Paper Group ANR 784
Learning to Request Guidance in Emergent Communication. Machine Learning and Big Scientific Data. Fluxonic Processing of Photonic Synapse Events. SPMF: A Social Trust and Preference Segmentation-based Matrix Factorization Recommendation Algorithm. Rotation-invariant shipwreck recognition with forward-looking sonar. Inferring Javascript types using …
Learning to Request Guidance in Emergent Communication
| Title | Learning to Request Guidance in Emergent Communication |
| Authors | Benjamin Kolb, Leon Lang, Henning Bartsch, Arwin Gansekoele, Raymond Koopmanschap, Leonardo Romor, David Speck, Mathijs Mul, Elia Bruni |
| Abstract | Previous research into agent communication has shown that a pre-trained guide can speed up the learning process of an imitation learning agent. The guide achieves this by providing the agent with discrete messages in an emerged language about how to solve the task. We extend this one-directional communication by a one-bit communication channel from the learner back to the guide: It is able to ask the guide for help, and we limit the guidance by penalizing the learner for these requests. During training, the agent learns to control this gate based on its current observation. We find that the amount of requested guidance decreases over time and guidance is requested in situations of high uncertainty. We investigate the agent’s performance in cases of open and closed gates and discuss potential motives for the observed gating behavior. |
| Tasks | Imitation Learning |
| Published | 2019-12-11 |
| URL | https://arxiv.org/abs/1912.05525v1 |
| https://arxiv.org/pdf/1912.05525v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-request-guidance-in-emergent-1 |
| Repo | |
| Framework | |
Machine Learning and Big Scientific Data
| Title | Machine Learning and Big Scientific Data |
| Authors | Tony Hey, Keith Butler, Sam Jackson, Jeyarajan Thiyagalingam |
| Abstract | This paper reviews some of the challenges posed by the huge growth of experimental data generated by the new generation of large-scale experiments at UK national facilities at the Rutherford Appleton Laboratory site at Harwell near Oxford. Such “Big Scientific Data” comes from the Diamond Light Source and Electron Microscopy Facilities, the ISIS Neutron and Muon Facility, and the UK’s Central Laser Facility. Increasingly, scientists are now needing to use advanced machine learning and other AI technologies both to automate parts of the data pipeline and also to help find new scientific discoveries in the analysis of their data. For commercially important applications, such as object recognition, natural language processing and automatic translation, deep learning has made dramatic breakthroughs. Google’s DeepMind has now also used deep learning technology to develop their AlphaFold tool to make predictions for protein folding. Remarkably, they have been able to achieve some spectacular results for this specific scientific problem. Can deep learning be similarly transformative for other scientific problems? After a brief review of some initial applications of machine learning at the Rutherford Appleton Laboratory, we focus on challenges and opportunities for AI in advancing materials science. Finally, we discuss the importance of developing some realistic machine learning benchmarks using Big Scientific Data coming from a number of different scientific domains. We conclude with some initial examples of our “SciML” benchmark suite and of the research challenges these benchmarks will enable. |
| Tasks | Object Recognition |
| Published | 2019-10-12 |
| URL | https://arxiv.org/abs/1910.07631v1 |
| https://arxiv.org/pdf/1910.07631v1.pdf | |
| PWC | https://paperswithcode.com/paper/machine-learning-and-big-scientific-data |
| Repo | |
| Framework | |
Fluxonic Processing of Photonic Synapse Events
| Title | Fluxonic Processing of Photonic Synapse Events |
| Authors | Jeffrey M. Shainline |
| Abstract | Much of the information processing performed by a neuron occurs in the dendritic tree. For neural systems using light for communication, it is advantageous to convert signals to the electronic domain at synaptic terminals so dendritic computation can be performed with electrical circuits. Here we present circuits based on Josephson junctions and mutual inductors that act as dendrites, processing signals from synapses receiving single-photon communication events with superconducting detectors. We show simulations of circuits performing basic temporal filtering, logical operations, and nonlinear transfer functions. We further show how the synaptic signal from a single-photon can fan out locally in the electronic domain to enable the dendrites of the receiving neuron to process a photonic synapse event or pulse train in multiple different ways simultaneously. Such a technique makes efficient use of photons, energy, space, and information. |
| Tasks | |
| Published | 2019-04-04 |
| URL | http://arxiv.org/abs/1904.02807v1 |
| http://arxiv.org/pdf/1904.02807v1.pdf | |
| PWC | https://paperswithcode.com/paper/fluxonic-processing-of-photonic-synapse |
| Repo | |
| Framework | |
SPMF: A Social Trust and Preference Segmentation-based Matrix Factorization Recommendation Algorithm
| Title | SPMF: A Social Trust and Preference Segmentation-based Matrix Factorization Recommendation Algorithm |
| Authors | Wei Peng, Baogui Xin |
| Abstract | The traditional social recommendation algorithm ignores the following fact: the preferences of users with trust relationships are not necessarily similar, and the consideration of user preference similarity should be limited to specific areas. A social trust and preference segmentation-based matrix factorization (SPMF) recommendation system is proposed to solve the above-mentioned problems. Experimental results based on the Ciao and Epinions datasets show that the accuracy of the SPMF algorithm is significantly higher than that of some state-of-the-art recommendation algorithms. The proposed SPMF algorithm is a more accurate and effective recommendation algorithm based on distinguishing the difference of trust relations and preference domain, which can support commercial activities such as product marketing. |
| Tasks | |
| Published | 2019-03-11 |
| URL | http://arxiv.org/abs/1903.04489v1 |
| http://arxiv.org/pdf/1903.04489v1.pdf | |
| PWC | https://paperswithcode.com/paper/spmf-a-social-trust-and-preference |
| Repo | |
| Framework | |
Rotation-invariant shipwreck recognition with forward-looking sonar
| Title | Rotation-invariant shipwreck recognition with forward-looking sonar |
| Authors | Gustavo Neves, Rômulo Cerqueira, Jan Albiez, Luciano Oliveira |
| Abstract | Under the sea, visible spectrum cameras have limited sensing capacity, being able to detect objects only in clear water, but in a constrained range. Considering any sea water condition, sonars are more suitable to support autonomous underwater vehicles’ navigation, even in turbid condition. Despite that sonar suitability, this type of sensor does not provide high-density information, such as optical sensors, making the process of object recognition to be more complex. To deal with that problem, we propose a novel trainable method to detect and recognize (identify) specific target objects under the sea with a forward-looking sonar. Our method has a preprocessing step in charge of strongly reducing the sensor noise and seabed background. To represent the object, our proposed method uses histogram of orientation gradient (HOG) as feature extractor. HOG ultimately feed a multi-scale oriented detector combined with a support vector machine to recognize specific trained objects in a rotation-invariant way. Performance assessment demonstrated promising results, favoring the method to be applied in underwater remote sensing. |
| Tasks | Object Recognition |
| Published | 2019-10-11 |
| URL | https://arxiv.org/abs/1910.05374v1 |
| https://arxiv.org/pdf/1910.05374v1.pdf | |
| PWC | https://paperswithcode.com/paper/rotation-invariant-shipwreck-recognition-with |
| Repo | |
| Framework | |
Inferring Javascript types using Graph Neural Networks
| Title | Inferring Javascript types using Graph Neural Networks |
| Authors | Jessica Schrouff, Kai Wohlfahrt, Bruno Marnette, Liam Atkinson |
| Abstract | The recent use of `Big Code’ with state-of-the-art deep learning methods offers promising avenues to ease program source code writing and correction. As a first step towards automatic code repair, we implemented a graph neural network model that predicts token types for Javascript programs. The predictions achieve an accuracy above $90%$, which improves on previous similar work. | |
| Tasks | |
| Published | 2019-05-16 |
| URL | https://arxiv.org/abs/1905.06707v1 |
| https://arxiv.org/pdf/1905.06707v1.pdf | |
| PWC | https://paperswithcode.com/paper/inferring-javascript-types-using-graph-neural |
| Repo | |
| Framework | |
Beyond Imitation: Generative and Variational Choreography via Machine Learning
| Title | Beyond Imitation: Generative and Variational Choreography via Machine Learning |
| Authors | Mariel Pettee, Chase Shimmin, Douglas Duhaime, Ilya Vidrin |
| Abstract | Our team of dance artists, physicists, and machine learning researchers has collectively developed several original, configurable machine-learning tools to generate novel sequences of choreography as well as tunable variations on input choreographic sequences. We use recurrent neural network and autoencoder architectures from a training dataset of movements captured as 53 three-dimensional points at each timestep. Sample animations of generated sequences and an interactive version of our model can be found at http: //www.beyondimitation.com. |
| Tasks | |
| Published | 2019-07-11 |
| URL | https://arxiv.org/abs/1907.05297v1 |
| https://arxiv.org/pdf/1907.05297v1.pdf | |
| PWC | https://paperswithcode.com/paper/beyond-imitation-generative-and-variational |
| Repo | |
| Framework | |
Next integrated result modelling for stopping the text field recognition process in a video using a result model with per-character alternatives
| Title | Next integrated result modelling for stopping the text field recognition process in a video using a result model with per-character alternatives |
| Authors | Konstantin Bulatov, Boris Savelyev, Vladimir V. Arlazarov |
| Abstract | In the field of document analysis and recognition using mobile devices for capturing, and the field of object recognition in a video stream, an important problem is determining the time when the capturing process should be stopped. Efficient stopping influences not only the total time spent for performing recognition and data entry, but the expected accuracy of the result as well. This paper is directed on extending the stopping method based on next integrated recognition result modelling, in order for it to be used within a string result recognition model with per-character alternatives. The stopping method and notes on its extension are described, and experimental evaluation is performed on an open dataset MIDV-500. The method was compares with previously published methods based on input observations clustering. The obtained results indicate that the stopping method based on the next integrated result modelling allows to achieve higher accuracy, even when compared with the best achievable configuration of the competing methods. |
| Tasks | Object Recognition |
| Published | 2019-10-09 |
| URL | https://arxiv.org/abs/1910.04107v1 |
| https://arxiv.org/pdf/1910.04107v1.pdf | |
| PWC | https://paperswithcode.com/paper/next-integrated-result-modelling-for-stopping |
| Repo | |
| Framework | |
Deep Transfer Learning for Source Code Modeling
| Title | Deep Transfer Learning for Source Code Modeling |
| Authors | Yasir Hussain, Zhiqiu Huang, Yu Zhou, Senzhang Wang |
| Abstract | In recent years, deep learning models have shown great potential in source code modeling and analysis. Generally, deep learning-based approaches are problem-specific and data-hungry. A challenging issue of these approaches is that they require training from starch for a different related problem. In this work, we propose a transfer learning-based approach that significantly improves the performance of deep learning-based source code models. In contrast to traditional learning paradigms, transfer learning can transfer the knowledge learned in solving one problem into another related problem. First, we present two recurrent neural network-based models RNN and GRU for the purpose of transfer learning in the domain of source code modeling. Next, via transfer learning, these pre-trained (RNN and GRU) models are used as feature extractors. Then, these extracted features are combined into attention learner for different downstream tasks. The attention learner leverages from the learned knowledge of pre-trained models and fine-tunes them for a specific downstream task. We evaluate the performance of the proposed approach with extensive experiments with the source code suggestion task. The results indicate that the proposed approach outperforms the state-of-the-art models in terms of accuracy, precision, recall, and F-measure without training the models from scratch. |
| Tasks | Transfer Learning |
| Published | 2019-10-12 |
| URL | https://arxiv.org/abs/1910.05493v1 |
| https://arxiv.org/pdf/1910.05493v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-transfer-learning-for-source-code |
| Repo | |
| Framework | |
From Here to There: Video Inbetweening Using Direct 3D Convolutions
| Title | From Here to There: Video Inbetweening Using Direct 3D Convolutions |
| Authors | Yunpeng Li, Dominik Roblek, Marco Tagliasacchi |
| Abstract | We consider the problem of generating plausible and diverse video sequences, when we are only given a start and an end frame. This task is also known as inbetweening, and it belongs to the broader area of stochastic video generation, which is generally approached by means of recurrent neural networks (RNN). In this paper, we propose instead a fully convolutional model to generate video sequences directly in the pixel domain. We first obtain a latent video representation using a stochastic fusion mechanism that learns how to incorporate information from the start and end frames. Our model learns to produce such latent representation by progressively increasing the temporal resolution, and then decode in the spatiotemporal domain using 3D convolutions. The model is trained end-to-end by minimizing an adversarial loss. Experiments on several widely-used benchmark datasets show that it is able to generate meaningful and diverse in-between video sequences, according to both quantitative and qualitative evaluations. |
| Tasks | Video Generation |
| Published | 2019-05-24 |
| URL | https://arxiv.org/abs/1905.10240v3 |
| https://arxiv.org/pdf/1905.10240v3.pdf | |
| PWC | https://paperswithcode.com/paper/from-here-to-there-video-inbetweening-using |
| Repo | |
| Framework | |
Attention Network Robustification for Person ReID
| Title | Attention Network Robustification for Person ReID |
| Authors | Hussam Lawen, Avi Ben-Cohen, Matan Protter, Itamar Friedman, Lihi Zelnik-Manor |
| Abstract | The task of person re-identification (ReID) has attracted growing attention in recent years with improving performance but lack of focus on real-world applications. Most state of the art methods use large pre-trained models, e.g., ResNet50 (~25M parameters), as their backbone, which makes it tedious to explore different architecture modifications. In this study, we focus on small-sized randomly initialized models which enable us to easily introduce network and training modifications suitable for person ReID public datasets and real-world setups. We show the robustness of our network and training improvements by outperforming state of the art results in terms of rank-1 accuracy and mAP on Market1501 (96.2, 89.7) and DukeMTMC (89.8, 80.3) with only 6.4M parameters and without using re-ranking. Finally, we show the applicability of the proposed ReID network for multi-object tracking. |
| Tasks | Multi-Object Tracking, Person Re-Identification |
| Published | 2019-10-15 |
| URL | https://arxiv.org/abs/1910.07038v2 |
| https://arxiv.org/pdf/1910.07038v2.pdf | |
| PWC | https://paperswithcode.com/paper/attention-network-robustification-for-person |
| Repo | |
| Framework | |
Universal Person Re-Identification
| Title | Universal Person Re-Identification |
| Authors | Xu Lan, Xiatian Zhu, Shaogang Gong |
| Abstract | Most state-of-the-art person re-identification (re-id) methods depend on supervised model learning with a large set of cross-view identity labelled training data. Even worse, such trained models are limited to only the same-domain deployment with significantly degraded cross-domain generalization capability, i.e. “domain specific”. To solve this limitation, there are a number of recent unsupervised domain adaptation and unsupervised learning methods that leverage unlabelled target domain training data. However, these methods need to train a separate model for each target domain as supervised learning methods. This conventional “{\em train once, run once}” pattern is unscalable to a large number of target domains typically encountered in real-world deployments. We address this problem by presenting a “train once, run everywhere” pattern industry-scale systems are desperate for. We formulate a “universal model learning’ approach enabling domain-generic person re-id using only limited training data of a “{\em single}” seed domain. Specifically, we train a universal re-id deep model to discriminate between a set of transformed person identity classes. Each of such classes is formed by applying a variety of random appearance transformations to the images of that class, where the transformations simulate the camera viewing conditions of any domains for making the model training domain generic. Extensive evaluations show the superiority of our method for universal person re-id over a wide variety of state-of-the-art unsupervised domain adaptation and unsupervised learning re-id methods on five standard benchmarks: Market-1501, DukeMTMC, CUHK03, MSMT17, and VIPeR. |
| Tasks | Domain Adaptation, Domain Generalization, Person Re-Identification, Unsupervised Domain Adaptation |
| Published | 2019-07-22 |
| URL | https://arxiv.org/abs/1907.09511v1 |
| https://arxiv.org/pdf/1907.09511v1.pdf | |
| PWC | https://paperswithcode.com/paper/universal-person-re-identification |
| Repo | |
| Framework | |
Generating Compact Geometric Track-Maps for Train Positioning Applications
| Title | Generating Compact Geometric Track-Maps for Train Positioning Applications |
| Authors | Hanno Winter, Stefan Luthardt, Volker Willert, Jürgen Adamy |
| Abstract | In this paper, we present a method to generate compact geometric track-maps for train-borne localization applications. Therefore, we first give a brief overview on the purpose of track maps in train-positioning applications. It becomes apparent that there are hardly any adequate methods to generate suitable geometric track-maps. This is why we present a novel map generation procedure. It uses an optimization formulation to find the continuous sequence of track geometries that fits the available measurement data best. The optimization is initialized with the results from a localization filter developed in our previous work. The localization filter also provides the required information for shape identification and measurement association. The presented approach will be evaluated on simulated data as well as on real measurements. |
| Tasks | |
| Published | 2019-03-12 |
| URL | https://arxiv.org/abs/1903.05014v2 |
| https://arxiv.org/pdf/1903.05014v2.pdf | |
| PWC | https://paperswithcode.com/paper/generating-compact-geometric-track-maps-for |
| Repo | |
| Framework | |
Fast Online “Next Best Offers” using Deep Learning
| Title | Fast Online “Next Best Offers” using Deep Learning |
| Authors | Rekha Singhal, Gautam Shroff, Mukund Kumar, Sharod Roy, Sanket Kadarkar, Rupinder virk, Siddharth Verma, Vartika Tiwari |
| Abstract | In this paper, we present iPrescribe, a scalable low-latency architecture for recommending ‘next-best-offers’ in an online setting. The paper presents the design of iPrescribe and compares its performance for implementations using different real-time streaming technology stacks. iPrescribe uses an ensemble of deep learning and machine learning algorithms for prediction. We describe the scalable real-time streaming technology stack and optimized machine-learning implementations to achieve a 90th percentile recommendation latency of 38 milliseconds. Optimizations include a novel mechanism to deploy recurrent Long Short Term Memory (LSTM) deep learning networks efficiently. |
| Tasks | |
| Published | 2019-05-31 |
| URL | https://arxiv.org/abs/1905.13368v1 |
| https://arxiv.org/pdf/1905.13368v1.pdf | |
| PWC | https://paperswithcode.com/paper/fast-online-next-best-offers-using-deep |
| Repo | |
| Framework | |
AM-LFS: AutoML for Loss Function Search
| Title | AM-LFS: AutoML for Loss Function Search |
| Authors | Chuming Li, Yuan Xin, Chen Lin, Minghao Guo, Wei Wu, Wanli Ouyang, Junjie Yan |
| Abstract | Designing an effective loss function plays an important role in visual analysis. Most existing loss function designs rely on hand-crafted heuristics that require domain experts to explore the large design space, which is usually sub-optimal and time-consuming. In this paper, we propose AutoML for Loss Function Search (AM-LFS) which leverages REINFORCE to search loss functions during the training process. The key contribution of this work is the design of search space which can guarantee the generalization and transferability on different vision tasks by including a bunch of existing prevailing loss functions in a unified formulation. We also propose an efficient optimization framework which can dynamically optimize the parameters of loss function’s distribution during training. Extensive experimental results on four benchmark datasets show that, without any tricks, our method outperforms existing hand-crafted loss functions in various computer vision tasks. |
| Tasks | AutoML |
| Published | 2019-05-17 |
| URL | https://arxiv.org/abs/1905.07375v2 |
| https://arxiv.org/pdf/1905.07375v2.pdf | |
| PWC | https://paperswithcode.com/paper/am-lfs-automl-for-loss-function-search |
| Repo | |
| Framework | |
