January 29, 2020

2731 words 13 mins read

Paper Group ANR 718

Data-Efficient Mutual Information Neural Estimator. SHREWD: Semantic Hierarchy-based Relational Embeddings for Weakly-supervised Deep Hashing. Unsupervised Star Galaxy Classification with Cascade Variational Auto-Encoder. Multi-views Embedding for Cattle Re-identification. RODEO: Robust DE-aliasing autoencOder for Real-time Medical Image Reconstruc …

Data-Efficient Mutual Information Neural Estimator


Title	Data-Efficient Mutual Information Neural Estimator
Authors	Xiao Lin, Indranil Sur, Samuel A. Nastase, Ajay Divakaran, Uri Hasson, Mohamed R. Amer
Abstract	Measuring Mutual Information (MI) between high-dimensional, continuous, random variables from observed samples has wide theoretical and practical applications. Recent work, MINE (Belghazi et al. 2018), focused on estimating tight variational lower bounds of MI using neural networks, but assumed unlimited supply of samples to prevent overfitting. In real world applications, data is not always available at a surplus. In this work, we focus on improving data efficiency and propose a Data-Efficient MINE Estimator (DEMINE), by developing a relaxed predictive MI lower bound that can be estimated at higher data efficiency by orders of magnitudes. The predictive MI lower bound also enables us to develop a new meta-learning approach using task augmentation, Meta-DEMINE, to improve generalization of the network and further boost estimation accuracy empirically. With improved data-efficiency, our estimators enables statistical testing of dependency at practical dataset sizes. We demonstrate the effectiveness of our estimators on synthetic benchmarks and a real world fMRI data, with application of inter-subject correlation analysis.
Tasks	Meta-Learning
Published	2019-05-08
URL	https://arxiv.org/abs/1905.03319v2
PDF	https://arxiv.org/pdf/1905.03319v2.pdf
PWC	https://paperswithcode.com/paper/190503319
Repo
Framework

SHREWD: Semantic Hierarchy-based Relational Embeddings for Weakly-supervised Deep Hashing


Title	SHREWD: Semantic Hierarchy-based Relational Embeddings for Weakly-supervised Deep Hashing
Authors	Heikki Arponen, Tom E Bishop
Abstract	Using class labels to represent class similarity is a typical approach to training deep hashing systems for retrieval; samples from the same or different classes take binary 1 or 0 similarity values. This similarity does not model the full rich knowledge of semantic relations that may be present between data points. In this work we build upon the idea of using semantic hierarchies to form distance metrics between all available sample labels; for example cat to dog has a smaller distance than cat to guitar. We combine this type of semantic distance into a loss function to promote similar distances between the deep neural network embeddings. We also introduce an empirical Kullback-Leibler divergence loss term to promote binarization and uniformity of the embeddings. We test the resulting SHREWD method and demonstrate improvements in hierarchical retrieval scores using compact, binary hash codes instead of real valued ones, and show that in a weakly supervised hashing setting we are able to learn competitively without explicitly relying on class labels, but instead on similarities between labels.
Tasks
Published	2019-08-12
URL	https://arxiv.org/abs/1908.05602v1
PDF	https://arxiv.org/pdf/1908.05602v1.pdf
PWC	https://paperswithcode.com/paper/shrewd-semantic-hierarchy-based-relational
Repo
Framework

Unsupervised Star Galaxy Classification with Cascade Variational Auto-Encoder


Title	Unsupervised Star Galaxy Classification with Cascade Variational Auto-Encoder
Authors	Hao Sun, Jiadong Guo, Edward J. Kim, Robert J. Brunner
Abstract	The increasing amount of data in astronomy provides great challenges for machine learning research. Previously, supervised learning methods achieved satisfactory recognition accuracy for the star-galaxy classification task, based on manually labeled data set. In this work, we propose a novel unsupervised approach for the star-galaxy recognition task, namely Cascade Variational Auto-Encoder (CasVAE). Our empirical results show our method outperforms the baseline model in both accuracy and stability.
Tasks
Published	2019-10-30
URL	https://arxiv.org/abs/1910.14056v1
PDF	https://arxiv.org/pdf/1910.14056v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-star-galaxy-classification-with
Repo
Framework

Multi-views Embedding for Cattle Re-identification


Title	Multi-views Embedding for Cattle Re-identification
Authors	Luca Bergamini, Angelo Porrello, Andrea Capobianco Dondona, Ercole Del Negro, Mauro Mattioli, Nicola D’Alterio, Simone Calderara
Abstract	People re-identification task has seen enormous improvements in the latest years, mainly due to the development of better image features extraction from deep Convolutional Neural Networks (CNN) and the availability of large datasets. However, little research has been conducted on animal identification and re-identification, even if this knowledge may be useful in a rich variety of different scenarios. Here, we tackle cattle re-identification exploiting deep CNN and show how this task is poorly related with the human one, presenting unique challenges that makes it far from being solved. We present various baselines, both based on deep architectures or on standard machine learning algorithms, and compared them with our solution. Finally, a rich ablation study has been conducted to further investigate the unique peculiarities of this task.
Tasks
Published	2019-02-13
URL	http://arxiv.org/abs/1902.04886v1
PDF	http://arxiv.org/pdf/1902.04886v1.pdf
PWC	https://paperswithcode.com/paper/multi-views-embedding-for-cattle-re
Repo
Framework

RODEO: Robust DE-aliasing autoencOder for Real-time Medical Image Reconstruction


Title	RODEO: Robust DE-aliasing autoencOder for Real-time Medical Image Reconstruction
Authors	Janki Mehta, Angshul Majumdar
Abstract	In this work we address the problem of real-time dynamic medical MRI and X Ray CT image reconstruction from parsimonious samples Fourier frequency space for MRI and sinogram tomographic projections for CT. Today the de facto standard for such reconstruction is compressed sensing. CS produces high quality images (with minimal perceptual loss, but such reconstructions are time consuming, requiring solving a complex optimization problem. In this work we propose to learn the reconstruction from training samples using an autoencoder. Our work is based on the universal function approximation capacity of neural networks. The training time for the autoencoder is large, but is offline and hence does not affect performance during operation. During testing or operation, our method requires only a few matrix vector products and hence is significantly faster than CS based methods. In fact, it is fast enough for real-time reconstruction the images are reconstructed as fast as they are acquired with only slight degradation of image quality. However, in order to make the autoencoder suitable for our problem, we depart from the standard Euclidean norm cost function of autoencoders and use a robust l1-norm instead. The ensuing problem is solved using the Split Bregman method.
Tasks	De-aliasing, Image Reconstruction
Published	2019-12-11
URL	https://arxiv.org/abs/1912.07519v1
PDF	https://arxiv.org/pdf/1912.07519v1.pdf
PWC	https://paperswithcode.com/paper/rodeo-robust-de-aliasing-autoencoder-for-real
Repo
Framework

SDNet: Semantically Guided Depth Estimation Network


Title	SDNet: Semantically Guided Depth Estimation Network
Authors	Matthias Ochs, Adrian Kretz, Rudolf Mester
Abstract	Autonomous vehicles and robots require a full scene understanding of the environment to interact with it. Such a perception typically incorporates pixel-wise knowledge of the depths and semantic labels for each image from a video sensor. Recent learning-based methods estimate both types of information independently using two separate CNNs. In this paper, we propose a model that is able to predict both outputs simultaneously, which leads to improved results and even reduced computational costs compared to independent estimation of depth and semantics. We also empirically prove that the CNN is capable of learning more meaningful and semantically richer features. Furthermore, our SDNet estimates the depth based on ordinal classification. On the basis of these two enhancements, our proposed method achieves state-of-the-art results in semantic segmentation and depth estimation from single monocular input images on two challenging datasets.
Tasks	Autonomous Vehicles, Depth Estimation, Scene Understanding, Semantic Segmentation
Published	2019-07-24
URL	https://arxiv.org/abs/1907.10659v1
PDF	https://arxiv.org/pdf/1907.10659v1.pdf
PWC	https://paperswithcode.com/paper/sdnet-semantically-guided-depth-estimation
Repo
Framework

Attacking Power Indices by Manipulating Player Reliability


Title	Attacking Power Indices by Manipulating Player Reliability
Authors	Gabriel Istrate, Cosmin Bonchiş, Alin Brînduşescu
Abstract	We investigate the manipulation of power indices in TU-cooperative games by stimulating (subject to a budget constraint) changes in the propensity of other players to participate to the game. We display several algorithms that show that the problem is often tractable for so-called network centrality games and influence attribution games, as well as an example when optimal manipulation is intractable, even though computing power indices is feasible.
Tasks
Published	2019-03-04
URL	https://arxiv.org/abs/1903.01165v2
PDF	https://arxiv.org/pdf/1903.01165v2.pdf
PWC	https://paperswithcode.com/paper/attacking-power-indices-by-manipulating
Repo
Framework

Deep Generalization of Structured Low Rank Algorithms (Deep-SLR)


Title	Deep Generalization of Structured Low Rank Algorithms (Deep-SLR)
Authors	Aniket Pramanik, Hemant Aggarwal, Mathews Jacob
Abstract	Structured low-rank (SLR) algorithms are emerging as powerful image reconstruction approaches because they can capitalize on several signal properties, which conventional image-based approaches have difficulty in exploiting. The main challenge with this scheme that self learns an annihilation convolutional filterbank from the undersampled data is its high computational complexity. We introduce a deep-learning approach to quite significantly reduce the computational complexity of SLR schemes. Specifically, we pre-learn a CNN-based annihilation filterbank from exemplar data, which is used as a prior in a model-based reconstruction scheme. The CNN parameters are learned in an end-to-end fashion by un-rolling the iterative algorithm. The main difference of the proposed scheme with current model-based deep learning strategies is the learning of non-linear annihilation relations in Fourier space using a modelbased framework. The experimental comparisons show that the proposed scheme can offer similar performance as SLR schemes in the calibrationless parallel MRI setting, while reducing the run-time by around three orders of magnitude. We also combine the proposed scheme with image domain priors, which are complementary, thus further improving the performance over SLR schemes.
Tasks	Image Reconstruction
Published	2019-12-07
URL	https://arxiv.org/abs/1912.03433v1
PDF	https://arxiv.org/pdf/1912.03433v1.pdf
PWC	https://paperswithcode.com/paper/deep-generalization-of-structured-low-rank
Repo
Framework

Pyramid Convolutional RNN for MRI Reconstruction


Title	Pyramid Convolutional RNN for MRI Reconstruction
Authors	Puyang Wang, Eric Z. Chen, Terrence Chen, Vishal M. Patel, Shanhui Sun
Abstract	Fast and accurate MRI image reconstruction from undersampled data is critically important in clinical practice. Compressed sensing based methods are widely used in image reconstruction but the speed is slow due to the iterative algorithms. Deep learning based methods have shown promising advances in recent years. However, recovering the fine details from highly undersampled data is still challenging. In this paper, we introduce a novel deep learning-based method, Pyramid Convolutional RNN (PC-RNN), to reconstruct the image from multiple scales. We evaluated our model on the fastMRI dataset and the results show that the proposed model achieves significant improvements than other methods and can recover more fine details.
Tasks	Image Reconstruction
Published	2019-12-02
URL	https://arxiv.org/abs/1912.00543v4
PDF	https://arxiv.org/pdf/1912.00543v4.pdf
PWC	https://paperswithcode.com/paper/pyramid-convolutional-rnn-for-mri
Repo
Framework

RC-QED: Evaluating Natural Language Derivations in Multi-Hop Reading Comprehension


Title	RC-QED: Evaluating Natural Language Derivations in Multi-Hop Reading Comprehension
Authors	Naoya Inoue, Pontus Stenetorp, Kentaro Inui
Abstract	Recent studies revealed that reading comprehension (RC) systems learn to exploit annotation artifacts and other biases in current datasets. This allows systems to “cheat” by employing simple heuristics to answer questions, e.g. by relying on semantic type consistency. This means that current datasets are not well-suited to evaluate RC systems. To address this issue, we introduce RC-QED, a new RC task that requires giving not only the correct answer to a question, but also the reasoning employed for arriving at this answer. For this, we release a large benchmark dataset consisting of 12,000 answers and corresponding reasoning in form of natural language derivations. Experiments show that our benchmark is robust to simple heuristics and challenging for state-of-the-art neural path ranking approaches.
Tasks	Multi-Hop Reading Comprehension, Reading Comprehension
Published	2019-10-10
URL	https://arxiv.org/abs/1910.04601v1
PDF	https://arxiv.org/pdf/1910.04601v1.pdf
PWC	https://paperswithcode.com/paper/rc-qed-evaluating-natural-language
Repo
Framework

Bayesian Optimization with Directionally Constrained Search


Title	Bayesian Optimization with Directionally Constrained Search
Authors	Yang Li, Yaqiang Yao
Abstract	Bayesian optimization offers a flexible framework to optimize an objective function that is expensive to be evaluated. A Bayesian optimizer iteratively queries the function values on its carefully selected points. Subsequently, it makes a sensible recommendation about where the optimum locates based on its accumulated knowledge. This procedure usually demands a long execution time. In practice, however, there often exists a computational budget or an evaluation limitation allocated to an optimizer, due to the resource scarcity. This constraint demands an optimizer to be aware of its remaining budget and able to spend it wisely, in order to return as better a point as possible. In this paper, we propose a Bayesian optimization approach in this evaluation-limited scenario. Our approach is based on constraining searching directions so as to dedicate the model capability to the most promising area. It could be viewed as a combination of local and global searching policies, which aims at reducing inefficient exploration in the local searching areas, thus making a searching policy more efficient. Experimental studies are conducted on both synthetic and real-world applications. The results demonstrate the superior performance of our newly proposed approach in searching for the optimum within a prescribed evaluation budget.
Tasks
Published	2019-06-22
URL	https://arxiv.org/abs/1906.09459v1
PDF	https://arxiv.org/pdf/1906.09459v1.pdf
PWC	https://paperswithcode.com/paper/bayesian-optimization-with-directionally
Repo
Framework

Tensor Basis Gaussian Process Models of Hyperelastic Materials


Title	Tensor Basis Gaussian Process Models of Hyperelastic Materials
Authors	Ari Frankel, Reese Jones, Laura Swiler
Abstract	In this work, we develop Gaussian process regression (GPR) models of hyperelastic material behavior. First, we consider the direct approach of modeling the components of the Cauchy stress tensor as a function of the components of the Finger stretch tensor in a Gaussian process. We then consider an improvement on this approach that embeds rotational invariance of the stress-stretch constitutive relation in the GPR representation. This approach requires fewer training examples and achieves higher accuracy while maintaining invariance to rotations exactly. Finally, we consider an approach that recovers the strain-energy density function and derives the stress tensor from this potential. Although the error of this model for predicting the stress tensor is higher, the strain-energy density is recovered with high accuracy from limited training data. The approaches presented here are examples of physics-informed machine learning. They go beyond purely data-driven approaches by embedding the physical system constraints directly into the Gaussian process representation of materials models.
Tasks
Published	2019-12-23
URL	https://arxiv.org/abs/1912.10872v1
PDF	https://arxiv.org/pdf/1912.10872v1.pdf
PWC	https://paperswithcode.com/paper/tensor-basis-gaussian-process-models-of
Repo
Framework

Improving Neural Machine Translation Robustness via Data Augmentation: Beyond Back Translation


Title	Improving Neural Machine Translation Robustness via Data Augmentation: Beyond Back Translation
Authors	Zhenhao Li, Lucia Specia
Abstract	Neural Machine Translation (NMT) models have been proved strong when translating clean texts, but they are very sensitive to noise in the input. Improving NMT models robustness can be seen as a form of “domain” adaption to noise. The recently created Machine Translation on Noisy Text task corpus provides noisy-clean parallel data for a few language pairs, but this data is very limited in size and diversity. The state-of-the-art approaches are heavily dependent on large volumes of back-translated data. This paper has two main contributions: Firstly, we propose new data augmentation methods to extend limited noisy data and further improve NMT robustness to noise while keeping the models small. Secondly, we explore the effect of utilizing noise from external data in the form of speech transcripts and show that it could help robustness.
Tasks	Data Augmentation, Domain Adaptation, Machine Translation
Published	2019-10-07
URL	https://arxiv.org/abs/1910.03009v3
PDF	https://arxiv.org/pdf/1910.03009v3.pdf
PWC	https://paperswithcode.com/paper/improving-neural-machine-translation
Repo
Framework

A Framework for App Store Optimization


Title	A Framework for App Store Optimization
Authors	Artur Strzelecki
Abstract	In this paper a framework for app store optimization is proposed. The framework is based on two main areas: developer dependent elements and user dependent elements. Developer dependent elements are similar factors in search engine optimization. User dependent elements are similar to activities in social media. The proposed framework is modelled after downloading sample data from two leading app stores: Google Play and Apple iTunes. Results show that developer dependent elements can be better optimized. Names and descriptions of mobile apps are not fully utilized.
Tasks
Published	2019-05-28
URL	https://arxiv.org/abs/1905.11668v1
PDF	https://arxiv.org/pdf/1905.11668v1.pdf
PWC	https://paperswithcode.com/paper/a-framework-for-app-store-optimization
Repo
Framework

Training Multiscale-CNN for Large Microscopy Image Classification in One Hour


Title	Training Multiscale-CNN for Large Microscopy Image Classification in One Hour
Authors	Kushal Datta, Imtiaz Hossain, Sun Choi, Vikram Saletore, Kyle Ambert, William J. Godinez, Xian Zhang
Abstract	Existing approaches to train neural networks that use large images require to either crop or down-sample data during pre-processing, use small batch sizes, or split the model across devices mainly due to the prohibitively limited memory capacity available on GPUs and emerging accelerators. These techniques often lead to longer time to convergence or time to train (TTT), and in some cases, lower model accuracy. CPUs, on the other hand, can leverage significant amounts of memory. While much work has been done on parallelizing neural network training on multiple CPUs, little attention has been given to tune neural network training with large images on CPUs. In this work, we train a multi-scale convolutional neural network (M-CNN) to classify large biomedical images for high content screening in one hour. The ability to leverage large memory capacity on CPUs enables us to scale to larger batch sizes without having to crop or down-sample the input images. In conjunction with large batch sizes, we find a generalized methodology of linearly scaling of learning rate and train M-CNN to state-of-the-art (SOTA) accuracy of 99% within one hour. We achieve fast time to convergence using 128 two socket Intel Xeon 6148 processor nodes with 192GB DDR4 memory connected with 100Gbps Intel Omnipath architecture.
Tasks	Image Classification
Published	2019-10-03
URL	https://arxiv.org/abs/1910.04852v2
PDF	https://arxiv.org/pdf/1910.04852v2.pdf
PWC	https://paperswithcode.com/paper/training-multiscale-cnn-for-large-microscopy
Repo
Framework