Paper Group NAWR 24
Seeing Deeply and Bidirectionally: A Deep Learning Approach for Single Image Reflection Removal. Ultra Large-Scale Feature Selection using Count-Sketches. DICOD: Distributed Convolutional Coordinate Descent for Convolutional Sparse Coding. Multimodal Lexical Translation. Nonconvex Optimization for Regression with Fairness Constraints. Conversationa …
Seeing Deeply and Bidirectionally: A Deep Learning Approach for Single Image Reflection Removal
| Title | Seeing Deeply and Bidirectionally: A Deep Learning Approach for Single Image Reflection Removal |
| Authors | Jie Yang, Dong Gong, Lingqiao Liu, Qinfeng Shi |
| Abstract | Reflections often obstruct the desired scene when taking photos through glass panels. Removing unwanted reflection automatically from the photos is highly desirable. Traditional methods often impose certain priors or assumptions to target particular type(s) of reflection such as shifted double reflection, thus have difficulty to generalise to other types. Very recently a deep learning approach has been proposed. It learns a deep neural network that directly maps a reflection contaminated image to a background (target) image (ie reflection free image) in an end to end fashion, and outperforms the previous methods. We argue that, to remove reflection truly well, we should estimate the reflection and utilise it to estimate the background image. We propose a cascade deep neural network, which estimates both the background image and the reflection. This significantly improves reflection removal. In the cascade deep network, we use the estimated background image to estimate the reflection, and then use the estimated reflection to estimate the background image, facilitating our idea of seeing deeply and bidirectionally. |
| Tasks | |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Jie_Yang_Seeing_Deeply_and_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Jie_Yang_Seeing_Deeply_and_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/seeing-deeply-and-bidirectionally-a-deep |
| Repo | https://github.com/yangj1e/bdn-refremv |
| Framework | pytorch |
Ultra Large-Scale Feature Selection using Count-Sketches
| Title | Ultra Large-Scale Feature Selection using Count-Sketches |
| Authors | Amirali Aghazadeh, Ryan Spring, Daniel Lejeune, Gautam Dasarathy, Anshumali Shrivastava, baraniuk |
| Abstract | Feature selection is an important challenge in machine learning. It plays a crucial role in the explainability of machine-driven decisions that are rapidly permeating throughout modern society. Unfortunately, the explosion in the size and dimensionality of real-world datasets poses a severe challenge to standard feature selection algorithms. Today, it is not uncommon for datasets to have billions of dimensions. At such scale, even storing the feature vector is impossible, causing most existing feature selection methods to fail. Workarounds like feature hashing, a standard approach to large-scale machine learning, helps with the computational feasibility, but at the cost of losing the interpretability of features. In this paper, we present MISSION, a novel framework for ultra large-scale feature selection that performs stochastic gradient descent while maintaining an efficient representation of the features in memory using a Count-Sketch data structure. MISSION retains the simplicity of feature hashing without sacrificing the interpretability of the features while using only O(log^2(p)) working memory. We demonstrate that MISSION accurately and efficiently performs feature selection on real-world, large-scale datasets with billions of dimensions. |
| Tasks | Feature Selection |
| Published | 2018-07-01 |
| URL | https://icml.cc/Conferences/2018/Schedule?showEvent=2249 |
| http://proceedings.mlr.press/v80/aghazadeh18a/aghazadeh18a.pdf | |
| PWC | https://paperswithcode.com/paper/ultra-large-scale-feature-selection-using |
| Repo | https://github.com/rdspring1/MISSION |
| Framework | none |
DICOD: Distributed Convolutional Coordinate Descent for Convolutional Sparse Coding
| Title | DICOD: Distributed Convolutional Coordinate Descent for Convolutional Sparse Coding |
| Authors | Thomas Moreau, Laurent Oudre, Nicolas Vayatis |
| Abstract | In this paper, we introduce DICOD, a convolutional sparse coding algorithm which builds shift invariant representations for long signals. This algorithm is designed to run in a distributed setting, with local message passing, making it communication efficient. It is based on coordinate descent and uses locally greedy updates which accelerate the resolution compared to greedy coordinate selection. We prove the convergence of this algorithm and highlight its computational speed-up which is super-linear in the number of cores used. We also provide empirical evidence for the acceleration properties of our algorithm compared to state-of-the-art methods. |
| Tasks | |
| Published | 2018-07-01 |
| URL | https://icml.cc/Conferences/2018/Schedule?showEvent=1904 |
| http://proceedings.mlr.press/v80/moreau18a/moreau18a.pdf | |
| PWC | https://paperswithcode.com/paper/dicod-distributed-convolutional-coordinate |
| Repo | https://github.com/tomMoral/dicod |
| Framework | none |
Multimodal Lexical Translation
| Title | Multimodal Lexical Translation |
| Authors | Chiraag Lala, Lucia Specia |
| Abstract | |
| Tasks | Machine Translation, Multimodal Machine Translation, Word Alignment, Word Sense Disambiguation |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1602/ |
| https://www.aclweb.org/anthology/L18-1602 | |
| PWC | https://paperswithcode.com/paper/multimodal-lexical-translation |
| Repo | https://github.com/sheffieldnlp/mlt |
| Framework | none |
Nonconvex Optimization for Regression with Fairness Constraints
| Title | Nonconvex Optimization for Regression with Fairness Constraints |
| Authors | Junpei Komiyama, Akiko Takeda, Junya Honda, Hajime Shimao |
| Abstract | The unfairness of a regressor is evaluated by measuring the correlation between the estimator and the sensitive attribute (e.g., race, gender, age), and the coefficient of determination (CoD) is a natural extension of the correlation coefficient when more than one sensitive attribute exists. As is well known, there is a trade-off between fairness and accuracy of a regressor, which implies a perfectly fair optimizer does not always yield a useful prediction. Taking this into consideration, we optimize the accuracy of the estimation subject to a user-defined level of fairness. However, a fairness level as a constraint induces a nonconvexity of the feasible region, which disables the use of an off-the-shelf convex optimizer. Despite such nonconvexity, we show an exact solution is available by using tools of global optimization theory. Furthermore, we propose a nonlinear extension of the method by kernel representation. Unlike most of existing fairness-aware machine learning methods, our method allows us to deal with numeric and multiple sensitive attributes. |
| Tasks | |
| Published | 2018-07-01 |
| URL | https://icml.cc/Conferences/2018/Schedule?showEvent=2037 |
| http://proceedings.mlr.press/v80/komiyama18a/komiyama18a.pdf | |
| PWC | https://paperswithcode.com/paper/nonconvex-optimization-for-regression-with |
| Repo | https://github.com/jkomiyama/fairregresion |
| Framework | none |
Conversational Memory Network for Emotion Recognition in Dyadic Dialogue Videos
| Title | Conversational Memory Network for Emotion Recognition in Dyadic Dialogue Videos |
| Authors | Devamanyu Hazarika, Soujanya Poria, Amir Zadeh, Erik Cambria, Louis-Philippe Morency, Roger Zimmermann |
| Abstract | Emotion recognition in conversations is crucial for the development of empathetic machines. Present methods mostly ignore the role of inter-speaker dependency relations while classifying emotions in conversations. In this paper, we address recognizing utterance-level emotions in dyadic conversational videos. We propose a deep neural framework, termed Conversational Memory Network (CMN), which leverages contextual information from the conversation history. In particular, CMN uses multimodal approach comprising audio, visual and textual features with gated recurrent units to model past utterances of each speaker into memories. These memories are then merged using attention-based hops to capture inter-speaker dependencies. Experiments show a significant improvement of 3 − 4{%} in accuracy over the state of the art. |
| Tasks | Emotion Recognition, Emotion Recognition in Context, Emotion Recognition in Conversation, Opinion Mining |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-1193/ |
| https://www.aclweb.org/anthology/N18-1193 | |
| PWC | https://paperswithcode.com/paper/conversational-memory-network-for-emotion |
| Repo | https://github.com/SenticNet/conv-emotion |
| Framework | pytorch |
Exploiting temporal information for 3D human pose estimation
| Title | Exploiting temporal information for 3D human pose estimation |
| Authors | Mir Rayat Imtiaz Hossain, James J. Little |
| Abstract | In this work, we address the problem of 3D human pose estimation from a sequence of 2D human poses. Although the recent success of deep networks has led many state-of-the-art methods for 3D pose estimation to train deep networks end-to-end to predict from images directly, the top-performing approaches have shown the effectiveness of dividing the task of 3D pose estimation into two steps: using a state-of-the-art 2D pose estimator to estimate the 2D pose from images and then mapping them into 3D space. They also showed that a low-dimensional representation like 2D locations of a set of joints can be discriminative enough to estimate 3D pose with high accuracy. However, estimation of 3D pose for individual frames leads to temporally incoherent estimates due to independent error in each frame causing jitter. Therefore, in this work we utilize the temporal information across a sequence of 2D joint locations to estimate a sequence of 3D poses. We designed a sequence-to-sequence network composed of layer-normalized LSTM units with shortcut connections connecting the input to the output on the decoder side and imposed temporal smoothness constraint during training. We found that the knowledge of temporal consistency improves the best reported result on Human3.6M dataset by approximately $12.2%$ and helps our network to recover temporally consistent 3D poses over a sequence of images even when the 2D pose detector fails. |
| Tasks | 3D Human Pose Estimation, 3D Pose Estimation, Pose Estimation |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Mir_Rayat_Imtiaz_Hossain_Exploiting_temporal_information_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Mir_Rayat_Imtiaz_Hossain_Exploiting_temporal_information_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/exploiting-temporal-information-for-3d-human |
| Repo | https://github.com/rayat137/Pose_3D |
| Framework | tf |
Discriminating between Lexico-Semantic Relations with the Specialization Tensor Model
| Title | Discriminating between Lexico-Semantic Relations with the Specialization Tensor Model |
| Authors | Goran Glava{\v{s}}, Ivan Vuli{'c} |
| Abstract | We present a simple and effective feed-forward neural architecture for discriminating between lexico-semantic relations (synonymy, antonymy, hypernymy, and meronymy). Our Specialization Tensor Model (STM) simultaneously produces multiple different specializations of input distributional word vectors, tailored for predicting lexico-semantic relations for word pairs. STM outperforms more complex state-of-the-art architectures on two benchmark datasets and exhibits stable performance across languages. We also show that, if coupled with a bilingual distributional space, the proposed model can transfer the prediction of lexico-semantic relations to a resource-lean target language without any training data. |
| Tasks | Natural Language Inference, Paraphrase Generation, Text Simplification, Word Embeddings |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-2029/ |
| https://www.aclweb.org/anthology/N18-2029 | |
| PWC | https://paperswithcode.com/paper/discriminating-between-lexico-semantic |
| Repo | https://github.com/codogogo/stm |
| Framework | tf |
Machine Learning and Blockchain for Fraud Detection: Employing Artificial Intelligence in the Banking Sector
| Title | Machine Learning and Blockchain for Fraud Detection: Employing Artificial Intelligence in the Banking Sector |
| Authors | Vinita Silaparasetty |
| Abstract | Fraudulent banking operations can cause huge losses to the bank and further affect the economy negatively. What if Blockchain Technology and Machine Learning could be combined to detect suspicious banking activity and stop transactions at the source? That is what this paper aims to do. In this paper, a system is created which consists of a the following components: 1) Blockchain: To securely store transaction history. 2) XGBoosted KMenas algorithm: For quick and efficient detection of outliers, which indicate suspicious activity. 3) Apache Ignite: This is an open source platform that provides powerful computing for real-time Machine Learning. Key words: Artificial Intelligence, Machine Learning, Data Science, Algorithm, Blockchain, Means, Apache. |
| Tasks | Fraud Detection |
| Published | 2018-06-18 |
| URL | https://www.academia.edu/40207849/Machine_Learning_and_Blockchain_for_Fraud_Detection_Employing_Artificial_Intelligence_in_the_Banking_Sector |
| https://www.academia.edu/40207849/Machine_Learning_and_Blockchain_for_Fraud_Detection_Employing_Artificial_Intelligence_in_the_Banking_Sector | |
| PWC | https://paperswithcode.com/paper/machine-learning-and-blockchain-for-fraud |
| Repo | https://github.com/VinitaSilaparasetty/Blockchain-ml |
| Framework | none |
Learning filter widths of spectral decompositions with wavelets
| Title | Learning filter widths of spectral decompositions with wavelets |
| Authors | Haidar Khan, Bulent Yener |
| Abstract | Time series classification using deep neural networks, such as convolutional neural networks (CNN), operate on the spectral decomposition of the time series computed using a preprocessing step. This step can include a large number of hyperparameters, such as window length, filter widths, and filter shapes, each with a range of possible values that must be chosen using time and data intensive cross-validation procedures. We propose the wavelet deconvolution (WD) layer as an efficient alternative to this preprocessing step that eliminates a significant number of hyperparameters. The WD layer uses wavelet functions with adjustable scale parameters to learn the spectral decomposition directly from the signal. Using backpropagation, we show the scale parameters can be optimized with gradient descent. Furthermore, the WD layer adds interpretability to the learned time series classifier by exploiting the properties of the wavelet transform. In our experiments, we show that the WD layer can automatically extract the frequency content used to generate a dataset. The WD layer combined with a CNN applied to the phone recognition task on the TIMIT database achieves a phone error rate of 18.1%, a relative improvement of 4% over the baseline CNN. Experiments on a dataset where engineered features are not available showed WD+CNN is the best performing method. Our results show that the WD layer can improve neural network based time series classifiers both in accuracy and interpretability by learning directly from the input signal. |
| Tasks | Time Series, Time Series Classification |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7711-learning-filter-widths-of-spectral-decompositions-with-wavelets |
| http://papers.nips.cc/paper/7711-learning-filter-widths-of-spectral-decompositions-with-wavelets.pdf | |
| PWC | https://paperswithcode.com/paper/learning-filter-widths-of-spectral |
| Repo | https://github.com/haidark/WaveletDeconv |
| Framework | tf |
Large-scale Exploration of Neural Relation Classification Architectures
| Title | Large-scale Exploration of Neural Relation Classification Architectures |
| Authors | Hoang-Quynh Le, Duy-Cat Can, Sinh T. Vu, Thanh Hai Dang, Mohammad Taher Pilehvar, Nigel Collier |
| Abstract | Experimental performance on the task of relation classification has generally improved using deep neural network architectures. One major drawback of reported studies is that individual models have been evaluated on a very narrow range of datasets, raising questions about the adaptability of the architectures, while making comparisons between approaches difficult. In this work, we present a systematic large-scale analysis of neural relation classification architectures on six benchmark datasets with widely varying characteristics. We propose a novel multi-channel LSTM model combined with a CNN that takes advantage of all currently popular linguistic and architectural features. Our {`}Man for All Seasons{'} approach achieves state-of-the-art performance on two datasets. More importantly, in our view, the model allowed us to obtain direct insights into the continued challenges faced by neural language models on this task. | |
| Tasks | Question Answering, Relation Classification |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1250/ |
| https://www.aclweb.org/anthology/D18-1250 | |
| PWC | https://paperswithcode.com/paper/large-scale-exploration-of-neural-relation |
| Repo | https://github.com/catcd/MASS |
| Framework | tf |
WordKit: a Python Package for Orthographic and Phonological Featurization
| Title | WordKit: a Python Package for Orthographic and Phonological Featurization |
| Authors | St{'e}phan Tulkens, S, Dominiek ra, Walter Daelemans |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1427/ |
| https://www.aclweb.org/anthology/L18-1427 | |
| PWC | https://paperswithcode.com/paper/wordkit-a-python-package-for-orthographic-and |
| Repo | https://github.com/stephantul/wordkit |
| Framework | none |
A-Contrario Horizon-First Vanishing Point Detection Using Second-Order Grouping Laws
| Title | A-Contrario Horizon-First Vanishing Point Detection Using Second-Order Grouping Laws |
| Authors | Gilles Simon, Antoine Fond, Marie-Odile Berger |
| Abstract | We show that, in images of man-made environments, the horizon line can usually be hypothesized based on an a contrario detection of second-order grouping events. This allows constraining the extraction of the horizontal vanishing points on that line, thus reducing false detections. Experiments made on three datasets show that our method, not only achieves state-of-the-art performance w.r.t. horizon line detection on two datasets, but also yields much less spurious vanishing points than the previous top-ranked methods. |
| Tasks | Horizon Line Estimation |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Gilles_Simon_A_Contrario_Horizon-First_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Gilles_Simon_A_Contrario_Horizon-First_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/a-contrario-horizon-first-vanishing-point |
| Repo | https://github.com/alexvonduar/V |
| Framework | none |
A Compact Convolutional Neural Network for Textured Surface Anomaly Detection
| Title | A Compact Convolutional Neural Network for Textured Surface Anomaly Detection |
| Authors | Domen Racki, Dejan Tomazevic, Danijel Skocaj |
| Abstract | Convolutional neural methods have proven to outperform other approaches in various computer vision tasks. In this paper we apply the deep learning technique to the domain of automated visual surface inspection. We design a unified CNN-based framework for segmentation and detection of surface anomalies. We investigate whether a compact CNN architecture, which exhibit fewer parameters that need to be learned, can be used, while retaining high classification accuracy. We propose and evaluate a compact CNN architecture on a dataset consisting of diverse textured surfaces with variously-shaped weakly-labeled anomalies. The proposed approach achieves state-of-the-art results in terms of anomaly segmentation as well as classification. |
| Tasks | Anomaly Detection |
| Published | 2018-05-18 |
| URL | https://www.semanticscholar.org/paper/A-Compact-Convolutional-Neural-Network-for-Textured-Racki-Tomazevic/17d3f90cb63fbac50a5e49b8a46e633ec1f526fd#extracted |
| https://www.researchgate.net/publication/324997586_A_Compact_Convolutional_Neural_Network_for_Textured_Surface_Anomaly_Detection | |
| PWC | https://paperswithcode.com/paper/a-compact-convolutional-neural-network-for |
| Repo | https://github.com/msminhas93/CompactCNN |
| Framework | pytorch |
Low Cost Edge Sensing for High Quality Demosaicking
| Title | Low Cost Edge Sensing for High Quality Demosaicking |
| Authors | Yan Niu et al. |
| Abstract | Digital cameras that use color filter arrays (CFA) entail a demosaicking procedure to form full RGB images. To digital camera industry, demosaicking speed is as important as demosaicking accuracy, because camera users have been accustomed to viewing captured photos instantly. Moreover, the cost associated with demosaicking should not go beyond the cost saved by using CFA. For this purpose, we revisit the classical Hamilton-Adams (HA) algorithm, which outperforms many sophisticated techniques in both speed and accuracy. Our analysis shows that the HA pipeline is highly efficient to exploit the originally captured data, but its oversimplified inter- and intra-channel smoothness formulation hinder its accuracy. Therefore, we propose a very low cost edge sensing scheme, which guides demosaicking by a logistic functional of the difference between directional variations. We extensively compare our algorithm with 27 demosaicking algorithms by running their open source code on benchmark datasets. Compared with the methods of similar computational cost, our method achieves substantially higher accuracy, whereas compared with the methods of similar accuracy, our method has significantly lower cost. On test images of currently popular resolution, the quality of our algorithm is comparable to top performers, yet our speed is tens of times faster. |
| Tasks | Demosaicking |
| Published | 2018-11-28 |
| URL | https://ieeexplore.ieee.org/document/8550686 |
| https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8550686 | |
| PWC | https://paperswithcode.com/paper/low-cost-edge-sensing-for-high-quality-1 |
| Repo | https://github.com/shmilyo/Low-Cost-Edge-Sensing-for-High-Quality-Demosaicking |
| Framework | none |
