Paper Group ANR 729
Tracing State-Level Obesity Prevalence from Sentence Embeddings of Tweets: A Feasibility Study. Domain Agnostic Feature Learning for Image and Video Based Face Anti-spoofing. Learning from Irregularly Sampled Data for Endomicroscopy Super-resolution: A Comparative Study of Sparse and Dense Approaches. A new approach to forecast service parts demand …
Tracing State-Level Obesity Prevalence from Sentence Embeddings of Tweets: A Feasibility Study
| Title | Tracing State-Level Obesity Prevalence from Sentence Embeddings of Tweets: A Feasibility Study |
| Authors | Xiaoyi Zhang, Rodoniki Athanasiadou, Narges Razavian |
| Abstract | Twitter data has been shown broadly applicable for public health surveillance. Previous public health studies based on Twitter data have largely relied on keyword-matching or topic models for clustering relevant tweets. However, both methods suffer from the short-length of texts and unpredictable noise that naturally occurs in user-generated contexts. In response, we introduce a deep learning approach that uses hashtags as a form of supervision and learns tweet embeddings for extracting informative textual features. In this case study, we address the specific task of estimating state-level obesity from dietary-related textual features. Our approach yields an estimation that strongly correlates the textual features to government data and outperforms the keyword-matching baseline. The results also demonstrate the potential of discovering risk factors using the textual features. This method is general-purpose and can be applied to a wide range of Twitter-based public health studies. |
| Tasks | Sentence Embeddings, Topic Models |
| Published | 2019-11-26 |
| URL | https://arxiv.org/abs/1911.11324v2 |
| https://arxiv.org/pdf/1911.11324v2.pdf | |
| PWC | https://paperswithcode.com/paper/tracing-state-level-obesity-prevalence-from |
| Repo | |
| Framework | |
Domain Agnostic Feature Learning for Image and Video Based Face Anti-spoofing
| Title | Domain Agnostic Feature Learning for Image and Video Based Face Anti-spoofing |
| Authors | Suman Saha, Wenhao Xu, Menelaos Kanakis, Stamatios Georgoulis, Yuhua Chen, Danda Pani Paudel, Luc Van Gool |
| Abstract | Nowadays, the increasingly growing number of mobile and computing devices has led to a demand for safer user authentication systems. Face anti-spoofing is a measure towards this direction for bio-metric user authentication, and in particular face recognition, that tries to prevent spoof attacks. The state-of-the-art anti-spoofing techniques leverage the ability of deep neural networks to learn discriminative features, based on cues from the training set images or video samples, in an effort to detect spoof attacks. However, due to the particular nature of the problem, i.e. large variability due to factors like different backgrounds, lighting conditions, camera resolutions, spoof materials, etc., these techniques typically fail to generalize to new samples. In this paper, we explicitly tackle this problem and propose a class-conditional domain discriminator module, that, coupled with a gradient reversal layer, tries to generate live and spoof features that are discriminative, but at the same time robust against the aforementioned variability factors. Extensive experimental analysis shows the effectiveness of the proposed method over existing image- and video-based anti-spoofing techniques, both in terms of numerical improvement as well as when visualizing the learned features. |
| Tasks | Face Anti-Spoofing, Face Recognition |
| Published | 2019-12-15 |
| URL | https://arxiv.org/abs/1912.07124v1 |
| https://arxiv.org/pdf/1912.07124v1.pdf | |
| PWC | https://paperswithcode.com/paper/domain-agnostic-feature-learning-for-image |
| Repo | |
| Framework | |
Learning from Irregularly Sampled Data for Endomicroscopy Super-resolution: A Comparative Study of Sparse and Dense Approaches
| Title | Learning from Irregularly Sampled Data for Endomicroscopy Super-resolution: A Comparative Study of Sparse and Dense Approaches |
| Authors | Agnieszka Barbara Szczotka, Dzhoshkun Ismail Shakir, DanieleRavi, Matthew J. Clarkson, Stephen P. Pereira, Tom Vercauteren |
| Abstract | Purpose: Probe-based Confocal Laser Endomicroscopy (pCLE) enables performing an optical biopsy, providing real-time microscopic images, via a probe. pCLE probes consist of multiple optical fibres arranged in a bundle, which taken together generate signals in an irregularly sampled pattern. Current pCLE reconstruction is based on interpolating irregular signals onto an over-sampled Cartesian grid, using a naive linear interpolation. It was shown that Convolutional Neural Networks (CNNs) could improve pCLE image quality. Although classical CNNs were applied to pCLE, input data were limited to reconstructed images in contrast to irregular data produced by pCLE. Methods: We compare pCLE reconstruction and super-resolution (SR) methods taking irregularly sampled or reconstructed pCLE images as input. We also propose to embed a Nadaraya-Watson (NW) kernel regression into the CNN framework as a novel trainable CNN layer. Using the NW layer and exemplar-based super-resolution, we design an NWNetSR architecture that allows for reconstructing high-quality pCLE images directly from the irregularly sampled input data. We created synthetic sparse pCLE images to evaluate our methodology. Results: The results were validated through an image quality assessment based on a combination of the following metrics: Peak signal-to-noise ratio, the Structural Similarity Index. Conclusion: Both dense and sparse CNNs outperform the reconstruction method currently used in the clinic. The main contributions of our study are a comparison of sparse and dense approach in pCLE image reconstruction, implementing trainable generalised NW kernel regression, and adaptation of synthetic data for training pCLE SR. |
| Tasks | Image Quality Assessment, Image Reconstruction, Super-Resolution |
| Published | 2019-11-29 |
| URL | https://arxiv.org/abs/1911.13169v1 |
| https://arxiv.org/pdf/1911.13169v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-from-irregularly-sampled-data-for |
| Repo | |
| Framework | |
A new approach to forecast service parts demand by integrating user preferences into multi-objective optimization
| Title | A new approach to forecast service parts demand by integrating user preferences into multi-objective optimization |
| Authors | Wenli Ouyang |
| Abstract | Service supply chain management is to prepare spare parts for failed products under warranty. Their goal is to reach agreed service level at the minimum cost. We convert this business problem into a preference based multi-objective optimization problem, where two quality criteria must be simultaneously optimized. One criterion is accuracy of demand forecast and the other is service level. Here we propose a general framework supporting solving preference-based multi-objective optimization problems (MOPs) by multi-gradient descent algorithm (MGDA), which is well suited for training deep neural network. The proposed framework treats agreed service level as a constrained criterion that must be met and generate a Pareto-optimal solution with highest forecasting accuracy. The neural networks used here are two Encoder-Decoder LSTM modes: one is used for pre-training phase to learn distributed representation of former generations’ service parts consumption data, and the other is used for supervised learning phase to generate forecast quantities of current generations’ service parts. Evaluated under the service parts consumption data in Lenovo Group Ltd, the proposed method clearly outperform baseline methods. |
| Tasks | |
| Published | 2019-06-17 |
| URL | https://arxiv.org/abs/1906.06816v2 |
| https://arxiv.org/pdf/1906.06816v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-new-approach-to-forecasting-service-parts |
| Repo | |
| Framework | |
Extra Proximal-Gradient Inspired Non-local Network
| Title | Extra Proximal-Gradient Inspired Non-local Network |
| Authors | Qingchao Zhang, Yunmei Chen |
| Abstract | Variational method and deep learning method are two mainstream powerful approaches to solve inverse problems in computer vision. To take advantages of advanced optimization algorithms and powerful representation ability of deep neural networks, we propose a novel deep network for image reconstruction. The architecture of this network is inspired by our proposed accelerated extra proximal gradient algorithm. It is able to incorporate non-local operation to exploit the non-local self-similarity of the images and to learn the nonlinear transform, under which the solution is sparse. All the parameters in our network are learned from minimizing a loss function. Our experimental results show that our network outperforms several state-of-the-art deep networks with almost the same number of learnable parameter. |
| Tasks | Image Reconstruction |
| Published | 2019-11-17 |
| URL | https://arxiv.org/abs/1911.07144v1 |
| https://arxiv.org/pdf/1911.07144v1.pdf | |
| PWC | https://paperswithcode.com/paper/extra-proximal-gradient-inspired-non-local |
| Repo | |
| Framework | |
Deep Encoder-decoder Adversarial Reconstruction (DEAR) Network for 3D CT from Few-view Data
| Title | Deep Encoder-decoder Adversarial Reconstruction (DEAR) Network for 3D CT from Few-view Data |
| Authors | Huidong Xie, Hongming Shan, Ge Wang |
| Abstract | X-ray computed tomography (CT) is widely used in clinical practice. The involved ionizing X-ray radiation, however, could increase cancer risk. Hence, the reduction of the radiation dose has been an important topic in recent years. Few-view CT image reconstruction is one of the main ways to minimize radiation dose and potentially allow a stationary CT architecture. In this paper, we propose a deep encoder-decoder adversarial reconstruction (DEAR) network for 3D CT image reconstruction from few-view data. Since the artifacts caused by few-view reconstruction appear in 3D instead of 2D geometry, a 3D deep network has a great potential for improving the image quality in a data-driven fashion. More specifically, our proposed DEAR-3D network aims at reconstructing 3D volume directly from clinical 3D spiral cone-beam image data. DEAR is validated on a publicly available abdominal CT dataset prepared and authorized by Mayo Clinic. Compared with other 2D deep-learning methods, the proposed DEAR-3D network can utilize 3D information to produce promising reconstruction results. |
| Tasks | Computed Tomography (CT), Image Reconstruction |
| Published | 2019-11-13 |
| URL | https://arxiv.org/abs/1911.05880v2 |
| https://arxiv.org/pdf/1911.05880v2.pdf | |
| PWC | https://paperswithcode.com/paper/deep-encoder-decoder-adversarial |
| Repo | |
| Framework | |
Evolving Losses for Unlabeled Video Representation Learning
| Title | Evolving Losses for Unlabeled Video Representation Learning |
| Authors | AJ Piergiovanni, Anelia Angelova, Michael S. Ryoo |
| Abstract | We present a new method to learn video representations from unlabeled data. Given large-scale unlabeled video data, the objective is to benefit from such data by learning a generic and transferable representation space that can be directly used for a new task such as zero/few-shot learning. We formulate our unsupervised representation learning as a multi-modal, multi-task learning problem, where the representations are also shared across different modalities via distillation. Further, we also introduce the concept of finding a better loss function to train such multi-task multi-modal representation space using an evolutionary algorithm; our method automatically searches over different combinations of loss functions capturing multiple (self-supervised) tasks and modalities. Our formulation allows for the distillation of audio, optical flow and temporal information into a single, RGB-based convolutional neural network. We also compare the effects of using additional unlabeled video data and evaluate our representation learning on standard public video datasets. |
| Tasks | Few-Shot Learning, Multi-Task Learning, Optical Flow Estimation, Representation Learning, Unsupervised Representation Learning |
| Published | 2019-06-07 |
| URL | https://arxiv.org/abs/1906.03248v1 |
| https://arxiv.org/pdf/1906.03248v1.pdf | |
| PWC | https://paperswithcode.com/paper/evolving-losses-for-unlabeled-video |
| Repo | |
| Framework | |
CASIA-SURF: A Large-scale Multi-modal Benchmark for Face Anti-spoofing
| Title | CASIA-SURF: A Large-scale Multi-modal Benchmark for Face Anti-spoofing |
| Authors | Shifeng Zhang, Ajian Liu, Jun Wan, Yanyan Liang, Guogong Guo, Sergio Escalera, Hugo Jair Escalante, Stan Z. Li |
| Abstract | Face anti-spoofing is essential to prevent face recognition systems from a security breach. Much of the progresses have been made by the availability of face anti-spoofing benchmark datasets in recent years. However, existing face anti-spoofing benchmarks have limited number of subjects ($\le\negmedspace170$) and modalities ($\leq\negmedspace2$), which hinder the further development of the academic community. To facilitate face anti-spoofing research, we introduce a large-scale multi-modal dataset, namely CASIA-SURF, which is the largest publicly available dataset for face anti-spoofing in terms of both subjects and modalities. Specifically, it consists of $1,000$ subjects with $21,000$ videos and each sample has $3$ modalities (i.e., RGB, Depth and IR). We also provide comprehensive evaluation metrics, diverse evaluation protocols, training/validation/testing subsets and a measurement tool, developing a new benchmark for face anti-spoofing. Moreover, we present a novel multi-modal multi-scale fusion method as a strong baseline, which performs feature re-weighting to select the more informative channel features while suppressing the less useful ones for each modality across different scales. Extensive experiments have been conducted on the proposed dataset to verify its significance and generalization capability. The dataset is available at https://sites.google.com/qq.com/face-anti-spoofing/welcome/challengecvpr2019?authuser=0 |
| Tasks | Face Anti-Spoofing, Face Recognition |
| Published | 2019-08-28 |
| URL | https://arxiv.org/abs/1908.10654v2 |
| https://arxiv.org/pdf/1908.10654v2.pdf | |
| PWC | https://paperswithcode.com/paper/casia-surf-a-large-scale-multi-modal |
| Repo | |
| Framework | |
Summarizing Data Succinctly with the Most Informative Itemsets
| Title | Summarizing Data Succinctly with the Most Informative Itemsets |
| Authors | Michael Mampaey, Jilles Vreeken, Nikolaj Tatti |
| Abstract | Knowledge discovery from data is an inherently iterative process. That is, what we know about the data greatly determines our expectations, and therefore, what results we would find interesting and/or surprising. Given new knowledge about the data, our expectations will change. Hence, in order to avoid redundant results, knowledge discovery algorithms ideally should follow such an iterative updating procedure. With this in mind, we introduce a well-founded approach for succinctly summarizing data with the most informative itemsets; using a probabilistic maximum entropy model, we iteratively find the itemset that provides us the most novel information–that is, for which the frequency in the data surprises us the most—and in turn we update our model accordingly. As we use the Maximum Entropy principle to obtain unbiased probabilistic models, and only include those itemsets that are most informative with regard to the current model, the summaries we construct are guaranteed to be both descriptive and non-redundant. The algorithm that we present, called MTV, can either discover the top-$k$ most informative itemsets, or we can employ either the Bayesian Information Criterion (BIC) or the Minimum Description Length (MDL) principle to automatically identify the set of itemsets that together summarize the data well. In other words, our method will `tell you what you need to know’ about the data. Importantly, it is a one-phase algorithm: rather than picking itemsets from a user-provided candidate set, itemsets and their supports are mined on-the-fly. To further its applicability, we provide an efficient method to compute the maximum entropy distribution using Quick Inclusion-Exclusion. Experiments on our method, using synthetic, benchmark, and real data, show that the discovered summaries are succinct, and correctly identify the key patterns in the data. | |
| Tasks | |
| Published | 2019-04-25 |
| URL | http://arxiv.org/abs/1904.11134v2 |
| http://arxiv.org/pdf/1904.11134v2.pdf | |
| PWC | https://paperswithcode.com/paper/tell-me-what-i-need-to-know-succinctly |
| Repo | |
| Framework | |
Discrete and Continuous Deep Residual Learning Over Graphs
| Title | Discrete and Continuous Deep Residual Learning Over Graphs |
| Authors | Pedro H. C. Avelar, Anderson R. Tavares, Marco Gori, Luis C. Lamb |
| Abstract | In this paper we propose the use of continuous residual modules for graph kernels in Graph Neural Networks. We show how both discrete and continuous residual layers allow for more robust training, being that continuous residual layers are those which are applied by integrating through an Ordinary Differential Equation (ODE) solver to produce their output. We experimentally show that these residuals achieve better results than the ones with non-residual modules when multiple layers are used, mitigating the low-pass filtering effect of GCN-based models. Finally, we apply and analyse the behaviour of these techniques and give pointers to how this technique can be useful in other domains by allowing more predictable behaviour under dynamic times of computation. |
| Tasks | |
| Published | 2019-11-21 |
| URL | https://arxiv.org/abs/1911.09554v2 |
| https://arxiv.org/pdf/1911.09554v2.pdf | |
| PWC | https://paperswithcode.com/paper/discrete-and-continuous-deep-residual |
| Repo | |
| Framework | |
Measuring Compositional Generalization: A Comprehensive Method on Realistic Data
| Title | Measuring Compositional Generalization: A Comprehensive Method on Realistic Data |
| Authors | Daniel Keysers, Nathanael Schärli, Nathan Scales, Hylke Buisman, Daniel Furrer, Sergii Kashubin, Nikola Momchev, Danila Sinopalnikov, Lukasz Stafiniak, Tibor Tihon, Dmitry Tsarkov, Xiao Wang, Marc van Zee, Olivier Bousquet |
| Abstract | State-of-the-art machine learning methods exhibit limited compositional generalization. At the same time, there is a lack of realistic benchmarks that comprehensively measure this ability, which makes it challenging to find and evaluate improvements. We introduce a novel method to systematically construct such benchmarks by maximizing compound divergence while guaranteeing a small atom divergence between train and test sets, and we quantitatively compare this method to other approaches for creating compositional generalization benchmarks. We present a large and realistic natural language question answering dataset that is constructed according to this method, and we use it to analyze the compositional generalization ability of three machine learning architectures. We find that they fail to generalize compositionally and that there is a surprisingly strong negative correlation between compound divergence and accuracy. We also demonstrate how our method can be used to create new compositionality benchmarks on top of the existing SCAN dataset, which confirms these findings. |
| Tasks | Question Answering |
| Published | 2019-12-20 |
| URL | https://arxiv.org/abs/1912.09713v1 |
| https://arxiv.org/pdf/1912.09713v1.pdf | |
| PWC | https://paperswithcode.com/paper/measuring-compositional-generalization-a-1 |
| Repo | |
| Framework | |
The Analysis of Projective Transformation Algorithms for Image Recognition on Mobile Devices
| Title | The Analysis of Projective Transformation Algorithms for Image Recognition on Mobile Devices |
| Authors | Anton Trusov, Elena Limonova |
| Abstract | In this work we apply commonly known methods of non-adaptive interpolation (nearest pixel, bilinear, B-spline, bicubic, Hermite spline) and sampling (point sampling, supersampling, mip-map pre-filtering, rip-map pre-filtering and FAST) to the problem of projective image transformation. We compare their computational complexity, describe their artifacts and than experimentally measure their quality and working time on mobile processor with ARM architecture. Those methods were widely developed in the 90s and early 2000s, but were not in an area of active research in resent years due to a lower need in computationally efficient algorithms. However, real-time mobile recognition systems, which collect more and more attention, do not only require fast projective transform methods, but also demand high quality images without artifacts. As a result, in this work we choose methods appropriate for those systems, which allow to avoid artifacts, while preserving low computational complexity. Based on the experimental results for our setting they are bilinear interpolation combined with either mip-map pre-filtering or FAST sampling, but could be modified for specific use cases. |
| Tasks | |
| Published | 2019-12-03 |
| URL | https://arxiv.org/abs/1912.01401v1 |
| https://arxiv.org/pdf/1912.01401v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-analysis-of-projective-transformation |
| Repo | |
| Framework | |
Learning Multiple Markov Chains via Adaptive Allocation
| Title | Learning Multiple Markov Chains via Adaptive Allocation |
| Authors | Mohammad Sadegh Talebi, Odalric-Ambrym Maillard |
| Abstract | We study the problem of learning the transition matrices of a set of Markov chains from a single stream of observations on each chain. We assume that the Markov chains are ergodic but otherwise unknown. The learner can sample Markov chains sequentially to observe their states. The goal of the learner is to sequentially select various chains to learn transition matrices uniformly well with respect to some loss function. We introduce a notion of loss that naturally extends the squared loss for learning distributions to the case of Markov chains, and further characterize the notion of being \emph{uniformly good} in all problem instances. We present a novel learning algorithm that efficiently balances \emph{exploration} and \emph{exploitation} intrinsic to this problem, without any prior knowledge of the chains. We provide finite-sample PAC-type guarantees on the performance of the algorithm. Further, we show that our algorithm asymptotically attains an optimal loss. |
| Tasks | |
| Published | 2019-05-27 |
| URL | https://arxiv.org/abs/1905.11128v2 |
| https://arxiv.org/pdf/1905.11128v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-multiple-markov-chains-via-adaptive |
| Repo | |
| Framework | |
Tree pyramidal adaptive importance sampling
| Title | Tree pyramidal adaptive importance sampling |
| Authors | Javier Felip, Nilesh Ahuja, Omesh Tickoo |
| Abstract | This paper introduces Tree-Pyramidal Adaptive Importance Sampling (TP-AIS), a novel iterated sampling method that outperforms state-of-the-art approaches like deterministic mixture population Monte Carlo (DM-PMC), mixture population Monte Carlo (M-PMC) and layered adaptive importance sampling (LAIS). TP-AIS iteratively builds a proposal distribution parameterized by a tree pyramid, where each tree leaf spans a subspace that represents its importance density. After each new sample operation, a set of tree leaves are subdivided for improving the approximation of the proposal distribution to the target density. Unlike the rest of the methods in the literature, TP-AIS is parameter free and requires no tuning to achieve its best performance. We evaluate TP-AIS with different complexity randomized target probability density functions (PDF) and also analyze its application to different dimensions. The results are compared to state-of-the-art iterative importance sampling approaches and other baseline MCMC approaches using Normalized Effective Sample Size (N-ESS), Jensen-Shannon Divergence, and time complexity. |
| Tasks | |
| Published | 2019-12-18 |
| URL | https://arxiv.org/abs/1912.08434v2 |
| https://arxiv.org/pdf/1912.08434v2.pdf | |
| PWC | https://paperswithcode.com/paper/tree-pyramidal-adaptive-importance-sampling |
| Repo | |
| Framework | |
Enabling Open-World Specification Mining via Unsupervised Learning
| Title | Enabling Open-World Specification Mining via Unsupervised Learning |
| Authors | Jordan Henkel, Shuvendu K. Lahiri, Ben Liblit, Thomas Reps |
| Abstract | Many programming tasks require using both domain-specific code and well-established patterns (such as routines concerned with file IO). Together, several small patterns combine to create complex interactions. This compounding effect, mixed with domain-specific idiosyncrasies, creates a challenging environment for fully automatic specification inference. Mining specifications in this environment, without the aid of rule templates, user-directed feedback, or predefined API surfaces, is a major challenge. We call this challenge Open-World Specification Mining. In this paper, we present a framework for mining specifications and usage patterns in an Open-World setting. We design this framework to be miner-agnostic and instead focus on disentangling complex and noisy API interactions. To evaluate our framework, we introduce a benchmark of 71 clusters extracted from five open-source projects. Using this dataset, we show that interesting clusters can be recovered, in a fully automatic way, by leveraging unsupervised learning in the form of word embeddings. Once clusters have been recovered, the challenge of Open-World Specification Mining is simplified and any trace-based mining technique can be applied. In addition, we provide a comprehensive evaluation of three word-vector learners to showcase the value of sub-word information for embeddings learned in the software-engineering domain. |
| Tasks | Word Embeddings |
| Published | 2019-04-27 |
| URL | http://arxiv.org/abs/1904.12098v1 |
| http://arxiv.org/pdf/1904.12098v1.pdf | |
| PWC | https://paperswithcode.com/paper/enabling-open-world-specification-mining-via |
| Repo | |
| Framework | |
