Paper Group ANR 1260
RoboNet: Large-Scale Multi-Robot Learning. Robust Tensor Recovery with Fiber Outliers for Traffic Events. Probabilistic Successor Representations with Kalman Temporal Differences. A Heuristic Algorithm for the Fabric Spreading and Cutting Problem in Apparel Factories. Reluctant generalized additive modeling. Particle swarm optimization model to pre …
RoboNet: Large-Scale Multi-Robot Learning
| Title | RoboNet: Large-Scale Multi-Robot Learning |
| Authors | Sudeep Dasari, Frederik Ebert, Stephen Tian, Suraj Nair, Bernadette Bucher, Karl Schmeckpeper, Siddharth Singh, Sergey Levine, Chelsea Finn |
| Abstract | Robot learning has emerged as a promising tool for taming the complexity and diversity of the real world. Methods based on high-capacity models, such as deep networks, hold the promise of providing effective generalization to a wide range of open-world environments. However, these same methods typically require large amounts of diverse training data to generalize effectively. In contrast, most robotic learning experiments are small-scale, single-domain, and single-robot. This leads to a frequent tension in robotic learning: how can we learn generalizable robotic controllers without having to collect impractically large amounts of data for each separate experiment? In this paper, we propose RoboNet, an open database for sharing robotic experience, which provides an initial pool of 15 million video frames, from 7 different robot platforms, and study how it can be used to learn generalizable models for vision-based robotic manipulation. We combine the dataset with two different learning algorithms: visual foresight, which uses forward video prediction models, and supervised inverse models. Our experiments test the learned algorithms’ ability to work across new objects, new tasks, new scenes, new camera viewpoints, new grippers, or even entirely new robots. In our final experiment, we find that by pre-training on RoboNet and fine-tuning on data from a held-out Franka or Kuka robot, we can exceed the performance of a robot-specific training approach that uses 4x-20x more data. For videos and data, see the project webpage: https://www.robonet.wiki/ |
| Tasks | Video Prediction |
| Published | 2019-10-24 |
| URL | https://arxiv.org/abs/1910.11215v2 |
| https://arxiv.org/pdf/1910.11215v2.pdf | |
| PWC | https://paperswithcode.com/paper/robonet-large-scale-multi-robot-learning |
| Repo | |
| Framework | |
Robust Tensor Recovery with Fiber Outliers for Traffic Events
| Title | Robust Tensor Recovery with Fiber Outliers for Traffic Events |
| Authors | Yue Hu, Dan Work |
| Abstract | Event detection is gaining increasing attention in smart cities research. Large-scale mobility data serves as an important tool to uncover the dynamics of urban transportation systems, and more often than not the dataset is incomplete. In this article, we develop a method to detect extreme events in large traffic datasets, and to impute missing data during regular conditions. Specifically, we propose a robust tensor recovery problem to recover low rank tensors under fiber-sparse corruptions with partial observations, and use it to identify events, and impute missing data under typical conditions. Our approach is scalable to large urban areas, taking full advantage of the spatio-temporal correlations in traffic patterns. We develop an efficient algorithm to solve the tensor recovery problem based on the alternating direction method of multipliers (ADMM) framework. Compared with existing $l_1$ norm regularized tensor decomposition methods, our algorithm can exactly recover the values of uncorrupted fibers of a low rank tensor and find the positions of corrupted fibers under mild conditions. Numerical experiments illustrate that our algorithm can exactly detect outliers even with missing data rates as high as 40%, conditioned on the outlier corruption rate and the Tucker rank of the low rank tensor. Finally, we apply our method on a real traffic dataset corresponding to downtown Nashville, TN, USA and successfully detect the events like severe car crashes, construction lane closures, and other large events that cause significant traffic disruptions. |
| Tasks | |
| Published | 2019-08-27 |
| URL | https://arxiv.org/abs/1908.10198v1 |
| https://arxiv.org/pdf/1908.10198v1.pdf | |
| PWC | https://paperswithcode.com/paper/robust-tensor-recovery-with-fiber-outliers |
| Repo | |
| Framework | |
Probabilistic Successor Representations with Kalman Temporal Differences
| Title | Probabilistic Successor Representations with Kalman Temporal Differences |
| Authors | Jesse P. Geerts, Kimberly L. Stachenfeld, Neil Burgess |
| Abstract | The effectiveness of Reinforcement Learning (RL) depends on an animal’s ability to assign credit for rewards to the appropriate preceding stimuli. One aspect of understanding the neural underpinnings of this process involves understanding what sorts of stimulus representations support generalisation. The Successor Representation (SR), which enforces generalisation over states that predict similar outcomes, has become an increasingly popular model in this space of inquiries. Another dimension of credit assignment involves understanding how animals handle uncertainty about learned associations, using probabilistic methods such as Kalman Temporal Differences (KTD). Combining these approaches, we propose using KTD to estimate a distribution over the SR. KTD-SR captures uncertainty about the estimated SR as well as covariances between different long-term predictions. We show that because of this, KTD-SR exhibits partial transition revaluation as humans do in this experiment without additional replay, unlike the standard TD-SR algorithm. We conclude by discussing future applications of the KTD-SR as a model of the interaction between predictive and probabilistic animal reasoning. |
| Tasks | |
| Published | 2019-10-06 |
| URL | https://arxiv.org/abs/1910.02532v1 |
| https://arxiv.org/pdf/1910.02532v1.pdf | |
| PWC | https://paperswithcode.com/paper/probabilistic-successor-representations-with |
| Repo | |
| Framework | |
A Heuristic Algorithm for the Fabric Spreading and Cutting Problem in Apparel Factories
| Title | A Heuristic Algorithm for the Fabric Spreading and Cutting Problem in Apparel Factories |
| Authors | Xiuqin Shang, Dayong Shen, Fei-Yue Wang, Timo R. Nyberg |
| Abstract | We study the fabric spreading and cutting problem in apparel factories. For the sake of saving the material costs, the cutting requirement should be met exactly without producing additional garment components. For reducing the production costs, the number of lays that corresponds to the frequency of using the cutting beds should be minimized. We propose an iterated greedy algorithm for solving the fabric spreading and cutting problem. This algorithm contains a constructive procedure and an improving loop. Firstly the constructive procedure creates a set of lays in sequence, and then the improving loop tries to pick each lay from the lay set and rearrange the remaining lays into a smaller lay set. The improving loop will run until it cannot obtain any small lay set or the time limit is due. The experiment results on 500 cases shows that the proposed algorithm is effective and efficient. |
| Tasks | |
| Published | 2019-03-13 |
| URL | http://arxiv.org/abs/1903.07557v1 |
| http://arxiv.org/pdf/1903.07557v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-heuristic-algorithm-for-the-fabric |
| Repo | |
| Framework | |
Reluctant generalized additive modeling
| Title | Reluctant generalized additive modeling |
| Authors | J. Kenneth Tay, Robert Tibshirani |
| Abstract | Sparse generalized additive models (GAMs) are an extension of sparse generalized linear models which allow a model’s prediction to vary non-linearly with an input variable. This enables the data analyst build more accurate models, especially when the linearity assumption is known to be a poor approximation of reality. Motivated by reluctant interaction modeling (Yu et al. 2019), we propose a multi-stage algorithm, called $\textit{reluctant generalized additive modeling (RGAM)}$, that can fit sparse generalized additive models at scale. It is guided by the principle that, if all else is equal, one should prefer a linear feature over a non-linear feature. Unlike existing methods for sparse GAMs, RGAM can be extended easily to binary, count and survival data. We demonstrate the method’s effectiveness on real and simulated examples. |
| Tasks | |
| Published | 2019-12-04 |
| URL | https://arxiv.org/abs/1912.01808v2 |
| https://arxiv.org/pdf/1912.01808v2.pdf | |
| PWC | https://paperswithcode.com/paper/reluctant-additive-modeling |
| Repo | |
| Framework | |
Particle swarm optimization model to predict scour depth around bridge pier
| Title | Particle swarm optimization model to predict scour depth around bridge pier |
| Authors | Shahaboddin Shamshirband, Amir Mosavi, Timon Rabczuk |
| Abstract | Scour depth around bridge piers plays a vital role in the safety and stability of the bridges. Existing methods to predict scour depth are mainly based on regression models or black box models in which the first one lacks enough accuracy while the later one does not provide a clear mathematical expression to easily employ it for other situations or cases. Therefore, this paper aims to develop new equations using particle swarm optimization as a metaheuristic approach to predict scour depth around bridge piers. To improve the efficiency of the proposed model, individual equations are derived for laboratory and field data. Moreover, sensitivity analysis is conducted to achieve the most effective parameters in the estimation of scour depth for both experimental and filed data sets. Comparing the results of the proposed model with those of existing regression-based equations reveal the superiority of the proposed method in terms of accuracy and uncertainty. Moreover, the ratio of pier width to flow depth and ratio of d50 (mean particle diameter) to flow depth for the laboratory and field data were recognized as the most effective parameters, respectively. The derived equations can be used as a suitable proxy to estimate scour depth in both experimental and prototype scales. |
| Tasks | |
| Published | 2019-05-26 |
| URL | https://arxiv.org/abs/1906.08863v1 |
| https://arxiv.org/pdf/1906.08863v1.pdf | |
| PWC | https://paperswithcode.com/paper/particle-swarm-optimization-model-to-predict |
| Repo | |
| Framework | |
Code-switching Language Modeling With Bilingual Word Embeddings: A Case Study for Egyptian Arabic-English
| Title | Code-switching Language Modeling With Bilingual Word Embeddings: A Case Study for Egyptian Arabic-English |
| Authors | Injy Hamed, Moritz Zhu, Mohamed Elmahdy, Slim Abdennadher, Ngoc Thang Vu |
| Abstract | Code-switching (CS) is a widespread phenomenon among bilingual and multilingual societies. The lack of CS resources hinders the performance of many NLP tasks. In this work, we explore the potential use of bilingual word embeddings for code-switching (CS) language modeling (LM) in the low resource Egyptian Arabic-English language. We evaluate different state-of-the-art bilingual word embeddings approaches that require cross-lingual resources at different levels and propose an innovative but simple approach that jointly learns bilingual word representations without the use of any parallel data, relying only on monolingual and a small amount of CS data. While all representations improve CS LM, ours performs the best and improves perplexity 33.5% relative over the baseline. |
| Tasks | Language Modelling, Word Embeddings |
| Published | 2019-09-24 |
| URL | https://arxiv.org/abs/1909.10892v1 |
| https://arxiv.org/pdf/1909.10892v1.pdf | |
| PWC | https://paperswithcode.com/paper/code-switching-language-modeling-with |
| Repo | |
| Framework | |
Dialog Intent Induction with Deep Multi-View Clustering
| Title | Dialog Intent Induction with Deep Multi-View Clustering |
| Authors | Hugh Perkins, Yi Yang |
| Abstract | We introduce the dialog intent induction task and present a novel deep multi-view clustering approach to tackle the problem. Dialog intent induction aims at discovering user intents from user query utterances in human-human conversations such as dialogs between customer support agents and customers. Motivated by the intuition that a dialog intent is not only expressed in the user query utterance but also captured in the rest of the dialog, we split a conversation into two independent views and exploit multi-view clustering techniques for inducing the dialog intent. In particular, we propose alternating-view k-means (AV-KMEANS) for joint multi-view representation learning and clustering analysis. The key innovation is that the instance-view representations are updated iteratively by predicting the cluster assignment obtained from the alternative view, so that the multi-view representations of the instances lead to similar cluster assignments. Experiments on two public datasets show that AV-KMEANS can induce better dialog intent clusters than state-of-the-art unsupervised representation learning methods and standard multi-view clustering approaches. |
| Tasks | Representation Learning, Unsupervised Representation Learning |
| Published | 2019-08-30 |
| URL | https://arxiv.org/abs/1908.11487v1 |
| https://arxiv.org/pdf/1908.11487v1.pdf | |
| PWC | https://paperswithcode.com/paper/dialog-intent-induction-with-deep-multi-view |
| Repo | |
| Framework | |
Spatial sensitivity analysis for urban land use prediction with physics-constrained conditional generative adversarial networks
| Title | Spatial sensitivity analysis for urban land use prediction with physics-constrained conditional generative adversarial networks |
| Authors | Adrian Albert, Jasleen Kaur, Emanuele Strano, Marta Gonzalez |
| Abstract | Accurately forecasting urban development and its environmental and climate impacts critically depends on realistic models of the spatial structure of the built environment, and of its dependence on key factors such as population and economic development. Scenario simulation and sensitivity analysis, i.e., predicting how changes in underlying factors at a given location affect urbanization outcomes at other locations, is currently not achievable at a large scale with traditional urban growth models, which are either too simplistic, or depend on detailed locally-collected socioeconomic data that is not available in most places. Here we develop a framework to estimate, purely from globally-available remote-sensing data and without parametric assumptions, the spatial sensitivity of the (\textit{static}) rate of change of urban sprawl to key macroeconomic development indicators. We formulate this spatial regression problem as an image-to-image translation task using conditional generative adversarial networks (GANs), where the gradients necessary for comparative static analysis are provided by the backpropagation algorithm used to train the model. This framework allows to naturally incorporate physical constraints, e.g., the inability to build over water bodies. To validate the spatial structure of model-generated built environment distributions, we use spatial statistics commonly used in urban form analysis. We apply our method to a novel dataset comprising of layers on the built environment, nightlighs measurements (a proxy for economic development and energy use), and population density for the world’s most populous 15,000 cities. |
| Tasks | Image-to-Image Translation |
| Published | 2019-07-22 |
| URL | https://arxiv.org/abs/1907.09543v1 |
| https://arxiv.org/pdf/1907.09543v1.pdf | |
| PWC | https://paperswithcode.com/paper/spatial-sensitivity-analysis-for-urban-land |
| Repo | |
| Framework | |
Complex Scene Classification of PolSAR Imagery based on a Self-paced Learning Approach
| Title | Complex Scene Classification of PolSAR Imagery based on a Self-paced Learning Approach |
| Authors | Wenshuai Chen, Shuiping Gou, Xinlin Wang, Licheng Jiao, Changzhe Jiao, Alina Zare |
| Abstract | Existing polarimetric synthetic aperture radar (PolSAR) image classification methods cannot achieve satisfactory performance on complex scenes characterized by several types of land cover with significant levels of noise or similar scattering properties across land cover types. Hence, we propose a supervised classification method aimed at constructing a classifier based on self-paced learning (SPL). SPL has been demonstrated to be effective at dealing with complex data while providing classifier. In this paper, a novel Support Vector Machine (SVM) algorithm based on SPL with neighborhood constraints (SVM_SPLNC) is proposed. The proposed method leverages the easiest samples first to obtain an initial parameter vector. Then, more complex samples are gradually incorporated to update the parameter vector iteratively. Moreover, neighborhood constraints are introduced during the training process to further improve performance. Experimental results on three real PolSAR images show that the proposed method performs well on complex scenes. |
| Tasks | Image Classification, Scene Classification |
| Published | 2019-03-18 |
| URL | http://arxiv.org/abs/1903.07243v1 |
| http://arxiv.org/pdf/1903.07243v1.pdf | |
| PWC | https://paperswithcode.com/paper/complex-scene-classification-of-polsar |
| Repo | |
| Framework | |
A blind Robust Image Watermarking Approach exploiting the DFT Magnitude
| Title | A blind Robust Image Watermarking Approach exploiting the DFT Magnitude |
| Authors | Mohamed Hamidi, Mohamed El Haziti, Hocine Cherifi, Driss Aboutajdine |
| Abstract | Due to the current progress in Internet, digital contents (video, audio and images) are widely used. Distribution of multimedia contents is now faster and it allows for easy unauthorized reproduction of information. Digital watermarking came up while trying to solve this problem. Its main idea is to embed a watermark into a host digital content without affecting its quality. Moreover, watermarking can be used in several applications such as authentication, copy control, indexation, Copyright protection, etc. In this paper, we propose a blind robust image watermarking approach as a solution to the problem of copyright protection of digital images. The underlying concept of our method is to apply a discrete cosine transform (DCT) to the magnitude resulting from a discrete Fourier transform (DFT) applied to the original image. Then, the watermark is embedded by modifying the coefficients of the DCT using a secret key to increase security. Experimental results show the robustness of the proposed technique to a wide range of common attacks, e.g., Low-Pass Gaussian Filtering, JPEG compression, Gaussian noise, salt & pepper noise, Gaussian Smoothing and Histogram equalization. The proposed method achieves a Peak signal-to-noise-ration (PSNR) value greater than 66 (dB) and ensures a perfect watermark extraction. |
| Tasks | |
| Published | 2019-10-22 |
| URL | https://arxiv.org/abs/1910.11185v1 |
| https://arxiv.org/pdf/1910.11185v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-blind-robust-image-watermarking-approach |
| Repo | |
| Framework | |
Deep Learning for Molecular Graphs with Tiered Graph Autoencoders and Graph Classification
| Title | Deep Learning for Molecular Graphs with Tiered Graph Autoencoders and Graph Classification |
| Authors | Daniel T. Chang |
| Abstract | Tiered graph autoencoders provide the architecture and mechanisms for learning tiered latent representations and latent spaces for molecular graphs that explicitly represent and utilize groups (e.g., functional groups). This enables the utilization and exploration of tiered molecular latent spaces, either individually – the node (atom) tier, the group tier, or the graph (molecule) tier – or jointly, as well as navigation across the tiers. In this paper, we discuss the use of tiered graph autoencoders together with graph classification for molecular graphs. We show features of molecular graphs used, and groups in molecular graphs identified for some sample molecules. We briefly review graph classification and the QM9 dataset for background information, and discuss the use of tiered graph embeddings for graph classification, particularly weighted group pooling. We find that functional groups and ring groups effectively capture and represent the chemical essence of molecular graphs (structures). Further, tiered graph autoencoders and graph classification together provide effective, efficient and interpretable deep learning for molecular graphs, with the former providing unsupervised, transferable learning and the latter providing supervised, task-optimized learning. |
| Tasks | Graph Classification |
| Published | 2019-10-24 |
| URL | https://arxiv.org/abs/1910.11390v1 |
| https://arxiv.org/pdf/1910.11390v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-for-molecular-graphs-with |
| Repo | |
| Framework | |
Knowledge-based multi-level aggregation for decision aid in the machining industry
| Title | Knowledge-based multi-level aggregation for decision aid in the machining industry |
| Authors | Mathieu Ritou, Farouk Belkadi, Zakaria Yahouni, Catherine Da Cunha, Florent Laroche, Benoit Furet |
| Abstract | In the context of Industry 4.0, data management is a key point for decision aid approaches. Large amounts of manufacturing digital data are collected on the shop floor. Their analysis can then require a large amount of computing power. The Big Data issue can be solved by aggregation, generating smart and meaningful data. This paper presents a new knowledge-based multi-level aggregation strategy to support decision making. Manufacturing knowledge is used at each level to design the monitoring criteria or aggregation operators. The proposed approach has been implemented as a demonstrator and successfully applied to a real machining database from the aeronautic industry. Decision Making; Machining; Knowledge based system |
| Tasks | Decision Making |
| Published | 2019-05-14 |
| URL | https://arxiv.org/abs/1905.06413v1 |
| https://arxiv.org/pdf/1905.06413v1.pdf | |
| PWC | https://paperswithcode.com/paper/knowledge-based-multi-level-aggregation-for |
| Repo | |
| Framework | |
Argus: Smartphone-enabled Human Cooperation via Multi-Agent Reinforcement Learning for Disaster Situational Awareness
| Title | Argus: Smartphone-enabled Human Cooperation via Multi-Agent Reinforcement Learning for Disaster Situational Awareness |
| Authors | Vidyasagar Sadhu, Gabriel Salles-Loustau, Dario Pompili, Saman Zonouz, Vincent Sritapan |
| Abstract | Argus exploits a Multi-Agent Reinforcement Learning (MARL) framework to create a 3D mapping of the disaster scene using agents present around the incident zone to facilitate the rescue operations. The agents can be both human bystanders at the disaster scene as well as drones or robots that can assist the humans. The agents are involved in capturing the images of the scene using their smartphones (or on-board cameras in case of drones) as directed by the MARL algorithm. These images are used to build real time a 3D map of the disaster scene. Via both simulations and real experiments, an evaluation of the framework in terms of effectiveness in tracking random dynamicity of the environment is presented. |
| Tasks | Multi-agent Reinforcement Learning |
| Published | 2019-04-29 |
| URL | https://arxiv.org/abs/1906.03037v1 |
| https://arxiv.org/pdf/1906.03037v1.pdf | |
| PWC | https://paperswithcode.com/paper/argus-smartphone-enabled-human-cooperation |
| Repo | |
| Framework | |
Deep Amortized Clustering
| Title | Deep Amortized Clustering |
| Authors | Juho Lee, Yoonho Lee, Yee Whye Teh |
| Abstract | We propose a deep amortized clustering (DAC), a neural architecture which learns to cluster datasets efficiently using a few forward passes. DAC implicitly learns what makes a cluster, how to group data points into clusters, and how to count the number of clusters in datasets. DAC is meta-learned using labelled datasets for training, a process distinct from traditional clustering algorithms which usually require hand-specified prior knowledge about cluster shapes/structures. We empirically show, on both synthetic and image data, that DAC can efficiently and accurately cluster new datasets coming from the same distribution used to generate training datasets. |
| Tasks | |
| Published | 2019-09-30 |
| URL | https://arxiv.org/abs/1909.13433v1 |
| https://arxiv.org/pdf/1909.13433v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-amortized-clustering |
| Repo | |
| Framework | |
