Paper Group ANR 410
Blind Deconvolution Microscopy Using Cycle Consistent CNN with Explicit PSF Layer. Iterative Channel Estimation for Discrete Denoising under Channel Uncertainty. Coupled CycleGAN: Unsupervised Hashing Network for Cross-Modal Retrieval. Multi-Task Learning with Language Modeling for Question Generation. Electrical Impedance Tomography based on Genet …
Blind Deconvolution Microscopy Using Cycle Consistent CNN with Explicit PSF Layer
| Title | Blind Deconvolution Microscopy Using Cycle Consistent CNN with Explicit PSF Layer |
| Authors | Sungjun Lim, Sang-Eun Lee, Sunghoe Chang, Jong Chul Ye |
| Abstract | Deconvolution microscopy has been extensively used to improve the resolution of the widefield fluorescent microscopy. Conventional approaches, which usually require the point spread function (PSF) measurement or blind estimation, are however computationally expensive. Recently, CNN based approaches have been explored as a fast and high performance alternative. In this paper, we present a novel unsupervised deep neural network for blind deconvolution based on cycle consistency and PSF modeling layers. In contrast to the recent CNN approaches for similar problem, the explicit PSF modeling layers improve the robustness of the algorithm. Experimental results confirm the efficacy of the algorithm. |
| Tasks | |
| Published | 2019-04-05 |
| URL | http://arxiv.org/abs/1904.02910v1 |
| http://arxiv.org/pdf/1904.02910v1.pdf | |
| PWC | https://paperswithcode.com/paper/blind-deconvolution-microscopy-using-cycle |
| Repo | |
| Framework | |
Iterative Channel Estimation for Discrete Denoising under Channel Uncertainty
| Title | Iterative Channel Estimation for Discrete Denoising under Channel Uncertainty |
| Authors | Hongjoon Ahn, Taesup Moon |
| Abstract | We propose a novel iterative channel estimation (ICE) algorithm that essentially removes the critical known noisy channel assumption for universal discrete denoising problem. Our algorithm is based on Neural DUDE (N-DUDE), a recently proposed neural network-based discrete denoiser, and it estimates the channel transition matrix as well as the neural network parameters in an alternating manner until convergence. While we do not make any probabilistic assumption on the underlying clean data, our ICE resembles Expectation-Maximization (EM) with variational approximation, and it takes advantage of the property of N-DUDE being locally robust around the true channel. With extensive experiments on several radically different types of data, we show that the ICE equipped N-DUDE (dubbed as ICE-N-DUDE) can perform \emph{universally} well regardless of the uncertainties in both the channel and the clean source. Moreover, we show ICE-N-DUDE becomes extremely robust to its hyperparameters and significantly outperforms the strong baseline that can deal with the channel uncertainties for denoising, the widely used Baum-Welch (BW) algorithm for hidden Markov models (HMM). |
| Tasks | Denoising |
| Published | 2019-02-24 |
| URL | https://arxiv.org/abs/1902.08921v2 |
| https://arxiv.org/pdf/1902.08921v2.pdf | |
| PWC | https://paperswithcode.com/paper/iterative-channel-estimation-for-discrete |
| Repo | |
| Framework | |
Coupled CycleGAN: Unsupervised Hashing Network for Cross-Modal Retrieval
| Title | Coupled CycleGAN: Unsupervised Hashing Network for Cross-Modal Retrieval |
| Authors | Chao Li, Cheng Deng, Lei Wang, De Xie, Xianglong Liu |
| Abstract | In recent years, hashing has attracted more and more attention owing to its superior capacity of low storage cost and high query efficiency in large-scale cross-modal retrieval. Benefiting from deep leaning, continuously compelling results in cross-modal retrieval community have been achieved. However, existing deep cross-modal hashing methods either rely on amounts of labeled information or have no ability to learn an accuracy correlation between different modalities. In this paper, we proposed Unsupervised coupled Cycle generative adversarial Hashing networks (UCH), for cross-modal retrieval, where outer-cycle network is used to learn powerful common representation, and inner-cycle network is explained to generate reliable hash codes. Specifically, our proposed UCH seamlessly couples these two networks with generative adversarial mechanism, which can be optimized simultaneously to learn representation and hash codes. Extensive experiments on three popular benchmark datasets show that the proposed UCH outperforms the state-of-the-art unsupervised cross-modal hashing methods. |
| Tasks | Cross-Modal Retrieval |
| Published | 2019-03-06 |
| URL | http://arxiv.org/abs/1903.02149v1 |
| http://arxiv.org/pdf/1903.02149v1.pdf | |
| PWC | https://paperswithcode.com/paper/coupled-cyclegan-unsupervised-hashing-network |
| Repo | |
| Framework | |
Multi-Task Learning with Language Modeling for Question Generation
| Title | Multi-Task Learning with Language Modeling for Question Generation |
| Authors | Wenjie Zhou, Minghua Zhang, Yunfang Wu |
| Abstract | This paper explores the task of answer-aware questions generation. Based on the attention-based pointer generator model, we propose to incorporate an auxiliary task of language modeling to help question generation in a hierarchical multi-task learning structure. Our joint-learning model enables the encoder to learn a better representation of the input sequence, which will guide the decoder to generate more coherent and fluent questions. On both SQuAD and MARCO datasets, our multi-task learning model boosts the performance, achieving state-of-the-art results. Moreover, human evaluation further proves the high quality of our generated questions. |
| Tasks | Language Modelling, Multi-Task Learning, Question Generation |
| Published | 2019-08-30 |
| URL | https://arxiv.org/abs/1908.11813v1 |
| https://arxiv.org/pdf/1908.11813v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-task-learning-with-language-modeling |
| Repo | |
| Framework | |
Electrical Impedance Tomography based on Genetic Algorithm
| Title | Electrical Impedance Tomography based on Genetic Algorithm |
| Authors | Mingyong Zhou |
| Abstract | In this paper, we applies GA algorithm into Electrical Impedance Tomography (EIT) application. We first outline the EIT problem as an optimization problem and define a target optimization function. Then we show how the GA algorithm as an alternative searching algorithm can be used for solving EIT inverse problem. In this paper, we explore evolutionary methods such as GA algorithms combined with various regularization operators to solve EIT inverse computing problem. Key words: Electrical Impedance Tomography (EIT), GA, Tikhonov operator , Mumford-Shah operator, Particle Swarm Optimization(PSO), Back Propagation(BP). |
| Tasks | |
| Published | 2019-01-14 |
| URL | http://arxiv.org/abs/1901.04872v1 |
| http://arxiv.org/pdf/1901.04872v1.pdf | |
| PWC | https://paperswithcode.com/paper/electrical-impedance-tomography-based-on |
| Repo | |
| Framework | |
Model Compression with Multi-Task Knowledge Distillation for Web-scale Question Answering System
| Title | Model Compression with Multi-Task Knowledge Distillation for Web-scale Question Answering System |
| Authors | Ze Yang, Linjun Shou, Ming Gong, Wutao Lin, Daxin Jiang |
| Abstract | Deep pre-training and fine-tuning models (like BERT, OpenAI GPT) have demonstrated excellent results in question answering areas. However, due to the sheer amount of model parameters, the inference speed of these models is very slow. How to apply these complex models to real business scenarios becomes a challenging but practical problem. Previous works often leverage model compression approaches to resolve this problem. However, these methods usually induce information loss during the model compression procedure, leading to incomparable results between compressed model and the original model. To tackle this challenge, we propose a Multi-task Knowledge Distillation Model (MKDM for short) for web-scale Question Answering system, by distilling knowledge from multiple teacher models to a light-weight student model. In this way, more generalized knowledge can be transferred. The experiment results show that our method can significantly outperform the baseline methods and even achieve comparable results with the original teacher models, along with significant speedup of model inference. |
| Tasks | Model Compression, Question Answering |
| Published | 2019-04-21 |
| URL | http://arxiv.org/abs/1904.09636v1 |
| http://arxiv.org/pdf/1904.09636v1.pdf | |
| PWC | https://paperswithcode.com/paper/model-compression-with-multi-task-knowledge |
| Repo | |
| Framework | |
Generating All the Roads to Rome: Road Layout Randomization for Improved Road Marking Segmentation
| Title | Generating All the Roads to Rome: Road Layout Randomization for Improved Road Marking Segmentation |
| Authors | Tom Bruls, Horia Porav, Lars Kunze, Paul Newman |
| Abstract | Road markings provide guidance to traffic participants and enforce safe driving behaviour, understanding their semantic meaning is therefore paramount in (automated) driving. However, producing the vast quantities of road marking labels required for training state-of-the-art deep networks is costly, time-consuming, and simply infeasible for every domain and condition. In addition, training data retrieved from virtual worlds often lack the richness and complexity of the real world and consequently cannot be used directly. In this paper, we provide an alternative approach in which new road marking training pairs are automatically generated. To this end, we apply principles of domain randomization to the road layout and synthesize new images from altered semantic labels. We demonstrate that training on these synthetic pairs improves mIoU of the segmentation of rare road marking classes during real-world deployment in complex urban environments by more than 12 percentage points, while performance for other classes is retained. This framework can easily be scaled to all domains and conditions to generate large-scale road marking datasets, while avoiding manual labelling effort. |
| Tasks | |
| Published | 2019-07-10 |
| URL | https://arxiv.org/abs/1907.04569v1 |
| https://arxiv.org/pdf/1907.04569v1.pdf | |
| PWC | https://paperswithcode.com/paper/generating-all-the-roads-to-rome-road-layout |
| Repo | |
| Framework | |
Multiple perspectives HMM-based feature engineering for credit card fraud detection
| Title | Multiple perspectives HMM-based feature engineering for credit card fraud detection |
| Authors | Yvan Lucas, Pierre-Edouard Portier, Léa Laporte, Olivier Caelen, Liyun He-Guelton, Sylvie Calabretto, Michael Granitzer |
| Abstract | Machine learning and data mining techniques have been used extensively in order to detect credit card frauds. However, most studies consider credit card transactions as isolated events and not as a sequence of transactions. In this article, we model a sequence of credit card transactions from three different perspectives, namely (i) does the sequence contain a Fraud? (ii) Is the sequence obtained by fixing the card-holder or the payment terminal? (iii) Is it a sequence of spent amount or of elapsed time between the current and previous transactions? Combinations of the three binary perspectives give eight sets of sequences from the (training) set of transactions. Each one of these sets is modelled with a Hidden Markov Model (HMM). Each HMM associates a likelihood to a transaction given its sequence of previous transactions. These likelihoods are used as additional features in a Random Forest classifier for fraud detection. This multiple perspectives HMM-based approach enables an automatic feature engineering in order to model the sequential properties of the dataset with respect to the classification task. This strategy allows for a 15% increase in the precision-recall AUC compared to the state of the art feature engineering strategy for credit card fraud detection. |
| Tasks | Feature Engineering, Fraud Detection |
| Published | 2019-05-15 |
| URL | https://arxiv.org/abs/1905.06247v1 |
| https://arxiv.org/pdf/1905.06247v1.pdf | |
| PWC | https://paperswithcode.com/paper/multiple-perspectives-hmm-based-feature |
| Repo | |
| Framework | |
Towards Scalable, Efficient and Accurate Deep Spiking Neural Networks with Backward Residual Connections, Stochastic Softmax and Hybridization
| Title | Towards Scalable, Efficient and Accurate Deep Spiking Neural Networks with Backward Residual Connections, Stochastic Softmax and Hybridization |
| Authors | Priyadarshini Panda, Aparna Aketi, Kaushik Roy |
| Abstract | Spiking Neural Networks (SNNs) may offer an energy-efficient alternative for implementing deep learning applications. In recent years, there have been several proposals focused on supervised (conversion, spike-based gradient descent) and unsupervised (spike timing dependent plasticity) training methods to improve the accuracy of SNNs on large-scale tasks. However, each of these methods suffer from scalability, latency and accuracy limitations. In this paper, we propose novel algorithmic techniques of modifying the SNN configuration with backward residual connections, stochastic softmax and hybrid artificial-and-spiking neuronal activations to improve the learning ability of the training methodologies to yield competitive accuracy, while, yielding large efficiency gains over their artificial counterparts. Note, artificial counterparts refer to conventional deep learning/artificial neural networks. Our techniques apply to VGG/Residual architectures, and are compatible with all forms of training methodologies. Our analysis reveals that the proposed solutions yield near state-of-the-art accuracy with significant energy-efficiency and reduced parameter overhead translating to hardware improvements on complex visual recognition tasks, such as, CIFAR10, Imagenet datatsets. |
| Tasks | |
| Published | 2019-10-30 |
| URL | https://arxiv.org/abs/1910.13931v1 |
| https://arxiv.org/pdf/1910.13931v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-scalable-efficient-and-accurate-deep |
| Repo | |
| Framework | |
Implicit Kernel Learning
| Title | Implicit Kernel Learning |
| Authors | Chun-Liang Li, Wei-Cheng Chang, Youssef Mroueh, Yiming Yang, Barnabás Póczos |
| Abstract | Kernels are powerful and versatile tools in machine learning and statistics. Although the notion of universal kernels and characteristic kernels has been studied, kernel selection still greatly influences the empirical performance. While learning the kernel in a data driven way has been investigated, in this paper we explore learning the spectral distribution of kernel via implicit generative models parametrized by deep neural networks. We called our method Implicit Kernel Learning (IKL). The proposed framework is simple to train and inference is performed via sampling random Fourier features. We investigate two applications of the proposed IKL as examples, including generative adversarial networks with MMD (MMD GAN) and standard supervised learning. Empirically, MMD GAN with IKL outperforms vanilla predefined kernels on both image and text generation benchmarks; using IKL with Random Kitchen Sinks also leads to substantial improvement over existing state-of-the-art kernel learning algorithms on popular supervised learning benchmarks. Theory and conditions for using IKL in both applications are also studied as well as connections to previous state-of-the-art methods. |
| Tasks | Text Generation |
| Published | 2019-02-26 |
| URL | http://arxiv.org/abs/1902.10214v1 |
| http://arxiv.org/pdf/1902.10214v1.pdf | |
| PWC | https://paperswithcode.com/paper/implicit-kernel-learning |
| Repo | |
| Framework | |
Fake News Early Detection: A Theory-driven Model
| Title | Fake News Early Detection: A Theory-driven Model |
| Authors | Xinyi Zhou, Atishay Jain, Vir V. Phoha, Reza Zafarani |
| Abstract | The explosive growth of fake news and its erosion of democracy, justice, and public trust has significantly increased the demand for accurate fake news detection. Recent advancements in this area have proposed novel techniques that aim to detect fake news by exploring how it propagates on social networks. However, to achieve fake news early detection, one is only provided with limited to no information on news propagation; hence, motivating the need to develop approaches that can detect fake news by focusing mainly on news content. In this paper, a theory-driven model is proposed for fake news detection. The method investigates news content at various levels: lexicon-level, syntax-level, semantic-level and discourse-level. We represent news at each level, relying on well-established theories in social and forensic psychology. Fake news detection is then conducted within a supervised machine learning framework. As an interdisciplinary research, our work explores potential fake news patterns, enhances the interpretability in fake news feature engineering, and studies the relationships among fake news, deception/disinformation, and clickbaits. Experiments conducted on two real-world datasets indicate that the proposed method can outperform the state-of-the-art and enable fake news early detection, even when there is limited content information. |
| Tasks | Fake News Detection, Feature Engineering |
| Published | 2019-04-26 |
| URL | http://arxiv.org/abs/1904.11679v1 |
| http://arxiv.org/pdf/1904.11679v1.pdf | |
| PWC | https://paperswithcode.com/paper/fake-news-early-detection-a-theory-driven |
| Repo | |
| Framework | |
You Only Recognize Once: Towards Fast Video Text Spotting
| Title | You Only Recognize Once: Towards Fast Video Text Spotting |
| Authors | Zhanzhan Cheng, Jing Lu, Yi Niu, Shiliang Pu, Fei Wu, Shuigeng Zhou |
| Abstract | Video text spotting is still an important research topic due to its various real-applications. Previous approaches usually fall into the four-staged pipeline: text detection in individual images, framewisely recognizing localized text regions, tracking text streams and generating final results with complicated post-processing skills, which might suffer from the huge computational cost as well as the interferences of low-quality text. In this paper, we propose a fast and robust video text spotting framework by only recognizing the localized text one-time instead of frame-wisely recognition. Specifically, we first obtain text regions in videos with a well-designed spatial-temporal detector. Then we concentrate on developing a novel text recommender for selecting the highest-quality text from text streams and only recognizing the selected ones. Here, the recommender assembles text tracking, quality scoring and recognition into an end-to-end trainable module, which not only avoids the interferences from low-quality text but also dramatically speeds up the video text spotting process. In addition, we collect a larger scale video text dataset (LSVTD) for promoting the video text spotting community, which contains 100 text videos from 22 different real-life scenarios. Extensive experiments on two public benchmarks show that our method greatly speeds up the recognition process averagely by 71 times compared with the frame-wise manner, and also achieves the remarkable state-of-the-art. |
| Tasks | Text Spotting |
| Published | 2019-03-08 |
| URL | https://arxiv.org/abs/1903.03299v2 |
| https://arxiv.org/pdf/1903.03299v2.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-video-scene-text-spotting-unifying |
| Repo | |
| Framework | |
Continuous Graph Flow
| Title | Continuous Graph Flow |
| Authors | Zhiwei Deng, Megha Nawhal, Lili Meng, Greg Mori |
| Abstract | In this paper, we propose Continuous Graph Flow, a generative continuous flow based method that aims to model complex distributions of graph-structured data. Once learned, the model can be applied to an arbitrary graph, defining a probability density over the random variables represented by the graph. It is formulated as an ordinary differential equation system with shared and reusable functions that operate over the graphs. This leads to a new type of neural graph message passing scheme that performs continuous message passing over time. This class of models offers several advantages: a flexible representation that can generalize to variable data dimensions; ability to model dependencies in complex data distributions; reversible and memory-efficient; and exact and efficient computation of the likelihood of the data. We demonstrate the effectiveness of our model on a diverse set of generation tasks across different domains: graph generation, image puzzle generation, and layout generation from scene graphs. Our proposed model achieves significantly better performance compared to state-of-the-art models. |
| Tasks | Density Estimation, Graph Generation |
| Published | 2019-08-07 |
| URL | https://arxiv.org/abs/1908.02436v2 |
| https://arxiv.org/pdf/1908.02436v2.pdf | |
| PWC | https://paperswithcode.com/paper/continuous-graph-flow-for-flexible-density |
| Repo | |
| Framework | |
Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training
| Title | Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training |
| Authors | Gen Li, Nan Duan, Yuejian Fang, Ming Gong, Daxin Jiang, Ming Zhou |
| Abstract | We propose Unicoder-VL, a universal encoder that aims to learn joint representations of vision and language in a pre-training manner. Borrow ideas from cross-lingual pre-trained models, such as XLM and Unicoder, both visual and linguistic contents are fed into a multi-layer Transformer for the cross-modal pre-training, where three pre-trained tasks are employed, including Masked Language Modeling (MLM), Masked Object Classification (MOC) and Visual-linguistic Matching (VLM). The first two tasks learn context-aware representations for input tokens based on linguistic and visual contents jointly. The last task tries to predict whether an image and a text describe each other. After pretraining on large-scale image-caption pairs, we transfer Unicoder-VL to caption-based image-text retrieval and visual commonsense reasoning, with just one additional output layer. We achieve state-of-the-art or comparable results on both two tasks and show the powerful ability of the cross-modal pre-training. |
| Tasks | Language Modelling, Object Classification, Visual Commonsense Reasoning |
| Published | 2019-08-16 |
| URL | https://arxiv.org/abs/1908.06066v3 |
| https://arxiv.org/pdf/1908.06066v3.pdf | |
| PWC | https://paperswithcode.com/paper/unicoder-vl-a-universal-encoder-for-vision |
| Repo | |
| Framework | |
Topic subject creation using unsupervised learning for topic modeling
| Title | Topic subject creation using unsupervised learning for topic modeling |
| Authors | Rashid Mehdiyev, Jean Nava, Karan Sodhi, Saurav Acharya, Annie Ibrahim Rana |
| Abstract | We describe the use of Non-Negative Matrix Factorization (NMF) and Latent Dirichlet Allocation (LDA) algorithms to perform topic mining and labelling applied to retail customer communications in attempt to characterize the subject of customers inquiries. In this paper we compare both algorithms in the topic mining performance and propose methods to assign topic subject labels in an automated way. |
| Tasks | |
| Published | 2019-12-18 |
| URL | https://arxiv.org/abs/1912.08868v1 |
| https://arxiv.org/pdf/1912.08868v1.pdf | |
| PWC | https://paperswithcode.com/paper/topic-subject-creation-using-unsupervised |
| Repo | |
| Framework | |
