Paper Group AWR 65
GANSynth: Adversarial Neural Audio Synthesis. Color Recognition for Rubik’s Cube Robot. Accelerating Self-Play Learning in Go. Building a Computer Mahjong Player via Deep Convolutional Neural Networks. Functional Isolation Forest. Multiple Landmark Detection using Multi-Agent Reinforcement Learning. Self-Supervised Unconstrained Illumination Invari …
GANSynth: Adversarial Neural Audio Synthesis
| Title | GANSynth: Adversarial Neural Audio Synthesis |
| Authors | Jesse Engel, Kumar Krishna Agrawal, Shuo Chen, Ishaan Gulrajani, Chris Donahue, Adam Roberts |
| Abstract | Efficient audio synthesis is an inherently difficult machine learning task, as human perception is sensitive to both global structure and fine-scale waveform coherence. Autoregressive models, such as WaveNet, model local structure at the expense of global latent structure and slow iterative sampling, while Generative Adversarial Networks (GANs), have global latent conditioning and efficient parallel sampling, but struggle to generate locally-coherent audio waveforms. Herein, we demonstrate that GANs can in fact generate high-fidelity and locally-coherent audio by modeling log magnitudes and instantaneous frequencies with sufficient frequency resolution in the spectral domain. Through extensive empirical investigations on the NSynth dataset, we demonstrate that GANs are able to outperform strong WaveNet baselines on automated and human evaluation metrics, and efficiently generate audio several orders of magnitude faster than their autoregressive counterparts. |
| Tasks | Audio Generation |
| Published | 2019-02-23 |
| URL | http://arxiv.org/abs/1902.08710v2 |
| http://arxiv.org/pdf/1902.08710v2.pdf | |
| PWC | https://paperswithcode.com/paper/gansynth-adversarial-neural-audio-synthesis |
| Repo | https://github.com/tensorflow/magenta |
| Framework | tf |
Color Recognition for Rubik’s Cube Robot
| Title | Color Recognition for Rubik’s Cube Robot |
| Authors | Shenglan Liu, Dong Jiang, Lin Feng, Feilong Wang, Zhanbo Feng, Xiang Liu, Shuai Guo, Bingjun Li, Yuchen Cong |
| Abstract | In this paper, we proposed three methods to solve color recognition of Rubik’s cube, which includes one offline method and two online methods. Scatter balance & extreme learning machine (SB-ELM), a offline method, is proposed to illustrate the efficiency of training based method. We also point out the conception of color drifting which indicates offline methods are always ineffectiveness and can not work well in continuous change circumstance. By contrast, dynamic weight label propagation is proposed for labeling blocks color by known center blocks color of Rubik’s cube. Furthermore, weak label hierarchic propagation, another online method, is also proposed for unknown all color information but only utilizes weak label of center block in color recognition. We finally design a Rubik’s cube robot and construct a dataset to illustrate the efficiency and effectiveness of our online methods and to indicate the ineffectiveness of offline method by color drifting in our dataset. |
| Tasks | |
| Published | 2019-01-11 |
| URL | http://arxiv.org/abs/1901.03470v1 |
| http://arxiv.org/pdf/1901.03470v1.pdf | |
| PWC | https://paperswithcode.com/paper/color-recognition-for-rubiks-cube-robot |
| Repo | https://github.com/eyeeco/Rubick-s-Cube-Dataset |
| Framework | none |
Accelerating Self-Play Learning in Go
| Title | Accelerating Self-Play Learning in Go |
| Authors | David J. Wu |
| Abstract | By introducing several improvements to the AlphaZero process and architecture, we greatly accelerate self-play learning in Go, achieving a 50x reduction in computation over comparable methods. Like AlphaZero and replications such as ELF OpenGo and Leela Zero, our bot KataGo only learns from neural-net-guided Monte Carlo tree search self-play. But whereas AlphaZero required thousands of TPUs over several days and ELF required thousands of GPUs over two weeks, KataGo surpasses ELF’s final model after only 19 days on fewer than 30 GPUs. Much of the speedup involves non-domain-specific improvements that might directly transfer to other problems. Further gains from domain-specific techniques reveal the remaining efficiency gap between the best methods and purely general methods such as AlphaZero. Our work is a step towards making learning in state spaces as large as Go possible without large-scale computational resources. |
| Tasks | Game of Go |
| Published | 2019-02-27 |
| URL | https://arxiv.org/abs/1902.10565v4 |
| https://arxiv.org/pdf/1902.10565v4.pdf | |
| PWC | https://paperswithcode.com/paper/accelerating-self-play-learning-in-go |
| Repo | https://github.com/lightvector/KataGo |
| Framework | tf |
Building a Computer Mahjong Player via Deep Convolutional Neural Networks
| Title | Building a Computer Mahjong Player via Deep Convolutional Neural Networks |
| Authors | Shiqi Gao, Fuminori Okuya, Yoshihiro Kawahara, Yoshimasa Tsuruoka |
| Abstract | The evaluation function for imperfect information games is always hard to define but owns a significant impact on the playing strength of a program. Deep learning has made great achievements these years, and already exceeded the top human players’ level even in the game of Go. In this paper, we introduce a new data model to represent the available imperfect information on the game table, and construct a well-designed convolutional neural network for game record training. We choose the accuracy of tile discarding which is also called as the agreement rate as the benchmark for this study. Our accuracy on test data reaches 70.44%, while the state-of-art baseline is 62.1% reported by Mizukami and Tsuruoka (2015), and is significantly higher than previous trials using deep learning, which shows the promising potential of our new model. For the AI program building, besides the tile discarding strategy, we adopt similar predicting strategies for other actions such as stealing (pon, chi, and kan) and riichi. With the simple combination of these several predicting networks and without any knowledge about the concrete rules of the game, a strength evaluation is made for the resulting program on the largest Japanese Mahjong site `Tenhou’. The program has achieved a rating of around 1850, which is significantly higher than that of an average human player and of programs among past studies. | |
| Tasks | Game of Go |
| Published | 2019-06-05 |
| URL | https://arxiv.org/abs/1906.02146v2 |
| https://arxiv.org/pdf/1906.02146v2.pdf | |
| PWC | https://paperswithcode.com/paper/building-a-computer-mahjong-player-via-deep |
| Repo | https://github.com/lucylow/Deep-Learning-Mahjong--- |
| Framework | none |
Functional Isolation Forest
| Title | Functional Isolation Forest |
| Authors | Guillaume Staerman, Pavlo Mozharovskyi, Stephan Clémençon, Florence d’Alché-Buc |
| Abstract | For the purpose of monitoring the behavior of complex infrastructures (e.g. aircrafts, transport or energy networks), high-rate sensors are deployed to capture multivariate data, generally unlabeled, in quasi continuous-time to detect quickly the occurrence of anomalies that may jeopardize the smooth operation of the system of interest. The statistical analysis of such massive data of functional nature raises many challenging methodological questions. The primary goal of this paper is to extend the popular Isolation Forest (IF) approach to Anomaly Detection, originally dedicated to finite dimensional observations, to functional data. The major difficulty lies in the wide variety of topological structures that may equip a space of functions and the great variety of patterns that may characterize abnormal curves. We address the issue of (randomly) splitting the functional space in a flexible manner in order to isolate progressively any trajectory from the others, a key ingredient to the efficiency of the algorithm. Beyond a detailed description of the algorithm, computational complexity and stability issues are investigated at length. From the scoring function measuring the degree of abnormality of an observation provided by the proposed variant of the IF algorithm, a Functional Statistical Depth function is defined and discussed as well as a multivariate functional extension. Numerical experiments provide strong empirical evidence of the accuracy of the extension proposed. |
| Tasks | Anomaly Detection |
| Published | 2019-04-09 |
| URL | https://arxiv.org/abs/1904.04573v3 |
| https://arxiv.org/pdf/1904.04573v3.pdf | |
| PWC | https://paperswithcode.com/paper/functional-isolation-forest |
| Repo | https://github.com/Gstaerman/FIF |
| Framework | none |
Multiple Landmark Detection using Multi-Agent Reinforcement Learning
| Title | Multiple Landmark Detection using Multi-Agent Reinforcement Learning |
| Authors | Athanasios Vlontzos, Amir Alansary, Konstantinos Kamnitsas, Daniel Rueckert, Bernhard Kainz |
| Abstract | The detection of anatomical landmarks is a vital step for medical image analysis and applications for diagnosis, interpretation and guidance. Manual annotation of landmarks is a tedious process that requires domain-specific expertise and introduces inter-observer variability. This paper proposes a new detection approach for multiple landmarks based on multi-agent reinforcement learning. Our hypothesis is that the position of all anatomical landmarks is interdependent and non-random within the human anatomy, thus finding one landmark can help to deduce the location of others. Using a Deep Q-Network (DQN) architecture we construct an environment and agent with implicit inter-communication such that we can accommodate K agents acting and learning simultaneously, while they attempt to detect K different landmarks. During training the agents collaborate by sharing their accumulated knowledge for a collective gain. We compare our approach with state-of-the-art architectures and achieve significantly better accuracy by reducing the detection error by 50%, while requiring fewer computational resources and time to train compared to the naive approach of training K agents separately. |
| Tasks | Multi-agent Reinforcement Learning |
| Published | 2019-06-30 |
| URL | https://arxiv.org/abs/1907.00318v2 |
| https://arxiv.org/pdf/1907.00318v2.pdf | |
| PWC | https://paperswithcode.com/paper/multiple-landmark-detection-using-multi-agent |
| Repo | https://github.com/thanosvlo/MARL-for-Anatomical-Landmark-Detection |
| Framework | tf |
Self-Supervised Unconstrained Illumination Invariant Representation
| Title | Self-Supervised Unconstrained Illumination Invariant Representation |
| Authors | Damian Kaliroff, Guy Gilboa |
| Abstract | We propose a new and completely data-driven approach for generating an unconstrained illumination invariant representation of images. Our method trains a neural network with a specialized triplet loss designed to emphasize actual scene changes while downplaying changes in illumination. For this purpose we use the BigTime image dataset, which contains static scenes acquired at different times. We analyze the attributes of our representation, and show that it improves patch matching and rigid registration over state-of-the-art illumination invariant representations. We point out that the utility of our method is not restricted to handling illumination invariance, and that it may be applied for generating representations which are invariant to general types of nuisance, undesired, image variants. |
| Tasks | |
| Published | 2019-11-28 |
| URL | https://arxiv.org/abs/1911.12641v1 |
| https://arxiv.org/pdf/1911.12641v1.pdf | |
| PWC | https://paperswithcode.com/paper/self-supervised-unconstrained-illumination |
| Repo | https://github.com/dkaliroff/invrepnet |
| Framework | pytorch |
A Regularized Opponent Model with Maximum Entropy Objective
| Title | A Regularized Opponent Model with Maximum Entropy Objective |
| Authors | Zheng Tian, Ying Wen, Zhichen Gong, Faiz Punakkath, Shihao Zou, Jun Wang |
| Abstract | In a single-agent setting, reinforcement learning (RL) tasks can be cast into an inference problem by introducing a binary random variable o, which stands for the “optimality”. In this paper, we redefine the binary random variable o in multi-agent setting and formalize multi-agent reinforcement learning (MARL) as probabilistic inference. We derive a variational lower bound of the likelihood of achieving the optimality and name it as Regularized Opponent Model with Maximum Entropy Objective (ROMMEO). From ROMMEO, we present a novel perspective on opponent modeling and show how it can improve the performance of training agents theoretically and empirically in cooperative games. To optimize ROMMEO, we first introduce a tabular Q-iteration method ROMMEO-Q with proof of convergence. We extend the exact algorithm to complex environments by proposing an approximate version, ROMMEO-AC. We evaluate these two algorithms on the challenging iterated matrix game and differential game respectively and show that they can outperform strong MARL baselines. |
| Tasks | Multi-agent Reinforcement Learning |
| Published | 2019-05-17 |
| URL | https://arxiv.org/abs/1905.08087v2 |
| https://arxiv.org/pdf/1905.08087v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-regularized-opponent-model-with-maximum |
| Repo | https://github.com/rommeoijcai2019/rommeo |
| Framework | tf |
Safety Verification and Robustness Analysis of Neural Networks via Quadratic Constraints and Semidefinite Programming
| Title | Safety Verification and Robustness Analysis of Neural Networks via Quadratic Constraints and Semidefinite Programming |
| Authors | Mahyar Fazlyab, Manfred Morari, George J. Pappas |
| Abstract | Analyzing the robustness of neural networks against norm-bounded uncertainties and adversarial attacks has found many applications ranging from safety verification to robust training. In this paper, we propose a semidefinite programming (SDP) framework for safety verification and robustness analysis of neural networks with general activation functions. Our main idea is to abstract various properties of activation functions (e.g., monotonicity, bounded slope, bounded values, and repetition across layers) with the formalism of quadratic constraints. We then analyze the safety properties of the abstracted network via the S-procedure and semidefinite programming. Compared to other semidefinite relaxations proposed in the literature, our method is less conservative, especially for deep networks, with an order of magnitude reduction in computational complexity. Furthermore, our approach is applicable to any activation functions. |
| Tasks | |
| Published | 2019-03-04 |
| URL | http://arxiv.org/abs/1903.01287v1 |
| http://arxiv.org/pdf/1903.01287v1.pdf | |
| PWC | https://paperswithcode.com/paper/safety-verification-and-robustness-analysis |
| Repo | https://github.com/arobey1/RobustNN |
| Framework | none |
Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Driving
| Title | Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Driving |
| Authors | Yurong You, Yan Wang, Wei-Lun Chao, Divyansh Garg, Geoff Pleiss, Bharath Hariharan, Mark Campbell, Kilian Q. Weinberger |
| Abstract | Detecting objects such as cars and pedestrians in 3D plays an indispensable role in autonomous driving. Existing approaches largely rely on expensive LiDAR sensors for accurate depth information. While recently pseudo-LiDAR has been introduced as a promising alternative, at a much lower cost based solely on stereo images, there is still a notable performance gap. In this paper we provide substantial advances to the pseudo-LiDAR framework through improvements in stereo depth estimation. Concretely, we adapt the stereo network architecture and loss function to be more aligned with accurate depth estimation of faraway objects — currently the primary weakness of pseudo-LiDAR. Further, we explore the idea to leverage cheaper but extremely sparse LiDAR sensors, which alone provide insufficient information for 3D detection, to de-bias our depth estimation. We propose a depth-propagation algorithm, guided by the initial depth estimates, to diffuse these few exact measurements across the entire depth map. We show on the KITTI object detection benchmark that our combined approach yields substantial improvements in depth estimation and stereo-based 3D object detection — outperforming the previous state-of-the-art detection accuracy for faraway objects by 40%. Our code is available at https://github.com/mileyan/Pseudo_Lidar_V2. |
| Tasks | 3D Object Detection, Autonomous Driving, Depth Estimation, Object Detection, Stereo Depth Estimation |
| Published | 2019-06-14 |
| URL | https://arxiv.org/abs/1906.06310v3 |
| https://arxiv.org/pdf/1906.06310v3.pdf | |
| PWC | https://paperswithcode.com/paper/pseudo-lidar-accurate-depth-for-3d-object |
| Repo | https://github.com/mileyan/Pseudo_Lidar_V2 |
| Framework | pytorch |
Hybrid Machine Learning Models of Classifying Residential Requests for Smart Dispatching
| Title | Hybrid Machine Learning Models of Classifying Residential Requests for Smart Dispatching |
| Authors | T. Chen, J. Sun, H. Lin, Y. Liu |
| Abstract | This paper presents a hybrid machine learning method of classifying residential requests in natural language to responsible departments that provide timely responses back to residents under the vision of digital government services in smart cities. Residential requests in natural language descriptions cover almost every aspect of a city’s daily operation. Hence the responsible departments are fine-grained to even the level of local communities. There are no specific general categories or labels for each request sample. This causes two issues for supervised classification solutions, namely (1) the request sample data is unbalanced and (2) lack of specific labels for training. To solve these issues, we investigate a hybrid machine learning method that generates meta-class labels by means of unsupervised clustering algorithms; applies two-word embedding methods with three classifiers (including two hierarchical classifiers and one residual convolutional neural network); and selects the best performing classifier as the classification result. We demonstrate our approach performing better classification tasks compared to two benchmarking machine learning models, Naive Bayes classifier and a Multiple Layer Perceptron (MLP). In addition, the hierarchical classification method provides insights into the source of classification errors. |
| Tasks | |
| Published | 2019-12-22 |
| URL | https://arxiv.org/abs/1912.10546v1 |
| https://arxiv.org/pdf/1912.10546v1.pdf | |
| PWC | https://paperswithcode.com/paper/hybrid-machine-learning-models-of-classifying |
| Repo | https://github.com/OneClickDeepLearning/classificationOfResidentialRequests |
| Framework | tf |
Searching for A Robust Neural Architecture in Four GPU Hours
| Title | Searching for A Robust Neural Architecture in Four GPU Hours |
| Authors | Xuanyi Dong, Yi Yang |
| Abstract | Conventional neural architecture search (NAS) approaches are based on reinforcement learning or evolutionary strategy, which take more than 3000 GPU hours to find a good model on CIFAR-10. We propose an efficient NAS approach learning to search by gradient descent. Our approach represents the search space as a directed acyclic graph (DAG). This DAG contains billions of sub-graphs, each of which indicates a kind of neural architecture. To avoid traversing all the possibilities of the sub-graphs, we develop a differentiable sampler over the DAG. This sampler is learnable and optimized by the validation loss after training the sampled architecture. In this way, our approach can be trained in an end-to-end fashion by gradient descent, named Gradient-based search using Differentiable Architecture Sampler (GDAS). In experiments, we can finish one searching procedure in four GPU hours on CIFAR-10, and the discovered model obtains a test error of 2.82% with only 2.5M parameters, which is on par with the state-of-the-art. Code is publicly available on GitHub: https://github.com/D-X-Y/NAS-Projects. |
| Tasks | Neural Architecture Search |
| Published | 2019-10-10 |
| URL | https://arxiv.org/abs/1910.04465v2 |
| https://arxiv.org/pdf/1910.04465v2.pdf | |
| PWC | https://paperswithcode.com/paper/searching-for-a-robust-neural-architecture-in-1 |
| Repo | https://github.com/D-X-Y/GDAS |
| Framework | pytorch |
InfoGAN-CR: Disentangling Generative Adversarial Networks with Contrastive Regularizers
| Title | InfoGAN-CR: Disentangling Generative Adversarial Networks with Contrastive Regularizers |
| Authors | Zinan Lin, Kiran Koshy Thekumparampil, Giulia Fanti, Sewoong Oh |
| Abstract | Training disentangled representations with generative adversarial networks (GANs) remains challenging, with leading implementations failing to achieve comparable performance to Variational Autoencoder (VAE)-based methods. After $\beta$-VAE and FactorVAE discovered that regularizing the total correlation of the latent vectors promotes disentanglement, numerous VAE-based methods emerged. Such a discovery has yet to be made for GANs, and reported disentanglement scores of GAN-based methods are significantly inferior to VAE-based methods on benchmark datasets. To this end, we propose a novel regularizer that achieves higher disentanglement scores than state-of-the-art VAE- and GAN-based approaches. The proposed contrastive regularizer is inspired by a natural notion of disentanglement: latent traversal. Latent traversal refers to generating images by varying one latent code while fixing the rest. We turn this intuition into a regularizer by adding a discriminator that detects how the latent codes are coupled together, in paired examples. Numerical experiments show that this approach improves upon competing state-of-the-art approaches on benchmark datasets. |
| Tasks | |
| Published | 2019-06-14 |
| URL | https://arxiv.org/abs/1906.06034v1 |
| https://arxiv.org/pdf/1906.06034v1.pdf | |
| PWC | https://paperswithcode.com/paper/infogan-cr-disentangling-generative |
| Repo | https://github.com/fjxmlzn/InfoGAN-CR |
| Framework | tf |
Learning with Average Precision: Training Image Retrieval with a Listwise Loss
| Title | Learning with Average Precision: Training Image Retrieval with a Listwise Loss |
| Authors | Jerome Revaud, Jon Almazan, Rafael Sampaio de Rezende, Cesar Roberto de Souza |
| Abstract | Image retrieval can be formulated as a ranking problem where the goal is to order database images by decreasing similarity to the query. Recent deep models for image retrieval have outperformed traditional methods by leveraging ranking-tailored loss functions, but important theoretical and practical problems remain. First, rather than directly optimizing the global ranking, they minimize an upper-bound on the essential loss, which does not necessarily result in an optimal mean average precision (mAP). Second, these methods require significant engineering efforts to work well, e.g. special pre-training and hard-negative mining. In this paper we propose instead to directly optimize the global mAP by leveraging recent advances in listwise loss formulations. Using a histogram binning approximation, the AP can be differentiated and thus employed to end-to-end learning. Compared to existing losses, the proposed method considers thousands of images simultaneously at each iteration and eliminates the need for ad hoc tricks. It also establishes a new state of the art on many standard retrieval benchmarks. Models and evaluation scripts have been made available at https://europe.naverlabs.com/Deep-Image-Retrieval/ |
| Tasks | Image Retrieval |
| Published | 2019-06-18 |
| URL | https://arxiv.org/abs/1906.07589v1 |
| https://arxiv.org/pdf/1906.07589v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-with-average-precision-training |
| Repo | https://github.com/almazan/deep-image-retrieval |
| Framework | pytorch |
Learning to Paint With Model-based Deep Reinforcement Learning
| Title | Learning to Paint With Model-based Deep Reinforcement Learning |
| Authors | Zhewei Huang, Wen Heng, Shuchang Zhou |
| Abstract | We show how to teach machines to paint like human painters, who can use a small number of strokes to create fantastic paintings. By employing a neural renderer in model-based Deep Reinforcement Learning (DRL), our agents learn to determine the position and color of each stroke and make long-term plans to decompose texture-rich images into strokes. Experiments demonstrate that excellent visual effects can be achieved using hundreds of strokes. The training process does not require the experience of human painters or stroke tracking data. The code is available at https://github.com/hzwer/ICCV2019-LearningToPaint. |
| Tasks | Learning to Paint |
| Published | 2019-03-11 |
| URL | https://arxiv.org/abs/1903.04411v3 |
| https://arxiv.org/pdf/1903.04411v3.pdf | |
| PWC | https://paperswithcode.com/paper/stroke-based-artistic-rendering-agent-with |
| Repo | https://github.com/hzwer/ICCV2019-LearningToPaint |
| Framework | pytorch |
