January 31, 2020

2913 words 14 mins read

Paper Group AWR 448

Resampling detection of recompressed images via dual-stream convolutional neural network. Technical report: supervised training of convolutional spiking neural networks with PyTorch. Copy Move Source-Target Disambiguation through Multi-Branch CNNs. Message Scheduling for Performant, Many-Core Belief Propagation. Exploring Interpretable LSTM Neural …

Resampling detection of recompressed images via dual-stream convolutional neural network


Title	Resampling detection of recompressed images via dual-stream convolutional neural network
Authors	Gang Cao, Antao Zhou, Xianglin Huang, Gege Song, Lifang Yang, Yonggui Zhu
Abstract	Resampling detection plays an important role in identifying image tampering, such as image splicing. Currently, the resampling detection is still difficult in recompressed images, which are yielded by applying resampling followed by post-JPEG compression to primary JPEG images. Except for the scenario of low quality primary compression, it remains rather challenging due to the widespread use of middle/high quality compression in imaging devices. In this paper, we propose a new convolution neural network (CNN) method to learn the resampling trace features directly from the recompressed images. To this end, a noise extraction layer based on low-order high pass filters is deployed to yield the image residual domain, which is more beneficial to extract manipulation trace features. A dual-stream CNN is presented to capture the resampling trails along different directions, where the horizontal and vertical streams are interleaved and concatenated. Lastly, the learned features are fed into Sigmoid/Softmax layer, which acts as a binary/multiple classifier for achieving the blind detection and parameter estimation of resampling, respectively. Extensive experimental results demonstrate that our proposed method could detect resampling effectively in recompressed images and outperform the state-of-the-art detectors.
Tasks
Published	2019-01-15
URL	https://arxiv.org/abs/1901.04637v3
PDF	https://arxiv.org/pdf/1901.04637v3.pdf
PWC	https://paperswithcode.com/paper/resampling-detection-of-recompressed-images
Repo	https://github.com/zhouantao/Resampling
Framework	tf

Technical report: supervised training of convolutional spiking neural networks with PyTorch


Title	Technical report: supervised training of convolutional spiking neural networks with PyTorch
Authors	Romain Zimmer, Thomas Pellegrini, Srisht Fateh Singh, Timothée Masquelier
Abstract	Recently, it has been shown that spiking neural networks (SNNs) can be trained efficiently, in a supervised manner, using backpropagation through time. Indeed, the most commonly used spiking neuron model, the leaky integrate-and-fire neuron, obeys a differential equation which can be approximated using discrete time steps, leading to a recurrent relation for the potential. The firing threshold causes optimization issues, but they can be overcome using a surrogate gradient. Here, we extend previous approaches in two ways. Firstly, we show that the approach can be used to train convolutional layers. Convolutions can be done in space, time (which simulates conduction delays), or both. Secondly, we include fast horizontal connections `a la Den`eve: when a neuron N fires, we subtract to the potentials of all the neurons with the same receptive the dot product between their weight vectors and the one of neuron N. As Den`eve et al. showed, this is useful to represent a dynamic multidimensional analog signal in a population of spiking neurons. Here we demonstrate that, in addition, such connections also allow implementing a multidimensional send-on-delta coding scheme. We validate our approach on one speech classification benchmarks: the Google speech command dataset. We managed to reach nearly state-of-the-art accuracy (94%) while maintaining low firing rates (about 5Hz). Our code is based on PyTorch and is available in open source at http://github.com/romainzimmer/s2net
Tasks
Published	2019-11-22
URL	https://arxiv.org/abs/1911.10124v1
PDF	https://arxiv.org/pdf/1911.10124v1.pdf
PWC	https://paperswithcode.com/paper/technical-report-supervised-training-of
Repo	https://github.com/romainzimmer/s2net
Framework	pytorch

Copy Move Source-Target Disambiguation through Multi-Branch CNNs


Title	Copy Move Source-Target Disambiguation through Multi-Branch CNNs
Authors	Mauro Barni, Quoc-Tin Phan, Benedetta Tondi
Abstract	We propose a method to identify the source and target regions of a copy-move forgery so allow a correct localisation of the tampered area. First, we cast the problem into a hypothesis testing framework whose goal is to decide which region between the two nearly-duplicate regions detected by a generic copy-move detector is the original one. Then we design a multi-branch CNN architecture that solves the hypothesis testing problem by learning a set of features capable to reveal the presence of interpolation artefacts and boundary inconsistencies in the copy-moved area. The proposed architecture, trained on a synthetic dataset explicitly built for this purpose, achieves good results on copy-move forgeries from both synthetic and realistic datasets. Based on our tests, the proposed disambiguation method can reliably reveal the target region even in realistic cases where an approximate version of the copy-move localization mask is provided by a state-of-the-art copy-move detection algorithm.
Tasks
Published	2019-12-29
URL	https://arxiv.org/abs/1912.12640v1
PDF	https://arxiv.org/pdf/1912.12640v1.pdf
PWC	https://paperswithcode.com/paper/copy-move-source-target-disambiguation
Repo	https://github.com/andreacos/MultiBranch_CNNCopyMove_Disambiguation
Framework	tf

Message Scheduling for Performant, Many-Core Belief Propagation


Title	Message Scheduling for Performant, Many-Core Belief Propagation
Authors	Mark Van der Merwe, Vinu Joseph, Ganesh Gopalakrishnan
Abstract	Belief Propagation (BP) is a message-passing algorithm for approximate inference over Probabilistic Graphical Models (PGMs), finding many applications such as computer vision, error-correcting codes, and protein-folding. While general, the convergence and speed of the algorithm has limited its practical use on difficult inference problems. As an algorithm that is highly amenable to parallelization, many-core Graphical Processing Units (GPUs) could significantly improve BP performance. Improving BP through many-core systems is non-trivial: the scheduling of messages in the algorithm strongly affects performance. We present a study of message scheduling for BP on GPUs. We demonstrate that BP exhibits a tradeoff between speed and convergence based on parallelism and show that existing message schedulings are not able to utilize this tradeoff. To this end, we present a novel randomized message scheduling approach, Randomized BP (RnBP), which outperforms existing methods on the GPU.
Tasks
Published	2019-09-24
URL	https://arxiv.org/abs/1909.11469v1
PDF	https://arxiv.org/pdf/1909.11469v1.pdf
PWC	https://paperswithcode.com/paper/message-scheduling-for-performant-many-core
Repo	https://github.com/mvandermerwe/BP-GPU-Message-Scheduling
Framework	none

Exploring Interpretable LSTM Neural Networks over Multi-Variable Data


Title	Exploring Interpretable LSTM Neural Networks over Multi-Variable Data
Authors	Tian Guo, Tao Lin, Nino Antulov-Fantulin
Abstract	For recurrent neural networks trained on time series with target and exogenous variables, in addition to accurate prediction, it is also desired to provide interpretable insights into the data. In this paper, we explore the structure of LSTM recurrent neural networks to learn variable-wise hidden states, with the aim to capture different dynamics in multi-variable time series and distinguish the contribution of variables to the prediction. With these variable-wise hidden states, a mixture attention mechanism is proposed to model the generative process of the target. Then we develop associated training methods to jointly learn network parameters, variable and temporal importance w.r.t the prediction of the target variable. Extensive experiments on real datasets demonstrate enhanced prediction performance by capturing the dynamics of different variables. Meanwhile, we evaluate the interpretation results both qualitatively and quantitatively. It exhibits the prospect as an end-to-end framework for both forecasting and knowledge extraction over multi-variable data.
Tasks	Time Series
Published	2019-05-28
URL	https://arxiv.org/abs/1905.12034v1
PDF	https://arxiv.org/pdf/1905.12034v1.pdf
PWC	https://paperswithcode.com/paper/exploring-interpretable-lstm-neural-networks
Repo	https://github.com/KurochkinAlexey/IMV_LSTM
Framework	pytorch

Dual Extrapolation for Sparse Generalized Linear Models


Title	Dual Extrapolation for Sparse Generalized Linear Models
Authors	Mathurin Massias, Samuel Vaiter, Alexandre Gramfort, Joseph Salmon
Abstract	Generalized Linear Models (GLM) form a wide class of regression and classification models, where prediction is a function of a linear combination of the input variables. For statistical inference in high dimension, sparsity inducing regularizations have proven to be useful while offering statistical guarantees. However, solving the resulting optimization problems can be challenging: even for popular iterative algorithms such as coordinate descent, one needs to loop over a large number of variables. To mitigate this, techniques known as screening rules and working sets diminish the size of the optimization problem at hand, either by progressively removing variables, or by solving a growing sequence of smaller problems. For both techniques, significant variables are identified thanks to convex duality arguments. In this paper, we show that the dual iterates of a GLM exhibit a Vector AutoRegressive (VAR) behavior after sign identification, when the primal problem is solved with proximal gradient descent or cyclic coordinate descent. Exploiting this regularity, one can construct dual points that offer tighter certificates of optimality, enhancing the performance of screening rules and helping to design competitive working set algorithms.
Tasks
Published	2019-07-12
URL	https://arxiv.org/abs/1907.05830v2
PDF	https://arxiv.org/pdf/1907.05830v2.pdf
PWC	https://paperswithcode.com/paper/dual-extrapolation-for-sparse-generalized
Repo	https://github.com/mathurinm/celer
Framework	none

Superposition of many models into one


Title	Superposition of many models into one
Authors	Brian Cheung, Alex Terekhov, Yubei Chen, Pulkit Agrawal, Bruno Olshausen
Abstract	We present a method for storing multiple models within a single set of parameters. Models can coexist in superposition and still be retrieved individually. In experiments with neural networks, we show that a surprisingly large number of models can be effectively stored within a single parameter instance. Furthermore, each of these models can undergo thousands of training steps without significantly interfering with other models within the superposition. This approach may be viewed as the online complement of compression: rather than reducing the size of a network after training, we make use of the unrealized capacity of a network during training.
Tasks
Published	2019-02-14
URL	https://arxiv.org/abs/1902.05522v2
PDF	https://arxiv.org/pdf/1902.05522v2.pdf
PWC	https://paperswithcode.com/paper/superposition-of-many-models-into-one
Repo	https://github.com/briancheung/superposition
Framework	pytorch

Tuning Hyperparameters without Grad Students: Scalable and Robust Bayesian Optimisation with Dragonfly


Title	Tuning Hyperparameters without Grad Students: Scalable and Robust Bayesian Optimisation with Dragonfly
Authors	Kirthevasan Kandasamy, Karun Raju Vysyaraju, Willie Neiswanger, Biswajit Paria, Christopher R. Collins, Jeff Schneider, Barnabas Poczos, Eric P. Xing
Abstract	Bayesian Optimisation (BO), refers to a suite of techniques for global optimisation of expensive black box functions, which use introspective Bayesian models of the function to efficiently find the optimum. While BO has been applied successfully in many applications, modern optimisation tasks usher in new challenges where conventional methods fail spectacularly. In this work, we present Dragonfly, an open source Python library for scalable and robust BO. Dragonfly incorporates multiple recently developed methods that allow BO to be applied in challenging real world settings; these include better methods for handling higher dimensional domains, methods for handling multi-fidelity evaluations when cheap approximations of an expensive function are available, methods for optimising over structured combinatorial spaces, such as the space of neural network architectures, and methods for handling parallel evaluations. Additionally, we develop new methodological improvements in BO for selecting the Bayesian model, selecting the acquisition function, and optimising over complex domains with different variable types and additional constraints. We compare Dragonfly to a suite of other packages and algorithms for global optimisation and demonstrate that when the above methods are integrated, they enable significant improvements in the performance of BO. The Dragonfly library is available at dragonfly.github.io.
Tasks	Bayesian Optimisation
Published	2019-03-15
URL	http://arxiv.org/abs/1903.06694v1
PDF	http://arxiv.org/pdf/1903.06694v1.pdf
PWC	https://paperswithcode.com/paper/tuning-hyperparameters-without-grad-students
Repo	https://github.com/dragonfly/dragonfly
Framework	none

Stochastic Weight Matrix-based Regularization Methods for Deep Neural Networks


Title	Stochastic Weight Matrix-based Regularization Methods for Deep Neural Networks
Authors	Patrik Reizinger, Bálint Gyires-Tóth
Abstract	The aim of this paper is to introduce two widely applicable regularization methods based on the direct modification of weight matrices. The first method, Weight Reinitialization, utilizes a simplified Bayesian assumption with partially resetting a sparse subset of the parameters. The second one, Weight Shuffling, introduces an entropy- and weight distribution-invariant non-white noise to the parameters. The latter can also be interpreted as an ensemble approach. The proposed methods are evaluated on benchmark datasets, such as MNIST, CIFAR-10 or the JSB Chorales database, and also on time series modeling tasks. We report gains both regarding performance and entropy of the analyzed networks. We also made our code available as a GitHub repository (https://github.com/rpatrik96/lod-wmm-2019).
Tasks	Time Series
Published	2019-09-26
URL	https://arxiv.org/abs/1909.11977v1
PDF	https://arxiv.org/pdf/1909.11977v1.pdf
PWC	https://paperswithcode.com/paper/stochastic-weight-matrix-based-regularization
Repo	https://github.com/rpatrik96/lod-wmm-2019
Framework	pytorch

GGNN: Graph-based GPU Nearest Neighbor Search


Title	GGNN: Graph-based GPU Nearest Neighbor Search
Authors	Fabian Groh, Lukas Ruppert, Patrick Wieschollek, Hendrik P. A. Lensch
Abstract	Approximate nearest neighbor (ANN) search in high dimensions is an integral part of several computer vision systems and gains importance in deep learning with explicit memory representations. Since PQT and FAISS started to leverage the massive parallelism offered by GPUs, GPU-based implementations are a crucial resource for today’s state-of-the-art ANN methods. While most of these methods allow for faster queries, less emphasis is devoted to accelerate the construction of the underlying index structures. In this paper, we propose a novel search structure based on nearest neighbor graphs and information propagation on graphs. Our method is designed to take advantage of GPU architectures to accelerate the hierarchical building of the index structure and for performing the query. Empirical evaluation shows that GGNN significantly surpasses the state-of-the-art GPU- and CPU-based systems in terms of build-time, accuracy and search speed.
Tasks
Published	2019-12-02
URL	https://arxiv.org/abs/1912.01059v2
PDF	https://arxiv.org/pdf/1912.01059v2.pdf
PWC	https://paperswithcode.com/paper/ggnn-graph-based-gpu-nearest-neighbor-search
Repo	https://github.com/cgtuebingen/ggnn
Framework	none

Single Image Haze Removal Using Conditional Wasserstein Generative Adversarial Networks


Title	Single Image Haze Removal Using Conditional Wasserstein Generative Adversarial Networks
Authors	Joshua Peter Ebenezer, Bijaylaxmi Das, Sudipta Mukhopadhyay
Abstract	We present a method to restore a clear image from a haze-affected image using a Wasserstein generative adversarial network. As the problem is ill-conditioned, previous methods have required a prior on natural images or multiple images of the same scene. We train a generative adversarial network to learn the probability distribution of clear images conditioned on the haze-affected images using the Wasserstein loss function, using a gradient penalty to enforce the Lipschitz constraint. The method is data-adaptive, end-to-end, and requires no further processing or tuning of parameters. We also incorporate the use of a texture-based loss metric and the L1 loss to improve results, and show that our results are better than the current state-of-the-art.
Tasks	Single Image Haze Removal
Published	2019-03-01
URL	http://arxiv.org/abs/1903.00395v1
PDF	http://arxiv.org/pdf/1903.00395v1.pdf
PWC	https://paperswithcode.com/paper/single-image-haze-removal-using-conditional
Repo	https://github.com/JoshuaEbenezer/cwgan
Framework	pytorch

Neural Generation for Czech: Data and Baselines


Title	Neural Generation for Czech: Data and Baselines
Authors	Ondřej Dušek, Filip Jurčíček
Abstract	We present the first dataset targeted at end-to-end NLG in Czech in the restaurant domain, along with several strong baseline models using the sequence-to-sequence approach. While non-English NLG is under-explored in general, Czech, as a morphologically rich language, makes the task even harder: Since Czech requires inflecting named entities, delexicalization or copy mechanisms do not work out-of-the-box and lexicalizing the generated outputs is non-trivial. In our experiments, we present two different approaches to this this problem: (1) using a neural language model to select the correct inflected form while lexicalizing, (2) a two-step generation setup: our sequence-to-sequence model generates an interleaved sequence of lemmas and morphological tags, which are then inflected by a morphological generator.
Tasks	Language Modelling
Published	2019-10-11
URL	https://arxiv.org/abs/1910.05298v1
PDF	https://arxiv.org/pdf/1910.05298v1.pdf
PWC	https://paperswithcode.com/paper/neural-generation-for-czech-data-and
Repo	https://github.com/UFAL-DSG/cs_restaurant_dataset
Framework	none

Unsupervised Deep Tracking


Title	Unsupervised Deep Tracking
Authors	Ning Wang, Yibing Song, Chao Ma, Wengang Zhou, Wei Liu, Houqiang Li
Abstract	We propose an unsupervised visual tracking method in this paper. Different from existing approaches using extensive annotated data for supervised learning, our CNN model is trained on large-scale unlabeled videos in an unsupervised manner. Our motivation is that a robust tracker should be effective in both the forward and backward predictions (i.e., the tracker can forward localize the target object in successive frames and backtrace to its initial position in the first frame). We build our framework on a Siamese correlation filter network, which is trained using unlabeled raw videos. Meanwhile, we propose a multiple-frame validation method and a cost-sensitive loss to facilitate unsupervised learning. Without bells and whistles, the proposed unsupervised tracker achieves the baseline accuracy of fully supervised trackers, which require complete and accurate labels during training. Furthermore, unsupervised framework exhibits a potential in leveraging unlabeled or weakly labeled data to further improve the tracking accuracy.
Tasks	Visual Tracking
Published	2019-04-03
URL	http://arxiv.org/abs/1904.01828v1
PDF	http://arxiv.org/pdf/1904.01828v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-deep-tracking
Repo	https://github.com/594422814/UDT
Framework	pytorch

Gaussian Process Priors for Dynamic Paired Comparison Modelling


Title	Gaussian Process Priors for Dynamic Paired Comparison Modelling
Authors	Martin Ingram
Abstract	Dynamic paired comparison models, such as Elo and Glicko, are frequently used for sports prediction and ranking players or teams. We present an alternative dynamic paired comparison model which uses a Gaussian Process (GP) as a prior for the time dynamics rather than the Markovian dynamics usually assumed. In addition, we show that the GP model can easily incorporate covariates. We derive an efficient approximate Bayesian inference procedure based on the Laplace Approximation and sparse linear algebra. We select hyperparameters by maximising their marginal likelihood using Bayesian Optimisation, comparing the results against random search. Finally, we fit and evaluate the model on the 2018 season of ATP tennis matches, where it performs competitively, outperforming Elo and Glicko on log loss, particularly when surface covariates are included.
Tasks	Bayesian Inference, Bayesian Optimisation
Published	2019-02-20
URL	http://arxiv.org/abs/1902.07378v1
PDF	http://arxiv.org/pdf/1902.07378v1.pdf
PWC	https://paperswithcode.com/paper/gaussian-process-priors-for-dynamic-paired
Repo	https://github.com/martiningram/paired-comparison-gp-laplace
Framework	none

Learning Neural Networks with Adaptive Regularization


Title	Learning Neural Networks with Adaptive Regularization
Authors	Han Zhao, Yao-Hung Hubert Tsai, Ruslan Salakhutdinov, Geoffrey J. Gordon
Abstract	Feed-forward neural networks can be understood as a combination of an intermediate representation and a linear hypothesis. While most previous works aim to diversify the representations, we explore the complementary direction by performing an adaptive and data-dependent regularization motivated by the empirical Bayes method. Specifically, we propose to construct a matrix-variate normal prior (on weights) whose covariance matrix has a Kronecker product structure. This structure is designed to capture the correlations in neurons through backpropagation. Under the assumption of this Kronecker factorization, the prior encourages neurons to borrow statistical strength from one another. Hence, it leads to an adaptive and data-dependent regularization when training networks on small datasets. To optimize the model, we present an efficient block coordinate descent algorithm with analytical solutions. Empirically, we demonstrate that the proposed method helps networks converge to local optima with smaller stable ranks and spectral norms. These properties suggest better generalizations and we present empirical results to support this expectation. We also verify the effectiveness of the approach on multiclass classification and multitask regression problems with various network structures.
Tasks
Published	2019-07-14
URL	https://arxiv.org/abs/1907.06288v2
PDF	https://arxiv.org/pdf/1907.06288v2.pdf
PWC	https://paperswithcode.com/paper/learning-neural-networks-with-adaptive
Repo	https://github.com/yaohungt/Adaptive-Regularization-Neural-Network
Framework	pytorch