February 1, 2020

2643 words 13 mins read

Paper Group AWR 280

Multi-scale Dynamic Feature Encoding Network for Image Demoireing. SmoothFool: An Efficient Framework for Computing Smooth Adversarial Perturbations. Differentiation of Blackbox Combinatorial Solvers. SPSTracker: Sub-Peak Suppression of Response Map for Robust Object Tracking. Variational Bayesian Decision-making for Continuous Utilities. Boosting …

Multi-scale Dynamic Feature Encoding Network for Image Demoireing


Title	Multi-scale Dynamic Feature Encoding Network for Image Demoireing
Authors	Xi Cheng, Zhenyong Fu, Jian Yang
Abstract	The prevalence of digital sensors, such as digital cameras and mobile phones, simplifies the acquisition of photos. Digital sensors, however, suffer from producing Moire when photographing objects having complex textures, which deteriorates the quality of photos. Moire spreads across various frequency bands of images and is a dynamic texture with varying colors and shapes, which pose two main challenges in demoireing—an important task in image restoration. In this paper, towards addressing the first challenge, we design a multi-scale network to process images at different spatial resolutions, obtaining features in different frequency bands, and thus our method can jointly remove moire in different frequency bands. Towards solving the second challenge, we propose a dynamic feature encoding module (DFE), embedded in each scale, for dynamic texture. Moire pattern can be eliminated more effectively via DFE.Our proposed method, termed Multi-scale convolutional network with Dynamic feature encoding for image DeMoireing (MDDM), can outperform the state of the arts in fidelity as well as perceptual on benchmarks.
Tasks	Image Restoration
Published	2019-09-26
URL	https://arxiv.org/abs/1909.11947v1
PDF	https://arxiv.org/pdf/1909.11947v1.pdf
PWC	https://paperswithcode.com/paper/multi-scale-dynamic-feature-encoding-network
Repo	https://github.com/opteroncx/MDDM
Framework	pytorch

SmoothFool: An Efficient Framework for Computing Smooth Adversarial Perturbations


Title	SmoothFool: An Efficient Framework for Computing Smooth Adversarial Perturbations
Authors	Ali Dabouei, Sobhan Soleymani, Fariborz Taherkhani, Jeremy Dawson, Nasser M. Nasrabadi
Abstract	Deep neural networks are susceptible to adversarial manipulations in the input domain. The extent of vulnerability has been explored intensively in cases of $\ell_p$-bounded and $\ell_p$-minimal adversarial perturbations. However, the vulnerability of DNNs to adversarial perturbations with specific statistical properties or frequency-domain characteristics has not been sufficiently explored. In this paper, we study the smoothness of perturbations and propose SmoothFool, a general and computationally efficient framework for computing smooth adversarial perturbations. Through extensive experiments, we validate the efficacy of the proposed method for both the white-box and black-box attack scenarios. In particular, we demonstrate that: (i) there exist extremely smooth adversarial perturbations for well-established and widely used network architectures, (ii) smoothness significantly enhances the robustness of perturbations against state-of-the-art defense mechanisms, (iii) smoothness improves the transferability of adversarial perturbations across both data points and network architectures, and (iv) class categories exhibit a variable range of susceptibility to smooth perturbations. Our results suggest that smooth APs can play a significant role in exploring the vulnerability extent of DNNs to adversarial examples.
Tasks
Published	2019-10-08
URL	https://arxiv.org/abs/1910.03624v1
PDF	https://arxiv.org/pdf/1910.03624v1.pdf
PWC	https://paperswithcode.com/paper/smoothfool-an-efficient-framework-for
Repo	https://github.com/alldbi/SmoothFool
Framework	pytorch

Differentiation of Blackbox Combinatorial Solvers


Title	Differentiation of Blackbox Combinatorial Solvers
Authors	Marin Vlastelica, Anselm Paulus, Vít Musil, Georg Martius, Michal Rolínek
Abstract	Achieving fusion of deep learning with combinatorial algorithms promises transformative changes to artificial intelligence. One possible approach is to introduce combinatorial building blocks into neural networks. Such end-to-end architectures have the potential to tackle combinatorial problems on raw input data such as ensuring global consistency in multi-object tracking or route planning on maps in robotics. In this work, we present a method that implements an efficient backward pass through blackbox implementations of combinatorial solvers with linear objective functions. We provide both theoretical and experimental backing. In particular, we incorporate the Gurobi MIP solver, Blossom V algorithm, and Dijkstra’s algorithm into architectures that extract suitable features from raw inputs for the traveling salesman problem, the min-cost perfect matching problem and the shortest path problem. The code is available at https://github.com/martius-lab/blackbox-backprop.
Tasks	Multi-Object Tracking, Object Tracking
Published	2019-12-04
URL	https://arxiv.org/abs/1912.02175v2
PDF	https://arxiv.org/pdf/1912.02175v2.pdf
PWC	https://paperswithcode.com/paper/differentiation-of-blackbox-combinatorial-1
Repo	https://github.com/martius-lab/blackbox-backprop
Framework	pytorch

SPSTracker: Sub-Peak Suppression of Response Map for Robust Object Tracking


Title	SPSTracker: Sub-Peak Suppression of Response Map for Robust Object Tracking
Authors	Qintao Hu, Lijun Zhou, Xiaoxiao Wang, Yao Mao, Jianlin Zhang, Qixiang Ye
Abstract	I’m sorry, Table2,3(VOT2016,2018) do not match figure6,7(VOT2016,2018).More experiments need to be added. However, this replacement version may take a lot of time, because a lot of experiments need to be done again, and now because of the Chinese Spring Festival and the 2019 novel coronavirus (2019-nCoV) can’t do experiments, in order to ensure the rigor of the paper, I applied to withdraw the manuscript, and then resubmit it after the replacement version.
Tasks	Object Tracking
Published	2019-12-02
URL	https://arxiv.org/abs/1912.00597v2
PDF	https://arxiv.org/pdf/1912.00597v2.pdf
PWC	https://paperswithcode.com/paper/spstracker-sub-peak-suppression-of-response
Repo	https://github.com/TrackerLB/SPSTracker
Framework	pytorch

Variational Bayesian Decision-making for Continuous Utilities


Title	Variational Bayesian Decision-making for Continuous Utilities
Authors	Tomasz Kuśmierczyk, Joseph Sakaya, Arto Klami
Abstract	Bayesian decision theory outlines a rigorous framework for making optimal decisions based on maximizing expected utility over a model posterior. However, practitioners often do not have access to the full posterior and resort to approximate inference strategies. In such cases, taking the eventual decision-making task into account while performing the inference allows for calibrating the posterior approximation to maximize the utility. We present an automatic pipeline that co-opts continuous utilities into variational inference algorithms to account for decision-making. We provide practical strategies for approximating and maximizing the gain, and empirically demonstrate consistent improvement when calibrating approximations for specific utilities.
Tasks	Decision Making
Published	2019-02-02
URL	https://arxiv.org/abs/1902.00792v3
PDF	https://arxiv.org/pdf/1902.00792v3.pdf
PWC	https://paperswithcode.com/paper/variational-bayesian-decision-making-for
Repo	https://github.com/tkusmierczyk/lcvi
Framework	pytorch

Boosting for Control of Dynamical Systems


Title	Boosting for Control of Dynamical Systems
Authors	Naman Agarwal, Nataly Brukhim, Elad Hazan, Zhou Lu
Abstract	We study the question of how to aggregate controllers for dynamical systems in order to improve their performance. To this end, we propose a framework of boosting for online control. Our main result is an efficient boosting algorithm that combines weak controllers into a provably more accurate one. Empirical evaluation on a host of control settings supports our theoretical findings.
Tasks
Published	2019-06-20
URL	https://arxiv.org/abs/1906.08720v2
PDF	https://arxiv.org/pdf/1906.08720v2.pdf
PWC	https://paperswithcode.com/paper/boosting-for-dynamical-systems
Repo	https://github.com/MinRegret/TigerForecast
Framework	jax

Soft-Label Dataset Distillation and Text Dataset Distillation


Title	Soft-Label Dataset Distillation and Text Dataset Distillation
Authors	Ilia Sucholutsky, Matthias Schonlau
Abstract	Dataset distillation is a method for reducing dataset sizes by learning a small number of synthetic samples containing all the information of a large dataset. This has several benefits like speeding up model training, reducing energy consumption, and reducing required storage space. Currently, each synthetic sample is assigned a single `hard' label, and also, dataset distillation can currently only be used with image data. We propose to simultaneously distill both images and their labels, thus assigning each synthetic sample a` soft’ label (a distribution of labels). Our algorithm increases accuracy by 2-4% over the original algorithm for several image classification tasks. Using `soft’ labels also enables distilled datasets to consist of fewer samples than there are classes as each sample can encode information for multiple classes. For example, training a LeNet model with 10 distilled images (one per class) results in over 96% accuracy on MNIST, and almost 92% accuracy when trained on just 5 distilled images. We also extend the dataset distillation algorithm to distill sequential datasets including texts. We demonstrate that text distillation outperforms other methods across multiple datasets. For example, models attain almost their original accuracy on the IMDB sentiment analysis task using just 20 distilled sentences. \|
Tasks	Data Summarization, Image Classification, Sentiment Analysis
Published	2019-10-06
URL	https://arxiv.org/abs/1910.02551v2
PDF	https://arxiv.org/pdf/1910.02551v2.pdf
PWC	https://paperswithcode.com/paper/improving-dataset-distillation
Repo	https://github.com/ilia10000/dataset-distillation
Framework	pytorch

apricot: Submodular selection for data summarization in Python


Title	apricot: Submodular selection for data summarization in Python
Authors	Jacob Schreiber, Jeffrey Bilmes, William Stafford Noble
Abstract	We present apricot, an open source Python package for selecting representative subsets from large data sets using submodular optimization. The package implements an efficient greedy selection algorithm that offers strong theoretical guarantees on the quality of the selected set. Two submodular set functions are implemented in apricot: facility location, which is broadly applicable but requires memory quadratic in the number of examples in the data set, and a feature-based function that is less broadly applicable but can scale to millions of examples. Apricot is extremely efficient, using both algorithmic speedups such as the lazy greedy algorithm and code optimizers such as numba. We demonstrate the use of subset selection by training machine learning models to comparable accuracy using either the full data set or a representative subset thereof. This paper presents an explanation of submodular selection, an overview of the features in apricot, and an application to several data sets. The code and tutorial Jupyter notebooks are available at https://github.com/jmschrei/apricot
Tasks	Data Summarization
Published	2019-06-08
URL	https://arxiv.org/abs/1906.03543v1
PDF	https://arxiv.org/pdf/1906.03543v1.pdf
PWC	https://paperswithcode.com/paper/apricot-submodular-selection-for-data
Repo	https://github.com/jmschrei/apricot
Framework	none

Augmenting Self-attention with Persistent Memory


Title	Augmenting Self-attention with Persistent Memory
Authors	Sainbayar Sukhbaatar, Edouard Grave, Guillaume Lample, Herve Jegou, Armand Joulin
Abstract	Transformer networks have lead to important progress in language modeling and machine translation. These models include two consecutive modules, a feed-forward layer and a self-attention layer. The latter allows the network to capture long term dependencies and are often regarded as the key ingredient in the success of Transformers. Building upon this intuition, we propose a new model that solely consists of attention layers. More precisely, we augment the self-attention layers with persistent memory vectors that play a similar role as the feed-forward layer. Thanks to these vectors, we can remove the feed-forward layer without degrading the performance of a transformer. Our evaluation shows the benefits brought by our model on standard character and word level language modeling benchmarks.
Tasks	Language Modelling
Published	2019-07-02
URL	https://arxiv.org/abs/1907.01470v1
PDF	https://arxiv.org/pdf/1907.01470v1.pdf
PWC	https://paperswithcode.com/paper/augmenting-self-attention-with-persistent
Repo	https://github.com/lucidrains/reformer-pytorch
Framework	pytorch

Palmprint Recognition in Uncontrolled and Uncooperative Environment


Title	Palmprint Recognition in Uncontrolled and Uncooperative Environment
Authors	Wojciech Michal Matkowski, Tingting Chai, Adams Wai Kin Kong
Abstract	Online palmprint recognition and latent palmprint identification are two branches of palmprint studies. The former uses middle-resolution images collected by a digital camera in a well-controlled or contact-based environment with user cooperation for commercial applications and the latter uses high-resolution latent palmprints collected in crime scenes for forensic investigation. However, these two branches do not cover some palmprint images which have the potential for forensic investigation. Due to the prevalence of smartphone and consumer camera, more evidence is in the form of digital images taken in uncontrolled and uncooperative environment, e.g., child pornographic images and terrorist images, where the criminals commonly hide or cover their face. However, their palms can be observable. To study palmprint identification on images collected in uncontrolled and uncooperative environment, a new palmprint database is established and an end-to-end deep learning algorithm is proposed. The new database named NTU Palmprints from the Internet (NTU-PI-v1) contains 7881 images from 2035 palms collected from the Internet. The proposed algorithm consists of an alignment network and a feature extraction network and is end-to-end trainable. The proposed algorithm is compared with the state-of-the-art online palmprint recognition methods and evaluated on three public contactless palmprint databases, IITD, CASIA, and PolyU and two new databases, NTU-PI-v1 and NTU contactless palmprint database. The experimental results showed that the proposed algorithm outperforms the existing palmprint recognition methods.
Tasks
Published	2019-11-28
URL	https://arxiv.org/abs/1911.12514v1
PDF	https://arxiv.org/pdf/1911.12514v1.pdf
PWC	https://paperswithcode.com/paper/palmprint-recognition-in-uncontrolled-and
Repo	https://github.com/BFLTeam/NTU_Dataset
Framework	none

Benchmarking Approximate Inference Methods for Neural Structured Prediction


Title	Benchmarking Approximate Inference Methods for Neural Structured Prediction
Authors	Lifu Tu, Kevin Gimpel
Abstract	Exact structured inference with neural network scoring functions is computationally challenging but several methods have been proposed for approximating inference. One approach is to perform gradient descent with respect to the output structure directly (Belanger and McCallum, 2016). Another approach, proposed recently, is to train a neural network (an “inference network”) to perform inference (Tu and Gimpel, 2018). In this paper, we compare these two families of inference methods on three sequence labeling datasets. We choose sequence labeling because it permits us to use exact inference as a benchmark in terms of speed, accuracy, and search error. Across datasets, we demonstrate that inference networks achieve a better speed/accuracy/search error trade-off than gradient descent, while also being faster than exact inference at similar accuracy levels. We find further benefit by combining inference networks and gradient descent, using the former to provide a warm start for the latter.
Tasks	Structured Prediction
Published	2019-04-01
URL	https://arxiv.org/abs/1904.01138v2
PDF	https://arxiv.org/pdf/1904.01138v2.pdf
PWC	https://paperswithcode.com/paper/benchmarking-approximate-inference-methods
Repo	https://github.com/lifu-tu/BenchmarkingApproximateInference
Framework	pytorch

Encode, Tag, Realize: High-Precision Text Editing


Title	Encode, Tag, Realize: High-Precision Text Editing
Authors	Eric Malmi, Sebastian Krause, Sascha Rothe, Daniil Mirylenka, Aliaksei Severyn
Abstract	We propose LaserTagger - a sequence tagging approach that casts text generation as a text editing task. Target texts are reconstructed from the inputs using three main edit operations: keeping a token, deleting it, and adding a phrase before the token. To predict the edit operations, we propose a novel model, which combines a BERT encoder with an autoregressive Transformer decoder. This approach is evaluated on English text on four tasks: sentence fusion, sentence splitting, abstractive summarization, and grammar correction. LaserTagger achieves new state-of-the-art results on three of these tasks, performs comparably to a set of strong seq2seq baselines with a large number of training examples, and outperforms them when the number of examples is limited. Furthermore, we show that at inference time tagging can be more than two orders of magnitude faster than comparable seq2seq models, making it more attractive for running in a live environment.
Tasks	Abstractive Text Summarization, Text Generation
Published	2019-09-03
URL	https://arxiv.org/abs/1909.01187v1
PDF	https://arxiv.org/pdf/1909.01187v1.pdf
PWC	https://paperswithcode.com/paper/encode-tag-realize-high-precision-text
Repo	https://github.com/Mleader2/text_scalpel
Framework	tf

Introducing RONEC – the Romanian Named Entity Corpus


Title	Introducing RONEC – the Romanian Named Entity Corpus
Authors	Stefan Daniel Dumitrescu, Andrei-Marius Avram
Abstract	We present RONEC - the Named Entity Corpus for the Romanian language. The corpus contains over 26000 entities in ~5000 annotated sentences, belonging to 16 distinct classes. The sentences have been extracted from a copy-right free newspaper, covering several styles. This corpus represents the first initiative in the Romanian language space specifically targeted for named entity recognition. It is available in BRAT and CoNLL-U Plus formats, and it is free to use and extend at github.com/dumitrescustefan/ronec .
Tasks	Named Entity Recognition
Published	2019-09-03
URL	https://arxiv.org/abs/1909.01247v1
PDF	https://arxiv.org/pdf/1909.01247v1.pdf
PWC	https://paperswithcode.com/paper/introducing-ronec-the-romanian-named-entity
Repo	https://github.com/dumitrescustefan/ronec
Framework	none

Churn Prediction with Sequential Data and Deep Neural Networks. A Comparative Analysis


Title	Churn Prediction with Sequential Data and Deep Neural Networks. A Comparative Analysis
Authors	C. Gary Mena, Arno De Caigny, Kristof Coussement, Koen W. De Bock, Stefan Lessmann
Abstract	Off-the-shelf machine learning algorithms for prediction such as regularized logistic regression cannot exploit the information of time-varying features without previously using an aggregation procedure of such sequential data. However, recurrent neural networks provide an alternative approach by which time-varying features can be readily used for modeling. This paper assesses the performance of neural networks for churn modeling using recency, frequency, and monetary value data from a financial services provider. Results show that RFM variables in combination with LSTM neural networks have larger top-decile lift and expected maximum profit metrics than regularized logistic regression models with commonly-used demographic variables. Moreover, we show that using the fitted probabilities from the LSTM as feature in the logistic regression increases the out-of-sample performance of the latter by 25 percent compared to a model with only static features.
Tasks
Published	2019-09-24
URL	https://arxiv.org/abs/1909.11114v1
PDF	https://arxiv.org/pdf/1909.11114v1.pdf
PWC	https://paperswithcode.com/paper/churn-prediction-with-sequential-data-and
Repo	https://github.com/adamribaudo/ds5500-capstone
Framework	none

Frequency Domain Transformer Networks for Video Prediction


Title	Frequency Domain Transformer Networks for Video Prediction
Authors	Hafez Farazi, Sven Behnke
Abstract	The task of video prediction is forecasting the next frames given some previous frames. Despite much recent progress, this task is still challenging mainly due to high nonlinearity in the spatial domain. To address this issue, we propose a novel architecture, Frequency Domain Transformer Network (FDTN), which is an end-to-end learnable model that estimates and uses the transformations of the signal in the frequency domain. Experimental evaluations show that this approach can outperform some widely used video prediction methods like Video Ladder Network (VLN) and Predictive Gated Pyramids (PGP).
Tasks	Video Prediction
Published	2019-03-01
URL	http://arxiv.org/abs/1903.00271v1
PDF	http://arxiv.org/pdf/1903.00271v1.pdf
PWC	https://paperswithcode.com/paper/frequency-domain-transformer-networks-for
Repo	https://github.com/AIS-Bonn/FreqNet
Framework	none