: (1) state-of-the-art results in SPRL, and (2) that our network naturally shares parameters between attributes, allowing for learning new attribute types with limited added supervision. |
Tasks | |
Published | 2018-04-21 |
URL | https://arxiv.org/abs/1804.07976v3 |
https://arxiv.org/pdf/1804.07976v3.pdf | |
PWC | https://paperswithcode.com/paper/neural-davidsonian-semantic-proto-role |
Repo | https://github.com/decomp-sem/neural-sprl |
Framework | pytorch |
Deep Learning based Early Detection and Grading of Diabetic Retinopathy Using Retinal Fundus Images
Title | Deep Learning based Early Detection and Grading of Diabetic Retinopathy Using Retinal Fundus Images |
Authors | Sheikh Muhammad Saiful Islam, Md Mahedi Hasan, Sohaib Abdullah |
Abstract | Diabetic Retinopathy (DR) is a constantly deteriorating disease, being one of the leading causes of vision impairment and blindness. Subtle distinction among different grades and existence of many significant small features make the task of recognition very challenging. In addition, the present approach of retinopathy detection is a very laborious and time-intensive task, which heavily relies on the skill of a physician. Automated detection of diabetic retinopathy is essential to tackle these problems. Early-stage detection of diabetic retinopathy is also very important for diagnosis, which can prevent blindness with proper treatment. In this paper, we developed a novel deep convolutional neural network, which performs the early-stage detection by identifying all microaneurysms (MAs), the first signs of DR, along with correctly assigning labels to retinal fundus images which are graded into five categories. We have tested our network on the largest publicly available Kaggle diabetic retinopathy dataset, and achieved 0.851 quadratic weighted kappa score and 0.844 AUC score, which achieves the state-of-the-art performance on severity grading. In the early-stage detection, we have achieved a sensitivity of 98% and specificity of above 94%, which demonstrates the effectiveness of our proposed method. Our proposed architecture is at the same time very simple and efficient with respect to computational time and space are concerned. |
Tasks | |
Published | 2018-12-27 |
URL | http://arxiv.org/abs/1812.10595v1 |
http://arxiv.org/pdf/1812.10595v1.pdf | |
PWC | https://paperswithcode.com/paper/deep-learning-based-early-detection-and |
Repo | https://github.com/saifulislampharma/ratinopathy |
Framework | none |
Bi-Directional Block Self-Attention for Fast and Memory-Efficient Sequence Modeling
Title | Bi-Directional Block Self-Attention for Fast and Memory-Efficient Sequence Modeling |
Authors | Tao Shen, Tianyi Zhou, Guodong Long, Jing Jiang, Chengqi Zhang |
Abstract | Recurrent neural networks (RNN), convolutional neural networks (CNN) and self-attention networks (SAN) are commonly used to produce context-aware representations. RNN can capture long-range dependency but is hard to parallelize and not time-efficient. CNN focuses on local dependency but does not perform well on some tasks. SAN can model both such dependencies via highly parallelizable computation, but memory requirement grows rapidly in line with sequence length. In this paper, we propose a model, called “bi-directional block self-attention network (Bi-BloSAN)", for RNN/CNN-free sequence encoding. It requires as little memory as RNN but with all the merits of SAN. Bi-BloSAN splits the entire sequence into blocks, and applies an intra-block SAN to each block for modeling local context, then applies an inter-block SAN to the outputs for all blocks to capture long-range dependency. Thus, each SAN only needs to process a short sequence, and only a small amount of memory is required. Additionally, we use feature-level attention to handle the variation of contexts around the same word, and use forward/backward masks to encode temporal order information. On nine benchmark datasets for different NLP tasks, Bi-BloSAN achieves or improves upon state-of-the-art accuracy, and shows better efficiency-memory trade-off than existing RNN/CNN/SAN. |
Tasks | |
Published | 2018-04-03 |
URL | http://arxiv.org/abs/1804.00857v1 |
http://arxiv.org/pdf/1804.00857v1.pdf | |
PWC | https://paperswithcode.com/paper/bi-directional-block-self-attention-for-fast |
Repo | https://github.com/taoshen58/BiBloSA |
Framework | tf |
Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels
Title | Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels |
Authors | Zhilu Zhang, Mert R. Sabuncu |
Abstract | Deep neural networks (DNNs) have achieved tremendous success in a variety of applications across many disciplines. Yet, their superior performance comes with the expensive cost of requiring correctly annotated large-scale datasets. Moreover, due to DNNs’ rich capacity, errors in training labels can hamper performance. To combat this problem, mean absolute error (MAE) has recently been proposed as a noise-robust alternative to the commonly-used categorical cross entropy (CCE) loss. However, as we show in this paper, MAE can perform poorly with DNNs and challenging datasets. Here, we present a theoretically grounded set of noise-robust loss functions that can be seen as a generalization of MAE and CCE. Proposed loss functions can be readily applied with any existing DNN architecture and algorithm, while yielding good performance in a wide range of noisy label scenarios. We report results from experiments conducted with CIFAR-10, CIFAR-100 and FASHION-MNIST datasets and synthetically generated noisy labels. |
Tasks | |
Published | 2018-05-20 |
URL | http://arxiv.org/abs/1805.07836v4 |
http://arxiv.org/pdf/1805.07836v4.pdf | |
PWC | https://paperswithcode.com/paper/generalized-cross-entropy-loss-for-training |
Repo | https://github.com/AlanChou/Truncated-Loss |
Framework | pytorch |
An Improvement of Data Classification Using Random Multimodel Deep Learning (RMDL)
Title | An Improvement of Data Classification Using Random Multimodel Deep Learning (RMDL) |
Authors | Mojtaba Heidarysafa, Kamran Kowsari, Donald E. Brown, Kiana Jafari Meimandi, Laura E. Barnes |
Abstract | The exponential growth in the number of complex datasets every year requires more enhancement in machine learning methods to provide robust and accurate data classification. Lately, deep learning approaches have achieved surpassing results in comparison to previous machine learning algorithms. However, finding the suitable structure for these models has been a challenge for researchers. This paper introduces Random Multimodel Deep Learning (RMDL): a new ensemble, deep learning approach for classification. RMDL solves the problem of finding the best deep learning structure and architecture while simultaneously improving robustness and accuracy through ensembles of deep learning architectures. In short, RMDL trains multiple randomly generated models of Deep Neural Network (DNN), Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) in parallel and combines their results to produce better result of any of those models individually. In this paper, we describe RMDL model and compare the results for image and text classification as well as face recognition. We used MNIST and CIFAR-10 datasets as ground truth datasets for image classification and WOS, Reuters, IMDB, and 20newsgroup datasets for text classification. Lastly, we used ORL dataset to compare the model performance on face recognition task. |
Tasks | Face Recognition, Image Classification, Text Classification |
Published | 2018-08-23 |
URL | http://arxiv.org/abs/1808.08121v1 |
http://arxiv.org/pdf/1808.08121v1.pdf | |
PWC | https://paperswithcode.com/paper/an-improvement-of-data-classification-using |
Repo | https://github.com/kk7nc/RMDL |
Framework | tf |
Better Conversations by Modeling,Filtering,and Optimizing for Coherence and Diversity
Title | Better Conversations by Modeling,Filtering,and Optimizing for Coherence and Diversity |
Authors | Xinnuo Xu, Ondřej Dušek, Ioannis Konstas, Verena Rieser |
Abstract | We present three enhancements to existing encoder-decoder models for open-domain conversational agents, aimed at effectively modeling coherence and promoting output diversity: (1) We introduce a measure of coherence as the GloVe embedding similarity between the dialogue context and the generated response, (2) we filter our training corpora based on the measure of coherence to obtain topically coherent and lexically diverse context-response pairs, (3) we then train a response generator using a conditional variational autoencoder model that incorporates the measure of coherence as a latent variable and uses a context gate to guarantee topical consistency with the context and promote lexical diversity. Experiments on the OpenSubtitles corpus show a substantial improvement over competitive neural models in terms of BLEU score as well as metrics of coherence and diversity. |
Tasks | |
Published | 2018-09-18 |
URL | http://arxiv.org/abs/1809.06873v1 |
http://arxiv.org/pdf/1809.06873v1.pdf | |
PWC | https://paperswithcode.com/paper/better-conversations-by-modelingfilteringand |
Repo | https://github.com/ricsinaruto/dialog-eval |
Framework | none |
Inference in Probabilistic Graphical Models by Graph Neural Networks
Title | Inference in Probabilistic Graphical Models by Graph Neural Networks |
Authors | KiJung Yoon, Renjie Liao, Yuwen Xiong, Lisa Zhang, Ethan Fetaya, Raquel Urtasun, Richard Zemel, Xaq Pitkow |
Abstract | A fundamental computation for statistical inference and accurate decision-making is to compute the marginal probabilities or most probable states of task-relevant variables. Probabilistic graphical models can efficiently represent the structure of such complex data, but performing these inferences is generally difficult. Message-passing algorithms, such as belief propagation, are a natural way to disseminate evidence amongst correlated variables while exploiting the graph structure, but these algorithms can struggle when the conditional dependency graphs contain loops. Here we use Graph Neural Networks (GNNs) to learn a message-passing algorithm that solves these inference tasks. We first show that the architecture of GNNs is well-matched to inference tasks. We then demonstrate the efficacy of this inference approach by training GNNs on a collection of graphical models and showing that they substantially outperform belief propagation on loopy graphs. Our message-passing algorithms generalize out of the training set to larger graphs and graphs with different structure. |
Tasks | Decision Making |
Published | 2018-03-21 |
URL | https://arxiv.org/abs/1803.07710v5 |
https://arxiv.org/pdf/1803.07710v5.pdf | |
PWC | https://paperswithcode.com/paper/inference-in-probabilistic-graphical-models |
Repo | https://github.com/anvinhnguyendinh/InferencePGMbyGNN |
Framework | tf |
DeepImageSpam: Deep Learning based Image Spam Detection
Title | DeepImageSpam: Deep Learning based Image Spam Detection |
Authors | Amara Dinesh Kumar, Vinayakumar R, Soman KP |
Abstract | Hackers and spammers are employing innovative and novel techniques to deceive novice and even knowledgeable internet users. Image spam is one of such technique where the spammer varies and changes some portion of the image such that it is indistinguishable from the original image fooling the users. This paper proposes a deep learning based approach for image spam detection using the convolutional neural networks which uses a dataset with 810 natural images and 928 spam images for classification achieving an accuracy of 91.7% outperforming the existing image processing and machine learning techniques |
Tasks | |
Published | 2018-10-03 |
URL | http://arxiv.org/abs/1810.03977v1 |
http://arxiv.org/pdf/1810.03977v1.pdf | |
PWC | https://paperswithcode.com/paper/deepimagespam-deep-learning-based-image-spam |
Repo | https://github.com/vinayakumarr/maching-learning-CDAC-Technopark |
Framework | tf |
DADA: Deep Adversarial Data Augmentation for Extremely Low Data Regime Classification
Title | DADA: Deep Adversarial Data Augmentation for Extremely Low Data Regime Classification |
Authors | Xiaofeng Zhang, Zhangyang Wang, Dong Liu, Qing Ling |
Abstract | Deep learning has revolutionized the performance of classification, but meanwhile demands sufficient labeled data for training. Given insufficient data, while many techniques have been developed to help combat overfitting, the challenge remains if one tries to train deep networks, especially in the ill-posed extremely low data regimes: only a small set of labeled data are available, and nothing – including unlabeled data – else. Such regimes arise from practical situations where not only data labeling but also data collection itself is expensive. We propose a deep adversarial data augmentation (DADA) technique to address the problem, in which we elaborately formulate data augmentation as a problem of training a class-conditional and supervised generative adversarial network (GAN). Specifically, a new discriminator loss is proposed to fit the goal of data augmentation, through which both real and augmented samples are enforced to contribute to and be consistent in finding the decision boundaries. Tailored training techniques are developed accordingly. To quantitatively validate its effectiveness, we first perform extensive simulations to show that DADA substantially outperforms both traditional data augmentation and a few GAN-based options. We then extend experiments to three real-world small labeled datasets where existing data augmentation and/or transfer learning strategies are either less effective or infeasible. All results endorse the superior capability of DADA in enhancing the generalization ability of deep networks trained in practical extremely low data regimes. Source code is available at https://github.com/SchafferZhang/DADA. |
Tasks | Data Augmentation, Transfer Learning |
Published | 2018-08-29 |
URL | http://arxiv.org/abs/1809.00981v1 |
http://arxiv.org/pdf/1809.00981v1.pdf | |
PWC | https://paperswithcode.com/paper/dada-deep-adversarial-data-augmentation-for |
Repo | https://github.com/SchafferZhang/DADA |
Framework | none |
Topic-based Evaluation for Conversational Bots
Title | Topic-based Evaluation for Conversational Bots |
Authors | Fenfei Guo, Angeliki Metallinou, Chandra Khatri, Anirudh Raju, Anu Venkatesh, Ashwin Ram |
Abstract | Dialog evaluation is a challenging problem, especially for non task-oriented dialogs where conversational success is not well-defined. We propose to evaluate dialog quality using topic-based metrics that describe the ability of a conversational bot to sustain coherent and engaging conversations on a topic, and the diversity of topics that a bot can handle. To detect conversation topics per utterance, we adopt Deep Average Networks (DAN) and train a topic classifier on a variety of question and query data categorized into multiple topics. We propose a novel extension to DAN by adding a topic-word attention table that allows the system to jointly capture topic keywords in an utterance and perform topic classification. We compare our proposed topic based metrics with the ratings provided by users and show that our metrics both correlate with and complement human judgment. Our analysis is performed on tens of thousands of real human-bot dialogs from the Alexa Prize competition and highlights user expectations for conversational bots. |
Tasks | |
Published | 2018-01-11 |
URL | http://arxiv.org/abs/1801.03622v1 |
http://arxiv.org/pdf/1801.03622v1.pdf | |
PWC | https://paperswithcode.com/paper/topic-based-evaluation-for-conversational |
Repo | https://github.com/knights207210/Deep-Learning-for-VUI |
Framework | pytorch |
Overview of PicTropes, a film trope dataset
Title | Overview of PicTropes, a film trope dataset |
Authors | Rubén H. García-Ortega, Juan J. Merelo-Guervós, Pablo García Sánchez, Gad Pitaru |
Abstract | From the database DBTropes.org, we have created a dataset of films and the tropes that they use, which we have called PicTropes. In this report we provide the descriptive analysis and a further discussion on the dataset PicTropes: The extracted features will help us decide the best values for a future recommendation system and content generator, whereas the analysis of the distribution functions that fit the best will help us interpret the relation between the films and the tropes that were found inside them. Additionally, we provide rankings of the top-25 tropes and films, which will help us discuss and formulate questions to guide future extensions of the PicTropes dataset. |
Tasks | |
Published | 2018-09-28 |
URL | http://arxiv.org/abs/1809.10959v2 |
http://arxiv.org/pdf/1809.10959v2.pdf | |
PWC | https://paperswithcode.com/paper/overview-of-pictropes-a-film-trope-dataset |
Repo | https://github.com/raiben/tropes_open_data |
Framework | none |
A Neural Transition-based Model for Nested Mention Recognition
Title | A Neural Transition-based Model for Nested Mention Recognition |
Authors | Bailin Wang, Wei Lu, Yu Wang, Hongxia Jin |
Abstract | It is common that entity mentions can contain other mentions recursively. This paper introduces a scalable transition-based method to model the nested structure of mentions. We first map a sentence with nested mentions to a designated forest where each mention corresponds to a constituent of the forest. Our shift-reduce based system then learns to construct the forest structure in a bottom-up manner through an action sequence whose maximal length is guaranteed to be three times of the sentence length. Based on Stack-LSTM which is employed to efficiently and effectively represent the states of the system in a continuous space, our system is further incorporated with a character-based component to capture letter-level patterns. Our model achieves the state-of-the-art results on ACE datasets, showing its effectiveness in detecting nested mentions. |
Tasks | Named Entity Recognition, Nested Mention Recognition, Nested Named Entity Recognition |
Published | 2018-10-03 |
URL | http://arxiv.org/abs/1810.01808v1 |
http://arxiv.org/pdf/1810.01808v1.pdf | |
PWC | https://paperswithcode.com/paper/a-neural-transition-based-model-for-nested |
Repo | https://github.com/berlino/nest-trans-em18 |
Framework | pytorch |
Benchmarking Neural Network Robustness to Common Corruptions and Surface Variations
Title | Benchmarking Neural Network Robustness to Common Corruptions and Surface Variations |
Authors | Dan Hendrycks, Thomas G. Dietterich |
Abstract | In this paper we establish rigorous benchmarks for image classifier robustness. Our first benchmark, ImageNet-C, standardizes and expands the corruption robustness topic, while showing which classifiers are preferable in safety-critical applications. Unlike recent robustness research, this benchmark evaluates performance on commonplace corruptions not worst-case adversarial corruptions. We find that there are negligible changes in relative corruption robustness from AlexNet to ResNet classifiers, and we discover ways to enhance corruption robustness. Then we propose a new dataset called Icons-50 which opens research on a new kind of robustness, surface variation robustness. With this dataset we evaluate the frailty of classifiers on new styles of known objects and unexpected instances of known classes. We also demonstrate two methods that improve surface variation robustness. Together our benchmarks may aid future work toward networks that learn fundamental class structure and also robustly generalize. |
Tasks | Adversarial Defense |
Published | 2018-07-04 |
URL | http://arxiv.org/abs/1807.01697v5 |
http://arxiv.org/pdf/1807.01697v5.pdf | |
PWC | https://paperswithcode.com/paper/benchmarking-neural-network-robustness-to |
Repo | https://github.com/bethgelab/imagecorruptions |
Framework | none |
Foreground Segmentation Using a Triplet Convolutional Neural Network for Multiscale Feature Encoding
Title | Foreground Segmentation Using a Triplet Convolutional Neural Network for Multiscale Feature Encoding |
Authors | Long Ang Lim, Hacer Yalim Keles |
Abstract | A common approach for moving objects segmentation in a scene is to perform a background subtraction. Several methods have been proposed in this domain. However, they lack the ability of handling various difficult scenarios such as illumination changes, background or camera motion, camouflage effect, shadow etc. To address these issues, we propose a robust and flexible encoder-decoder type neural network based approach. We adapt a pre-trained convolutional network, i.e. VGG-16 Net, under a triplet framework in the encoder part to embed an image in multiple scales into the feature space and use a transposed convolutional network in the decoder part to learn a mapping from feature space to image space. We train this network end-to-end by using only a few training samples. Our network takes an RGB image in three different scales and produces a foreground segmentation probability mask for the corresponding image. In order to evaluate our model, we entered the Change Detection 2014 Challenge (changedetection.net) and our method outperformed all the existing state-of-the-art methods by an average F-Measure of 0.9770. Our source code will be made publicly available at https://github.com/lim-anggun/FgSegNet. |
Tasks | |
Published | 2018-01-07 |
URL | http://arxiv.org/abs/1801.02225v1 |
http://arxiv.org/pdf/1801.02225v1.pdf | |
PWC | https://paperswithcode.com/paper/foreground-segmentation-using-a-triplet |
Repo | https://github.com/lim-anggun/FgSegNet |
Framework | tf |