Paper Group ANR 373
Scene Induced Multi-Modal Trajectory Forecasting via Planning. A Facial Affect Analysis System for Autism Spectrum Disorder. Fast LLMMSE filter for low-dose CT imaging. Curriculum Learning for Deep Generative Models with Clustering. Machine Learning Inter-Atomic Potentials Generation Driven by Active Learning: A Case Study for Amorphous and Liquid …
Scene Induced Multi-Modal Trajectory Forecasting via Planning
| Title | Scene Induced Multi-Modal Trajectory Forecasting via Planning |
| Authors | Nachiket Deo, Mohan M. Trivedi |
| Abstract | We address multi-modal trajectory forecasting of agents in unknown scenes by formulating it as a planning problem. We present an approach consisting of three models; a goal prediction model to identify potential goals of the agent, an inverse reinforcement learning model to plan optimal paths to each goal, and a trajectory generator to obtain future trajectories along the planned paths. Analysis of predictions on the Stanford drone dataset, shows generalizability of our approach to novel scenes. |
| Tasks | |
| Published | 2019-05-23 |
| URL | https://arxiv.org/abs/1905.09949v1 |
| https://arxiv.org/pdf/1905.09949v1.pdf | |
| PWC | https://paperswithcode.com/paper/190509949 |
| Repo | |
| Framework | |
A Facial Affect Analysis System for Autism Spectrum Disorder
| Title | A Facial Affect Analysis System for Autism Spectrum Disorder |
| Authors | Beibin Li, Sachin Mehta, Deepali Aneja, Claire Foster, Pamela Ventola, Frederick Shic, Linda Shapiro |
| Abstract | In this paper, we introduce an end-to-end machine learning-based system for classifying autism spectrum disorder (ASD) using facial attributes such as expressions, action units, arousal, and valence. Our system classifies ASD using representations of different facial attributes from convolutional neural networks, which are trained on images in the wild. Our experimental results show that different facial attributes used in our system are statistically significant and improve sensitivity, specificity, and F1 score of ASD classification by a large margin. In particular, the addition of different facial attributes improves the performance of ASD classification by about 7% which achieves a F1 score of 76%. |
| Tasks | |
| Published | 2019-04-07 |
| URL | http://arxiv.org/abs/1904.03616v1 |
| http://arxiv.org/pdf/1904.03616v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-facial-affect-analysis-system-for-autism |
| Repo | |
| Framework | |
Fast LLMMSE filter for low-dose CT imaging
| Title | Fast LLMMSE filter for low-dose CT imaging |
| Authors | Fengling Wang, Bowen Lin, Shujun Fu, Shiling Xie, Zhigang Zhao, Yuliang Li |
| Abstract | Low-dose X-ray CT technology is one of important directions of current research and development of medical imaging equipment. A fast algorithm of blockwise sinogram filtering is presented for realtime low-dose CT imaging. A nonstationary Gaussian noise model of low-dose sinogram data is proposed in the low-mA (tube current) CT protocol. Then, according to the linear minimum mean square error principle, an adaptive blockwise algorithm is built to filter contaminated sinogram data caused by photon starvation. A moving sum technique is used to speed the algorithm into a linear time one, regardless of the block size and thedata range. The proposedfast filtering givesa better performance in noise reduction and detail preservation in the reconstructed images,which is verified in experiments on simulated and real data compared with some related filtering methods. |
| Tasks | |
| Published | 2019-03-23 |
| URL | http://arxiv.org/abs/1903.09745v1 |
| http://arxiv.org/pdf/1903.09745v1.pdf | |
| PWC | https://paperswithcode.com/paper/fast-llmmse-filter-for-low-dose-ct-imaging |
| Repo | |
| Framework | |
Curriculum Learning for Deep Generative Models with Clustering
| Title | Curriculum Learning for Deep Generative Models with Clustering |
| Authors | Deli Zhao, Jiapeng Zhu, Zhenfang Guo, Bo Zhang |
| Abstract | Training generative models like Generative Adversarial Network (GAN) is challenging for noisy data. A novel curriculum learning algorithm pertaining to clustering is proposed to address this issue in this paper. The curriculum construction is based on the centrality of underlying clusters in data points. The data points of high centrality takes priority of being fed into generative models during training. To make our algorithm scalable to large-scale data, the active set is devised, in the sense that every round of training proceeds only on an active subset containing a small fraction of already trained data and the incremental data of lower centrality. Moreover, the geometric analysis is presented to interpret the necessity of cluster curriculum for generative models. The experiments on cat and human-face data validate that our algorithm is able to learn the optimal generative models (e.g. ProGAN) with respect to specified quality metrics for noisy data. An interesting finding is that the optimal cluster curriculum is closely related to the critical point of the geometric percolation process formulated in the paper. |
| Tasks | |
| Published | 2019-06-27 |
| URL | https://arxiv.org/abs/1906.11594v2 |
| https://arxiv.org/pdf/1906.11594v2.pdf | |
| PWC | https://paperswithcode.com/paper/curriculum-learning-for-deep-generative |
| Repo | |
| Framework | |
Machine Learning Inter-Atomic Potentials Generation Driven by Active Learning: A Case Study for Amorphous and Liquid Hafnium dioxide
| Title | Machine Learning Inter-Atomic Potentials Generation Driven by Active Learning: A Case Study for Amorphous and Liquid Hafnium dioxide |
| Authors | Ganesh Sivaraman, Anand Narayanan Krishnamoorthy, Matthias Baur, Christian Holm, Marius Stan, Gabor Csányi, Chris Benmore, Álvaro Vázquez-Mayagoitia |
| Abstract | We propose a novel active learning scheme for automatically sampling a minimum number of uncorrelated configurations for fitting the Gaussian Approximation Potential (GAP). Our active learning scheme consists of an unsupervised machine learning (ML) scheme coupled to Bayesian optimization technique that evaluates the GAP model. We apply this scheme to a Hafnium dioxide (HfO2) dataset generated from a melt-quench ab initio molecular dynamics (AIMD) protocol. Our results show that the active learning scheme, with no prior knowledge of the dataset is able to extract a configuration that reaches the required energy fit tolerance. Further, molecular dynamics (MD) simulations performed using this active learned GAP model on 6144-atom systems of amorphous and liquid state elucidate the structural properties of HfO2 with near ab initio precision and quench rates (i.e. 1.0 K/ps) not accessible via AIMD. The melt and amorphous x-ray structural factors generated from our simulation are in good agreement with experiment. Additionally, the calculated diffusion constants are in good agreement with previous ab initio studies. |
| Tasks | Active Learning |
| Published | 2019-10-22 |
| URL | https://arxiv.org/abs/1910.10254v1 |
| https://arxiv.org/pdf/1910.10254v1.pdf | |
| PWC | https://paperswithcode.com/paper/machine-learning-inter-atomic-potentials |
| Repo | |
| Framework | |
Active Learning with Importance Sampling
| Title | Active Learning with Importance Sampling |
| Authors | Muni Sreenivas Pydi, Vishnu Suresh Lokhande |
| Abstract | We consider an active learning setting where the algorithm has access to a large pool of unlabeled data and a small pool of labeled data. In each iteration, the algorithm chooses few unlabeled data points and obtains their labels from an oracle. In this paper, we consider a probabilistic querying procedure to choose the points to be labeled. We propose an algorithm for Active Learning with Importance Sampling (ALIS), and derive upper bounds on the true loss incurred by the algorithm for any arbitrary probabilistic sampling procedure. Further, we propose an optimal sampling distribution that minimizes the upper bound on the true loss. |
| Tasks | Active Learning |
| Published | 2019-10-10 |
| URL | https://arxiv.org/abs/1910.04371v1 |
| https://arxiv.org/pdf/1910.04371v1.pdf | |
| PWC | https://paperswithcode.com/paper/active-learning-with-importance-sampling |
| Repo | |
| Framework | |
Learning Action Representations for Reinforcement Learning
| Title | Learning Action Representations for Reinforcement Learning |
| Authors | Yash Chandak, Georgios Theocharous, James Kostas, Scott Jordan, Philip S. Thomas |
| Abstract | Most model-free reinforcement learning methods leverage state representations (embeddings) for generalization, but either ignore structure in the space of actions or assume the structure is provided a priori. We show how a policy can be decomposed into a component that acts in a low-dimensional space of action representations and a component that transforms these representations into actual actions. These representations improve generalization over large, finite action sets by allowing the agent to infer the outcomes of actions similar to actions already taken. We provide an algorithm to both learn and use action representations and provide conditions for its convergence. The efficacy of the proposed method is demonstrated on large-scale real-world problems. |
| Tasks | |
| Published | 2019-02-01 |
| URL | https://arxiv.org/abs/1902.00183v2 |
| https://arxiv.org/pdf/1902.00183v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-action-representations-for |
| Repo | |
| Framework | |
Neural Metric Learning for Fast End-to-End Relation Extraction
| Title | Neural Metric Learning for Fast End-to-End Relation Extraction |
| Authors | Tung Tran, Ramakanth Kavuluru |
| Abstract | Relation extraction (RE) is an indispensable information extraction task in several disciplines. RE models typically assume that named entity recognition (NER) is already performed in a previous step by another independent model. Several recent efforts, under the theme of end-to-end RE, seek to exploit inter-task correlations by modeling both NER and RE tasks jointly. Earlier work in this area commonly reduces the task to a table-filling problem wherein an additional expensive decoding step involving beam search is applied to obtain globally consistent cell labels. In efforts that do not employ table-filling, global optimization in the form of CRFs with Viterbi decoding for the NER component is still necessary for competitive performance. We introduce a novel neural architecture utilizing the table structure, based on repeated applications of 2D convolutions for pooling local dependency and metric-based features, that improves on the state-of-the-art without the need for global optimization. We validate our model on the ADE and CoNLL04 datasets for end-to-end RE and demonstrate $\approx 1%$ gain (in F-score) over prior best results with training and testing times that are seven to ten times faster — the latter highly advantageous for time-sensitive end user applications. |
| Tasks | Metric Learning, Named Entity Recognition, Relation Extraction |
| Published | 2019-05-17 |
| URL | https://arxiv.org/abs/1905.07458v4 |
| https://arxiv.org/pdf/1905.07458v4.pdf | |
| PWC | https://paperswithcode.com/paper/neural-metric-learning-for-fast-end-to-end |
| Repo | |
| Framework | |
Scale-Equivariant Neural Networks with Decomposed Convolutional Filters
| Title | Scale-Equivariant Neural Networks with Decomposed Convolutional Filters |
| Authors | Wei Zhu, Qiang Qiu, Robert Calderbank, Guillermo Sapiro, Xiuyuan Cheng |
| Abstract | Encoding the input scale information explicitly into the representation learned by a convolutional neural network (CNN) is beneficial for many vision tasks especially when dealing with multiscale input signals. We study, in this paper, a scale-equivariant CNN architecture with joint convolutions across the space and the scaling group, which is shown to be both sufficient and necessary to achieve scale-equivariant representations. To reduce the model complexity and computational burden, we decompose the convolutional filters under two pre-fixed separable bases and truncate the expansion to low-frequency components. A further benefit of the truncated filter expansion is the improved deformation robustness of the equivariant representation. Numerical experiments demonstrate that the proposed scale-equivariant neural network with decomposed convolutional filters (ScDCFNet) achieves significantly improved performance in multiscale image classification and better interpretability than regular CNNs at a reduced model size. |
| Tasks | Image Classification |
| Published | 2019-09-24 |
| URL | https://arxiv.org/abs/1909.11193v1 |
| https://arxiv.org/pdf/1909.11193v1.pdf | |
| PWC | https://paperswithcode.com/paper/scale-equivariant-neural-networks-with |
| Repo | |
| Framework | |
Playing magic tricks to deep neural networks untangles human deception
| Title | Playing magic tricks to deep neural networks untangles human deception |
| Authors | Regina Zaghi-Lara, Miguel Ángel Gea, Jordi Camí, Luis M. Martínez, Alex Gomez-Marin |
| Abstract | Magic is the art of producing in the spectator an illusion of impossibility. Although the scientific study of magic is in its infancy, the advent of recent tracking algorithms based on deep learning allow now to quantify the skills of the magician in naturalistic conditions at unprecedented resolution and robustness. In this study, we deconstructed stage magic into purely motor maneuvers and trained an artificial neural network (DeepLabCut) to follow coins as a professional magician made them appear and disappear in a series of tricks. Rather than using AI as a mere tracking tool, we conceived it as an “artificial spectator”. When the coins were not visible, the algorithm was trained to infer their location as a human spectator would (i.e. in the left fist). This created situations where the human was fooled while AI (as seen by a human) was not, and vice versa. Magic from the perspective of the machine reveals our own cognitive biases. |
| Tasks | |
| Published | 2019-08-20 |
| URL | https://arxiv.org/abs/1908.07446v1 |
| https://arxiv.org/pdf/1908.07446v1.pdf | |
| PWC | https://paperswithcode.com/paper/playing-magic-tricks-to-deep-neural-networks |
| Repo | |
| Framework | |
Radial Prediction Layer
| Title | Radial Prediction Layer |
| Authors | Christian Herta, Benjamin Voigt |
| Abstract | For a broad variety of critical applications, it is essential to know how confident a classification prediction is. In this paper, we discuss the drawbacks of softmax to calculate class probabilities and to handle uncertainty in Bayesian neural networks. We introduce a new kind of prediction layer called radial prediction layer (RPL) to overcome these issues. In contrast to the softmax classification, RPL is based on the open-world assumption. Therefore, the class prediction probabilities are much more meaningful to assess the uncertainty concerning the novelty of the input. We show that neural networks with RPLs can be learned in the same way as neural networks using softmax. On a 2D toy data set (spiral data), we demonstrate the fundamental principles and advantages. On the real-world ImageNet data set, we show that the open-world properties are beneficially fulfilled. Additionally, we show that RPLs are less sensible to adversarial attacks on the MNIST data set. Due to its features, we expect RPL to be beneficial in a broad variety of applications, especially in critical environments, such as medicine or autonomous driving. |
| Tasks | Autonomous Driving |
| Published | 2019-05-27 |
| URL | https://arxiv.org/abs/1905.11150v2 |
| https://arxiv.org/pdf/1905.11150v2.pdf | |
| PWC | https://paperswithcode.com/paper/radial-prediction-layer |
| Repo | |
| Framework | |
Unsupervised Eyeglasses Removal in the Wild
| Title | Unsupervised Eyeglasses Removal in the Wild |
| Authors | Bingwen Hu, Zhedong Zheng, Ping Liu, Wankou Yang, Mingwu Ren |
| Abstract | Eyeglasses removal is challenging in removing different kinds of eyeglasses, e.g., rimless glasses, full-rim glasses and sunglasses, and recovering appropriate eyes. Due to the large visual variants, the conventional methods lack scalability. Most existing works focus on the frontal face images in the controlled environment, such as the laboratory, and need to design specific systems for different eyeglass types. To address the limitation, we propose a unified eyeglass removal model called Eyeglasses Removal Generative Adversarial Network (ERGAN), which could handle different types of glasses in the wild. The proposed method does not depend on the dense annotation of eyeglasses location but benefits from the large-scale face images with weak annotations. Specifically, we study the two relevant tasks simultaneously, i.e., removing and wearing eyeglasses. Given two facial images with and without eyeglasses, the proposed model learns to swap the eye area in two faces. The generation mechanism focuses on the eye area and invades the difficulty of generating a new face. In the experiment, we show the proposed method achieves a competitive removal quality in terms of realism and diversity. Furthermore, we evaluate ERGAN on several subsequent tasks, such as face verification and facial expression recognition. The experiment shows that our method could serve as a pre-processing method for these tasks. |
| Tasks | Face Verification, Facial Expression Recognition |
| Published | 2019-09-16 |
| URL | https://arxiv.org/abs/1909.06989v3 |
| https://arxiv.org/pdf/1909.06989v3.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-eyeglasses-removal-in-the-wild |
| Repo | |
| Framework | |
Low-supervision urgency detection and transfer in short crisis messages
| Title | Low-supervision urgency detection and transfer in short crisis messages |
| Authors | Mayank Kejriwal, Peilin Zhou |
| Abstract | Humanitarian disasters have been on the rise in recent years due to the effects of climate change and socio-political situations such as the refugee crisis. Technology can be used to best mobilize resources such as food and water in the event of a natural disaster, by semi-automatically flagging tweets and short messages as indicating an urgent need. The problem is challenging not just because of the sparseness of data in the immediate aftermath of a disaster, but because of the varying characteristics of disasters in developing countries (making it difficult to train just one system) and the noise and quirks in social media. In this paper, we present a robust, low-supervision social media urgency system that adapts to arbitrary crises by leveraging both labeled and unlabeled data in an ensemble setting. The system is also able to adapt to new crises where an unlabeled background corpus may not be available yet by utilizing a simple and effective transfer learning methodology. Experimentally, our transfer learning and low-supervision approaches are found to outperform viable baselines with high significance on myriad disaster datasets. |
| Tasks | Transfer Learning |
| Published | 2019-07-15 |
| URL | https://arxiv.org/abs/1907.06745v1 |
| https://arxiv.org/pdf/1907.06745v1.pdf | |
| PWC | https://paperswithcode.com/paper/low-supervision-urgency-detection-and |
| Repo | |
| Framework | |
Atmospheric turbulence removal using convolutional neural network
| Title | Atmospheric turbulence removal using convolutional neural network |
| Authors | Jing Gao, N. Anantrasirichai, David Bull |
| Abstract | This paper describes a novel deep learning-based method for mitigating the effects of atmospheric distortion. We have built an end-to-end supervised convolutional neural network (CNN) to reconstruct turbulence-corrupted video sequence. Our framework has been developed on the residual learning concept, where the spatio-temporal distortions are learnt and predicted. Our experiments demonstrate that the proposed method can deblur, remove ripple effect and enhance contrast of the video sequences simultaneously. Our model was trained and tested with both simulated and real distortions. Experimental results of the real distortions show that our method outperforms the existing ones by up to 3.8% in term of the quality of restored images, and it achieves faster speed than the state-of-the-art methods by up to 23 times with GPU implementation. |
| Tasks | |
| Published | 2019-12-22 |
| URL | https://arxiv.org/abs/1912.11350v1 |
| https://arxiv.org/pdf/1912.11350v1.pdf | |
| PWC | https://paperswithcode.com/paper/atmospheric-turbulence-removal-using |
| Repo | |
| Framework | |
A Parallel Corpus of Theses and Dissertations Abstracts
| Title | A Parallel Corpus of Theses and Dissertations Abstracts |
| Authors | Felipe Soares, Gabrielli Harumi Yamashita, Michel Jose Anzanello |
| Abstract | In Brazil, the governmental body responsible for overseeing and coordinating post-graduate programs, CAPES, keeps records of all theses and dissertations presented in the country. Information regarding such documents can be accessed online in the Theses and Dissertations Catalog (TDC), which contains abstracts in Portuguese and English, and additional metadata. Thus, this database can be a potential source of parallel corpora for the Portuguese and English languages. In this article, we present the development of a parallel corpus from TDC, which is made available by CAPES under the open data initiative. Approximately 240,000 documents were collected and aligned using the Hunalign tool. We demonstrate the capability of our developed corpus by training Statistical Machine Translation (SMT) and Neural Machine Translation (NMT) models for both language directions, followed by a comparison with Google Translate (GT). Both translation models presented better BLEU scores than GT, with NMT system being the most accurate one. Sentence alignment was also manually evaluated, presenting an average of 82.30% correctly aligned sentences. Our parallel corpus is freely available in TMX format, with complementary information regarding document metadata |
| Tasks | Machine Translation |
| Published | 2019-05-05 |
| URL | https://arxiv.org/abs/1905.01715v1 |
| https://arxiv.org/pdf/1905.01715v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-parallel-corpus-of-theses-and-dissertations |
| Repo | |
| Framework | |
