Paper Group ANR 331
Brazilian Lyrics-Based Music Genre Classification Using a BLSTM Network. Towards Safer Self-Driving Through Great PAIN (Physically Adversarial Intelligent Networks). Automatic Data Augmentation via Deep Reinforcement Learning for Effective Kidney Tumor Segmentation. Multi-Agent Deep Reinforcement Learning for Cooperative Connected Vehicles. The Pow …
Brazilian Lyrics-Based Music Genre Classification Using a BLSTM Network
| Title | Brazilian Lyrics-Based Music Genre Classification Using a BLSTM Network |
| Authors | Raul de Araújo Lima, Rômulo César Costa de Sousa, Simone Diniz Junqueira Barbosa, Hélio Cortês Vieira Lopes |
| Abstract | Organize songs, albums, and artists in groups with shared similarity could be done with the help of genre labels. In this paper, we present a novel approach for automatic classifying musical genre in Brazilian music using only the song lyrics. This kind of classification remains a challenge in the field of Natural Language Processing. We construct a dataset of 138,368 Brazilian song lyrics distributed in 14 genres. We apply SVM, Random Forest and a Bidirectional Long Short-Term Memory (BLSTM) network combined with different word embeddings techniques to address this classification task. Our experiments show that the BLSTM method outperforms the other models with an F1-score average of $0.48$. Some genres like “gospel”, “funk-carioca” and “sertanejo”, which obtained 0.89, 0.70 and 0.69 of F1-score, respectively, can be defined as the most distinct and easy to classify in the Brazilian musical genres context. |
| Tasks | Word Embeddings |
| Published | 2020-03-06 |
| URL | https://arxiv.org/abs/2003.05377v1 |
| https://arxiv.org/pdf/2003.05377v1.pdf | |
| PWC | https://paperswithcode.com/paper/brazilian-lyrics-based-music-genre |
| Repo | |
| Framework | |
Towards Safer Self-Driving Through Great PAIN (Physically Adversarial Intelligent Networks)
| Title | Towards Safer Self-Driving Through Great PAIN (Physically Adversarial Intelligent Networks) |
| Authors | Piyush Gupta, Demetris Coleman, Joshua E. Siegel |
| Abstract | Automated vehicles’ neural networks suffer from overfit, poor generalizability, and untrained edge cases due to limited data availability. Researchers synthesize randomized edge-case scenarios to assist in the training process, though simulation introduces potential for overfit to latent rules and features. Automating worst-case scenario generation could yield informative data for improving self driving. To this end, we introduce a “Physically Adversarial Intelligent Network” (PAIN), wherein self-driving vehicles interact aggressively in the CARLA simulation environment. We train two agents, a protagonist and an adversary, using dueling double deep Q networks (DDDQNs) with prioritized experience replay. The coupled networks alternately seek-to-collide and to avoid collisions such that the “defensive” avoidance algorithm increases the mean-time-to-failure and distance traveled under non-hostile operating conditions. The trained protagonist becomes more resilient to environmental uncertainty and less prone to corner case failures resulting in collisions than the agent trained without an adversary. |
| Tasks | |
| Published | 2020-03-24 |
| URL | https://arxiv.org/abs/2003.10662v1 |
| https://arxiv.org/pdf/2003.10662v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-safer-self-driving-through-great-pain |
| Repo | |
| Framework | |
Automatic Data Augmentation via Deep Reinforcement Learning for Effective Kidney Tumor Segmentation
| Title | Automatic Data Augmentation via Deep Reinforcement Learning for Effective Kidney Tumor Segmentation |
| Authors | Tiexin Qin, Ziyuan Wang, Kelei He, Yinghuan Shi, Yang Gao, Dinggang Shen |
| Abstract | Conventional data augmentation realized by performing simple pre-processing operations (\eg, rotation, crop, \etc) has been validated for its advantage in enhancing the performance for medical image segmentation. However, the data generated by these conventional augmentation methods are random and sometimes harmful to the subsequent segmentation. In this paper, we developed a novel automatic learning-based data augmentation method for medical image segmentation which models the augmentation task as a trial-and-error procedure using deep reinforcement learning (DRL). In our method, we innovatively combine the data augmentation module and the subsequent segmentation module in an end-to-end training manner with a consistent loss. Specifically, the best sequential combination of different basic operations is automatically learned by directly maximizing the performance improvement (\ie, Dice ratio) on the available validation set. We extensively evaluated our method on CT kidney tumor segmentation which validated the promising results of our method. |
| Tasks | Data Augmentation, Medical Image Segmentation, Semantic Segmentation |
| Published | 2020-02-22 |
| URL | https://arxiv.org/abs/2002.09703v1 |
| https://arxiv.org/pdf/2002.09703v1.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-data-augmentation-via-deep |
| Repo | |
| Framework | |
Multi-Agent Deep Reinforcement Learning for Cooperative Connected Vehicles
| Title | Multi-Agent Deep Reinforcement Learning for Cooperative Connected Vehicles |
| Authors | Dohyun Kwon, Joongheon Kim |
| Abstract | Millimeter-wave (mmWave) base station can offer abundant high capacity channel resources toward connected vehicles so that quality-of-service (QoS) of them in terms of downlink throughput can be highly improved. The mmWave base station can operate among existing base stations (e.g., macro-cell base station) on non-overlapped channels among them and the vehicles can make decision what base station to associate, and what channel to utilize on heterogeneous networks. Furthermore, because of the non-omni property of mmWave communication, the vehicles decide how to align the beam direction toward mmWave base station to associate with it. However, such joint problem requires high computational cost, which is NP-hard and has combinatorial features. In this paper, we solve the problem in 3-tier heterogeneous vehicular network (HetVNet) with multi-agent deep reinforcement learning (DRL) in a way that maximizes expected total reward (i.e., downlink throughput) of vehicles. The multi-agent deep deterministic policy gradient (MADDPG) approach is introduced to achieve optimal policy in continuous action domain. |
| Tasks | |
| Published | 2020-01-08 |
| URL | https://arxiv.org/abs/2001.02337v1 |
| https://arxiv.org/pdf/2001.02337v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-agent-deep-reinforcement-learning-for-4 |
| Repo | |
| Framework | |
The Power of Linear Controllers in LQR Control
| Title | The Power of Linear Controllers in LQR Control |
| Authors | Gautam Goel, Babak Hassibi |
| Abstract | The Linear Quadratic Regulator (LQR) framework considers the problem of regulating a linear dynamical system perturbed by environmental noise. We compute the policy regret between three distinct control policies: i) the optimal online policy, whose linear structure is given by the Ricatti equations; ii) the optimal offline linear policy, which is the best linear state feedback policy given the noise sequence; and iii) the optimal offline policy, which selects the globally optimal control actions given the noise sequence. We fully characterize the optimal offline policy and show that it has a recursive form in terms of the optimal online policy and future disturbances. We also show that cost of the optimal offline linear policy converges to the cost of the optimal online policy as the time horizon grows large, and consequently the optimal offline linear policy incurs linear regret relative to the optimal offline policy, even in the optimistic setting where the noise is drawn i.i.d from a known distribution. Although we focus on the setting where the noise is stochastic, our results also imply new lower bounds on the policy regret achievable when the noise is chosen by an adaptive adversary. |
| Tasks | |
| Published | 2020-02-07 |
| URL | https://arxiv.org/abs/2002.02574v1 |
| https://arxiv.org/pdf/2002.02574v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-power-of-linear-controllers-in-lqr |
| Repo | |
| Framework | |
Rainy screens: Collecting rainy datasets, indoors
| Title | Rainy screens: Collecting rainy datasets, indoors |
| Authors | Horia Porav, Valentina-Nicoleta Musat, Tom Bruls, Paul Newman |
| Abstract | Acquisition of data with adverse conditions in robotics is a cumbersome task due to the difficulty in guaranteeing proper ground truth and synchronising with desired weather conditions. In this paper, we present a simple method - recording a high resolution screen - for generating diverse rainy images from existing clear ground-truth images that is domain- and source-agnostic, simple and scales up. This setup allows us to leverage the diversity of existing datasets with auxiliary task ground-truth data, such as semantic segmentation, object positions etc. We generate rainy images with real adherent droplets and rain streaks based on Cityscapes and BDD, and train a de-raining model. We present quantitative results for image reconstruction and semantic segmentation, and qualitative results for an out-of-sample domain, showing that models trained with our data generalize well. |
| Tasks | Image Reconstruction, Semantic Segmentation |
| Published | 2020-03-10 |
| URL | https://arxiv.org/abs/2003.04742v1 |
| https://arxiv.org/pdf/2003.04742v1.pdf | |
| PWC | https://paperswithcode.com/paper/rainy-screens-collecting-rainy-datasets |
| Repo | |
| Framework | |
Data Augmentation for Copy-Mechanism in Dialogue State Tracking
| Title | Data Augmentation for Copy-Mechanism in Dialogue State Tracking |
| Authors | Xiaohui Song, Liangjun Zang, Yipeng Su, Xing Wu, Jizhong Han, Songlin Hu |
| Abstract | While several state-of-the-art approaches to dialogue state tracking (DST) have shown promising performances on several benchmarks, there is still a significant performance gap between seen slot values (i.e., values that occur in both training set and test set) and unseen ones (values that occur in training set but not in test set). Recently, the copy-mechanism has been widely used in DST models to handle unseen slot values, which copies slot values from user utterance directly. In this paper, we aim to find out the factors that influence the generalization ability of a common copy-mechanism model for DST. Our key observations include: 1) the copy-mechanism tends to memorize values rather than infer them from contexts, which is the primary reason for unsatisfactory generalization performance; 2) greater diversity of slot values in the training set increase the performance on unseen values but slightly decrease the performance on seen values. Moreover, we propose a simple but effective algorithm of data augmentation to train copy-mechanism models, which augments the input dataset by copying user utterances and replacing the real slot values with randomly generated strings. Users could use two hyper-parameters to realize a trade-off between the performances on seen values and unseen ones, as well as a trade-off between overall performance and computational cost. Experimental results on three widely used datasets (WoZ 2.0, DSTC2, and Multi-WoZ 2.0) show the effectiveness of our approach. |
| Tasks | Data Augmentation, Dialogue State Tracking |
| Published | 2020-02-22 |
| URL | https://arxiv.org/abs/2002.09634v1 |
| https://arxiv.org/pdf/2002.09634v1.pdf | |
| PWC | https://paperswithcode.com/paper/data-augmentation-for-copy-mechanism-in |
| Repo | |
| Framework | |
A Non-Dominated Sorting Based Customized Random-Key Genetic Algorithm for the Bi-Objective Traveling Thief Problem
| Title | A Non-Dominated Sorting Based Customized Random-Key Genetic Algorithm for the Bi-Objective Traveling Thief Problem |
| Authors | Jonatas B. C. Chagas, Julian Blank, Markus Wagner, Marcone J. F. Souza, Kalyanmoy Deb |
| Abstract | In this paper, we propose a method to solve a bi-objective variant of the well-studied Traveling Thief Problem (TTP). The TTP is a multi-component problem that combines two classic combinatorial problems: Traveling Salesman Problem (TSP) and Knapsack Problem (KP). In the TTP, a thief has to visit each city exactly once and can pick items throughout their journey. The thief begins their journey with an empty knapsack and travels with a speed inversely proportional to the knapsack weight. We address the BI-TTP, a bi-objective version of the TTP, where the goal is to minimize the overall traveling time and to maximize the profit of the collected items. Our method is based on a genetic algorithm with customization addressing problem characteristics. We incorporate domain knowledge through a combination of near-optimal solutions of each subproblem in the initial population and a custom repair operation to avoid the evaluation of infeasible solutions. Moreover, the independent variables of the TSP and KP components are unified to a real variable representation by using a biased random-key approach. The bi-objective aspect of the problem is addressed through an elite population extracted based on the non-dominated rank and crowding distance of each solution. Furthermore, we provide a comprehensive study which shows the influence of hyperparameters on the performance of our method and investigate the performance of each hyperparameter combination over time. In addition to our experiments, we discuss the results of the BI-TTP competitions at EMO-2019 and GECCO-2019 conferences where our method has won first and second place, respectively, thus proving its ability to find high-quality solutions consistently. |
| Tasks | |
| Published | 2020-02-11 |
| URL | https://arxiv.org/abs/2002.04303v1 |
| https://arxiv.org/pdf/2002.04303v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-non-dominated-sorting-based-customized |
| Repo | |
| Framework | |
GLU Variants Improve Transformer
| Title | GLU Variants Improve Transformer |
| Authors | Noam Shazeer |
| Abstract | Gated Linear Units (arXiv:1612.08083) consist of the component-wise product of two linear projections, one of which is first passed through a sigmoid function. Variations on GLU are possible, using different nonlinear (or even linear) functions in place of sigmoid. We test these variants in the feed-forward sublayers of the Transformer (arXiv:1706.03762) sequence-to-sequence model, and find that some of them yield quality improvements over the typically-used ReLU or GELU activations. |
| Tasks | |
| Published | 2020-02-12 |
| URL | https://arxiv.org/abs/2002.05202v1 |
| https://arxiv.org/pdf/2002.05202v1.pdf | |
| PWC | https://paperswithcode.com/paper/glu-variants-improve-transformer |
| Repo | |
| Framework | |
The benefits of synthetic data for action categorization
| Title | The benefits of synthetic data for action categorization |
| Authors | Mohamad Ballout, Mohammad Tuqan, Daniel Asmar, Elie Shammas, George Sakr |
| Abstract | In this paper, we study the value of using synthetically produced videos as training data for neural networks used for action categorization. Motivated by the fact that texture and background of a video play little to no significant roles in optical flow, we generated simplified texture-less and background-less videos and utilized the synthetic data to train a Temporal Segment Network (TSN). The results demonstrated that augmenting TSN with simplified synthetic data improved the original network accuracy (68.5%), achieving 71.8% on HMDB-51 when adding 4,000 videos and 72.4% when adding 8,000 videos. Also, training using simplified synthetic videos alone on 25 classes of UCF-101 achieved 30.71% when trained on 2500 videos and 52.7% when trained on 5000 videos. Finally, results showed that when reducing the number of real videos of UCF-25 to 10% and combining them with synthetic videos, the accuracy drops to only 85.41%, compared to a drop to 77.4% when no synthetic data is added. |
| Tasks | Optical Flow Estimation |
| Published | 2020-01-20 |
| URL | https://arxiv.org/abs/2001.11091v1 |
| https://arxiv.org/pdf/2001.11091v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-benefits-of-synthetic-data-for-action |
| Repo | |
| Framework | |
Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output Observations
| Title | Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output Observations |
| Authors | Aditya Golatkar, Alessandro Achille, Stefano Soatto |
| Abstract | We describe a procedure for removing dependency on a cohort of training data from a trained deep network that improves upon and generalizes previous methods to different readout functions and can be extended to ensure forgetting in the activations of the network. We introduce a new bound on how much information can be extracted per query about the forgotten cohort from a black-box network for which only the input-output behavior is observed. The proposed forgetting procedure has a deterministic part derived from the differential equations of a linearized version of the model, and a stochastic part that ensures information destruction by adding noise tailored to the geometry of the loss landscape. We exploit the connections between the activation and weight dynamics of a DNN inspired by Neural Tangent Kernels to compute the information in the activations. |
| Tasks | |
| Published | 2020-03-05 |
| URL | https://arxiv.org/abs/2003.02960v2 |
| https://arxiv.org/pdf/2003.02960v2.pdf | |
| PWC | https://paperswithcode.com/paper/forgetting-outside-the-box-scrubbing-deep |
| Repo | |
| Framework | |
Extreme Regression for Dynamic Search Advertising
| Title | Extreme Regression for Dynamic Search Advertising |
| Authors | Yashoteja Prabhu, Aditya Kusupati, Nilesh Gupta, Manik Varma |
| Abstract | This paper introduces a new learning paradigm called eXtreme Regression (XR) whose objective is to accurately predict the numerical degrees of relevance of an extremely large number of labels to a data point. XR can provide elegant solutions to many large-scale ranking and recommendation applications including Dynamic Search Advertising (DSA). XR can learn more accurate models than the recently popular extreme classifiers which incorrectly assume strictly binary-valued label relevances. Traditional regression metrics which sum the errors over all the labels are unsuitable for XR problems since they could give extremely loose bounds for the label ranking quality. Also, the existing regression algorithms won’t efficiently scale to millions of labels. This paper addresses these limitations through: (1) new evaluation metrics for XR which sum only the k largest regression errors; (2) a new algorithm called XReg which decomposes XR task into a hierarchy of much smaller regression problems thus leading to highly efficient training and prediction. This paper also introduces a (3) new labelwise prediction algorithm in XReg useful for DSA and other recommendation tasks. Experiments on benchmark datasets demonstrated that XReg can outperform the state-of-the-art extreme classifiers as well as large-scale regressors and rankers by up to 50% reduction in the new XR error metric, and up to 2% and 2.4% improvements in terms of the propensity-scored precision metric used in extreme classification and the click-through rate metric used in DSA respectively. Deployment of XReg on DSA in Bing resulted in a relative gain of 27% in query coverage. XReg’s source code can be downloaded from http://manikvarma.org/code/XReg/download.html. |
| Tasks | |
| Published | 2020-01-15 |
| URL | https://arxiv.org/abs/2001.05228v3 |
| https://arxiv.org/pdf/2001.05228v3.pdf | |
| PWC | https://paperswithcode.com/paper/extreme-regression-for-dynamic-search |
| Repo | |
| Framework | |
Active Reward Learning for Co-Robotic Vision Based Exploration in Bandwidth Limited Environments
| Title | Active Reward Learning for Co-Robotic Vision Based Exploration in Bandwidth Limited Environments |
| Authors | Stewart Jamieson, Jonathan P. How, Yogesh Girdhar |
| Abstract | We present a novel POMDP problem formulation for a robot that must autonomously decide where to go to collect new and scientifically relevant images given a limited ability to communicate with its human operator. From this formulation we derive constraints and design principles for the observation model, reward model, and communication strategy of such a robot, exploring techniques to deal with the very high-dimensional observation space and scarcity of relevant training data. We introduce a novel active reward learning strategy based on making queries to help the robot minimize path “regret” online, and evaluate it for suitability in autonomous visual exploration through simulations. We demonstrate that, in some bandwidth-limited environments, this novel regret-based criterion enables the robotic explorer to collect up to 17% more reward per mission than the next-best criterion. |
| Tasks | |
| Published | 2020-03-10 |
| URL | https://arxiv.org/abs/2003.05016v1 |
| https://arxiv.org/pdf/2003.05016v1.pdf | |
| PWC | https://paperswithcode.com/paper/active-reward-learning-for-co-robotic-vision |
| Repo | |
| Framework | |
Neural Generators of Sparse Local Linear Models for Achieving both Accuracy and Interpretability
| Title | Neural Generators of Sparse Local Linear Models for Achieving both Accuracy and Interpretability |
| Authors | Yuya Yoshikawa, Tomoharu Iwata |
| Abstract | For reliability, it is important that the predictions made by machine learning methods are interpretable by human. In general, deep neural networks (DNNs) can provide accurate predictions, although it is difficult to interpret why such predictions are obtained by DNNs. On the other hand, interpretation of linear models is easy, although their predictive performance would be low since real-world data is often intrinsically non-linear. To combine both the benefits of the high predictive performance of DNNs and high interpretability of linear models into a single model, we propose neural generators of sparse local linear models (NGSLLs). The sparse local linear models have high flexibility as they can approximate non-linear functions. The NGSLL generates sparse linear weights for each sample using DNNs that take original representations of each sample (e.g., word sequence) and their simplified representations (e.g., bag-of-words) as input. By extracting features from the original representations, the weights can contain rich information to achieve high predictive performance. Additionally, the prediction is interpretable because it is obtained by the inner product between the simplified representations and the sparse weights, where only a small number of weights are selected by our gate module in the NGSLL. In experiments with real-world datasets, we demonstrate the effectiveness of the NGSLL quantitatively and qualitatively by evaluating prediction performance and visualizing generated weights on image and text classification tasks. |
| Tasks | Text Classification |
| Published | 2020-03-13 |
| URL | https://arxiv.org/abs/2003.06441v1 |
| https://arxiv.org/pdf/2003.06441v1.pdf | |
| PWC | https://paperswithcode.com/paper/neural-generators-of-sparse-local-linear |
| Repo | |
| Framework | |
An Experimental Study of Formula Embeddings for Automated Theorem Proving in First-Order Logic
| Title | An Experimental Study of Formula Embeddings for Automated Theorem Proving in First-Order Logic |
| Authors | Ibrahim Abdelaziz, Veronika Thost, Maxwell Crouse, Achille Fokoue |
| Abstract | Automated theorem proving in first-order logic is an active research area which is successfully supported by machine learning. While there have been various proposals for encoding logical formulas into numerical vectors – from simple strings to more involved graph-based embeddings – little is known about how these different encodings compare. In this paper, we study and experimentally compare pattern-based embeddings that are applied in current systems with popular graph-based encodings, most of which have not been considered in the theorem proving context before. Our experiments show that the advantages of simpler encoding schemes in terms of runtime are outdone by more complex graph-based embeddings, which yield more efficient search strategies and simpler proofs. To support this, we present a detailed analysis across several dimensions of theorem prover performance beyond just proof completion rate, thus providing empirical evidence to help guide future research on neural-guided theorem proving towards the most promising directions. |
| Tasks | Automated Theorem Proving |
| Published | 2020-02-02 |
| URL | https://arxiv.org/abs/2002.00423v2 |
| https://arxiv.org/pdf/2002.00423v2.pdf | |
| PWC | https://paperswithcode.com/paper/an-experimental-study-of-formula-embeddings |
| Repo | |
| Framework | |
