February 1, 2020

3086 words 15 mins read

Paper Group AWR 119

bLIMEy: Surrogate Prediction Explanations Beyond LIME. Scale-wise Convolution for Image Restoration. Monocular 3D Human Pose Estimation by Generation and Ordinal Ranking. Defending Against Adversarial Examples with K-Nearest Neighbor. Reparameterizing Distributions on Lie Groups. A Realistic Dataset and Baseline Temporal Model for Early Drowsiness …

bLIMEy: Surrogate Prediction Explanations Beyond LIME


Title	bLIMEy: Surrogate Prediction Explanations Beyond LIME
Authors	Kacper Sokol, Alexander Hepburn, Raul Santos-Rodriguez, Peter Flach
Abstract	Surrogate explainers of black-box machine learning predictions are of paramount importance in the field of eXplainable Artificial Intelligence since they can be applied to any type of data (images, text and tabular), are model-agnostic and are post-hoc (i.e., can be retrofitted). The Local Interpretable Model-agnostic Explanations (LIME) algorithm is often mistakenly unified with a more general framework of surrogate explainers, which may lead to a belief that it is the solution to surrogate explainability. In this paper we empower the community to “build LIME yourself” (bLIMEy) by proposing a principled algorithmic framework for building custom local surrogate explainers of black-box model predictions, including LIME itself. To this end, we demonstrate how to decompose the surrogate explainers family into algorithmically independent and interoperable modules and discuss the influence of these component choices on the functional capabilities of the resulting explainer, using the example of LIME.
Tasks
Published	2019-10-29
URL	https://arxiv.org/abs/1910.13016v1
PDF	https://arxiv.org/pdf/1910.13016v1.pdf
PWC	https://paperswithcode.com/paper/blimey-surrogate-prediction-explanations
Repo	https://github.com/So-Cool/bLIMEy
Framework	none

Scale-wise Convolution for Image Restoration


Title	Scale-wise Convolution for Image Restoration
Authors	Yuchen Fan, Jiahui Yu, Ding Liu, Thomas S. Huang
Abstract	While scale-invariant modeling has substantially boosted the performance of visual recognition tasks, it remains largely under-explored in deep networks based image restoration. Naively applying those scale-invariant techniques (e.g. multi-scale testing, random-scale data augmentation) to image restoration tasks usually leads to inferior performance. In this paper, we show that properly modeling scale-invariance into neural networks can bring significant benefits to image restoration performance. Inspired from spatial-wise convolution for shift-invariance, “scale-wise convolution” is proposed to convolve across multiple scales for scale-invariance. In our scale-wise convolutional network (SCN), we first map the input image to the feature space and then build a feature pyramid representation via bi-linear down-scaling progressively. The feature pyramid is then passed to a residual network with scale-wise convolutions. The proposed scale-wise convolution learns to dynamically activate and aggregate features from different input scales in each residual building block, in order to exploit contextual information on multiple scales. In experiments, we compare the restoration accuracy and parameter efficiency among our model and many different variants of multi-scale neural networks. The proposed network with scale-wise convolution achieves superior performance in multiple image restoration tasks including image super-resolution, image denoising and image compression artifacts removal. Code and models are available at: https://github.com/ychfan/scn_sr
Tasks	Data Augmentation, Denoising, Image Compression, Image Denoising, Image Restoration, Image Super-Resolution, Super-Resolution
Published	2019-12-19
URL	https://arxiv.org/abs/1912.09028v1
PDF	https://arxiv.org/pdf/1912.09028v1.pdf
PWC	https://paperswithcode.com/paper/scale-wise-convolution-for-image-restoration
Repo	https://github.com/ychfan/scn
Framework	pytorch

Monocular 3D Human Pose Estimation by Generation and Ordinal Ranking


Title	Monocular 3D Human Pose Estimation by Generation and Ordinal Ranking
Authors	Saurabh Sharma, Pavan Teja Varigonda, Prashast Bindal, Abhishek Sharma, Arjun Jain
Abstract	Monocular 3D human-pose estimation from static images is a challenging problem, due to the curse of dimensionality and the ill-posed nature of lifting 2D-to-3D. In this paper, we propose a Deep Conditional Variational Autoencoder based model that synthesizes diverse anatomically plausible 3D-pose samples conditioned on the estimated 2D-pose. We show that CVAE-based 3D-pose sample set is consistent with the 2D-pose and helps tackling the inherent ambiguity in 2D-to-3D lifting. We propose two strategies for obtaining the final 3D pose- (a) depth-ordering/ordinal relations to score and weight-average the candidate 3D-poses, referred to as OrdinalScore, and (b) with supervision from an Oracle. We report close to state of-the-art results on two benchmark datasets using OrdinalScore, and state-of-the-art results using the Oracle. We also show that our pipeline yields competitive results without paired image-to-3D annotations. The training and evaluation code is available at https://github.com/ssfootball04/generative_pose.
Tasks	3D Human Pose Estimation, Pose Estimation
Published	2019-04-02
URL	https://arxiv.org/abs/1904.01324v2
PDF	https://arxiv.org/pdf/1904.01324v2.pdf
PWC	https://paperswithcode.com/paper/monocular-3d-human-pose-estimation-by-1
Repo	https://github.com/ssfootball04/generative_pose
Framework	pytorch

Defending Against Adversarial Examples with K-Nearest Neighbor


Title	Defending Against Adversarial Examples with K-Nearest Neighbor
Authors	Chawin Sitawarin, David Wagner
Abstract	Robustness is an increasingly important property of machine learning models as they become more and more prevalent. We propose a defense against adversarial examples based on a k-nearest neighbor (kNN) on the intermediate activation of neural networks. Our scheme surpasses state-of-the-art defenses on MNIST and CIFAR-10 against l2-perturbation by a significant margin. With our models, the mean perturbation norm required to fool our MNIST model is 3.07 and 2.30 on CIFAR-10. Additionally, we propose a simple certifiable lower bound on the l2-norm of the adversarial perturbation using a more specific version of our scheme, a 1-NN on representations learned by a Lipschitz network. Our model provides a nontrivial average lower bound of the perturbation norm, comparable to other schemes on MNIST with similar clean accuracy.
Tasks
Published	2019-06-23
URL	https://arxiv.org/abs/1906.09525v2
PDF	https://arxiv.org/pdf/1906.09525v2.pdf
PWC	https://paperswithcode.com/paper/defending-against-adversarial-examples-with-k
Repo	https://github.com/chawins/knn-defense
Framework	pytorch

Reparameterizing Distributions on Lie Groups


Title	Reparameterizing Distributions on Lie Groups
Authors	Luca Falorsi, Pim de Haan, Tim R. Davidson, Patrick Forré
Abstract	Reparameterizable densities are an important way to learn probability distributions in a deep learning setting. For many distributions it is possible to create low-variance gradient estimators by utilizing a `reparameterization trick’. Due to the absence of a general reparameterization trick, much research has recently been devoted to extend the number of reparameterizable distributional families. Unfortunately, this research has primarily focused on distributions defined in Euclidean space, ruling out the usage of one of the most influential class of spaces with non-trivial topologies: Lie groups. In this work we define a general framework to create reparameterizable densities on arbitrary Lie groups, and provide a detailed practitioners guide to further the ease of usage. We demonstrate how to create complex and multimodal distributions on the well known oriented group of 3D rotations, $\operatorname{SO}(3)$, using normalizing flows. Our experiments on applying such distributions in a Bayesian setting for pose estimation on objects with discrete and continuous symmetries, showcase their necessity in achieving realistic uncertainty estimates. \|
Tasks	Pose Estimation
Published	2019-03-07
URL	http://arxiv.org/abs/1903.02958v1
PDF	http://arxiv.org/pdf/1903.02958v1.pdf
PWC	https://paperswithcode.com/paper/reparameterizing-distributions-on-lie-groups
Repo	https://github.com/pimdh/relie
Framework	pytorch

A Realistic Dataset and Baseline Temporal Model for Early Drowsiness Detection


Title	A Realistic Dataset and Baseline Temporal Model for Early Drowsiness Detection
Authors	Reza Ghoddoosian, Marnim Galib, Vassilis Athitsos
Abstract	Drowsiness can put lives of many drivers and workers in danger. It is important to design practical and easy-to-deploy real-world systems to detect the onset of drowsiness.In this paper, we address early drowsiness detection, which can provide early alerts and offer subjects ample time to react. We present a large and public real-life dataset of 60 subjects, with video segments labeled as alert, low vigilant, or drowsy. This dataset consists of around 30 hours of video, with contents ranging from subtle signs of drowsiness to more obvious ones. We also benchmark a temporal model for our dataset, which has low computational and storage demands. The core of our proposed method is a Hierarchical Multiscale Long Short-Term Memory (HM-LSTM) network, that is fed by detected blink features in sequence. Our experiments demonstrate the relationship between the sequential blink features and drowsiness. In the experimental results, our baseline method produces higher accuracy than human judgment.
Tasks
Published	2019-04-15
URL	http://arxiv.org/abs/1904.07312v1
PDF	http://arxiv.org/pdf/1904.07312v1.pdf
PWC	https://paperswithcode.com/paper/a-realistic-dataset-and-baseline-temporal
Repo	https://github.com/steffytw/machine-learning-iris
Framework	tf

Uncovering convolutional neural network decisions for diagnosing multiple sclerosis on conventional MRI using layer-wise relevance propagation


Title	Uncovering convolutional neural network decisions for diagnosing multiple sclerosis on conventional MRI using layer-wise relevance propagation
Authors	Fabian Eitel, Emily Soehler, Judith Bellmann-Strobl, Alexander U. Brandt, Klemens Ruprecht, René M. Giess, Joseph Kuchling, Susanna Asseyer, Martin Weygandt, John-Dylan Haynes, Michael Scheel, Friedemann Paul, Kerstin Ritter
Abstract	Machine learning-based imaging diagnostics has recently reached or even superseded the level of clinical experts in several clinical domains. However, classification decisions of a trained machine learning system are typically non-transparent, a major hindrance for clinical integration, error tracking or knowledge discovery. In this study, we present a transparent deep learning framework relying on convolutional neural networks (CNNs) and layer-wise relevance propagation (LRP) for diagnosing multiple sclerosis (MS). MS is commonly diagnosed utilizing a combination of clinical presentation and conventional magnetic resonance imaging (MRI), specifically the occurrence and presentation of white matter lesions in T2-weighted images. We hypothesized that using LRP in a naive predictive model would enable us to uncover relevant image features that a trained CNN uses for decision-making. Since imaging markers in MS are well-established this would enable us to validate the respective CNN model. First, we pre-trained a CNN on MRI data from the Alzheimer’s Disease Neuroimaging Initiative (n = 921), afterwards specializing the CNN to discriminate between MS patients and healthy controls (n = 147). Using LRP, we then produced a heatmap for each subject in the holdout set depicting the voxel-wise relevance for a particular classification decision. The resulting CNN model resulted in a balanced accuracy of 87.04% and an area under the curve of 96.08% in a receiver operating characteristic curve. The subsequent LRP visualization revealed that the CNN model focuses indeed on individual lesions, but also incorporates additional information such as lesion location, non-lesional white matter or gray matter areas such as the thalamus, which are established conventional and advanced MRI markers in MS. We conclude that LRP and the proposed framework have the capability to make diagnostic decisions of…
Tasks	Decision Making
Published	2019-04-18
URL	http://arxiv.org/abs/1904.08771v1
PDF	http://arxiv.org/pdf/1904.08771v1.pdf
PWC	https://paperswithcode.com/paper/uncovering-convolutional-neural-network
Repo	https://github.com/derEitel/explainableMS
Framework	none

Syntactically Supervised Transformers for Faster Neural Machine Translation


Title	Syntactically Supervised Transformers for Faster Neural Machine Translation
Authors	Nader Akoury, Kalpesh Krishna, Mohit Iyyer
Abstract	Standard decoders for neural machine translation autoregressively generate a single target token per time step, which slows inference especially for long outputs. While architectural advances such as the Transformer fully parallelize the decoder computations at training time, inference still proceeds sequentially. Recent developments in non- and semi- autoregressive decoding produce multiple tokens per time step independently of the others, which improves inference speed but deteriorates translation quality. In this work, we propose the syntactically supervised Transformer (SynST), which first autoregressively predicts a chunked parse tree before generating all of the target tokens in one shot conditioned on the predicted parse. A series of controlled experiments demonstrates that SynST decodes sentences ~ 5x faster than the baseline autoregressive Transformer while achieving higher BLEU scores than most competing methods on En-De and En-Fr datasets.
Tasks	Machine Translation
Published	2019-06-06
URL	https://arxiv.org/abs/1906.02780v1
PDF	https://arxiv.org/pdf/1906.02780v1.pdf
PWC	https://paperswithcode.com/paper/syntactically-supervised-transformers-for
Repo	https://github.com/dojoteef/synst
Framework	pytorch

DiaBLa: A Corpus of Bilingual Spontaneous Written Dialogues for Machine Translation


Title	DiaBLa: A Corpus of Bilingual Spontaneous Written Dialogues for Machine Translation
Authors	Rachel Bawden, Sophie Rosset, Thomas Lavergne, Eric Bilinski
Abstract	We present a new English-French test set for the evaluation of Machine Translation (MT) for informal, written bilingual dialogue. The test set contains 144 spontaneous dialogues (5,700+ sentences) between native English and French speakers, mediated by one of two neural MT systems in a range of role-play settings. The dialogues are accompanied by fine-grained sentence-level judgments of MT quality, produced by the dialogue participants themselves, as well as by manually normalised versions and reference translations produced a posteriori. The motivation for the corpus is two-fold: to provide (i) a unique resource for evaluating MT models, and (ii) a corpus for the analysis of MT-mediated communication. We provide a preliminary analysis of the corpus to confirm that the participants’ judgments reveal perceptible differences in MT quality between the two MT systems used.
Tasks	Machine Translation
Published	2019-05-30
URL	https://arxiv.org/abs/1905.13354v1
PDF	https://arxiv.org/pdf/1905.13354v1.pdf
PWC	https://paperswithcode.com/paper/diabla-a-corpus-of-bilingual-spontaneous
Repo	https://github.com/rbawden/DiaBLa-dataset
Framework	none

ITENE: Intrinsic Transfer Entropy Neural Estimator


Title	ITENE: Intrinsic Transfer Entropy Neural Estimator
Authors	Jingjing Zhang, Osvaldo Simeone, Zoran Cvetkovic, Eugenio Abela, Mark Richardson
Abstract	Quantifying the directionality of information flow is instrumental in understanding, and possibly controlling, the operation of many complex systems, such as transportation, social, neural, or gene-regulatory networks. The standard Transfer Entropy (TE) metric follows Granger’s causality principle by measuring the Mutual Information (MI) between the past states of a source signal $X$ and the future state of a target signal $Y$ while conditioning on past states of $Y$. Hence, the TE quantifies the improvement, as measured by the log-loss, in the prediction of the target sequence $Y$ that can be accrued when, in addition to the past of $Y$, one also has available past samples from $X$. However, by conditioning on the past of $Y$, the TE also measures information that can be synergistically extracted by observing both the past of $X$ and $Y$, and not solely the past of $X$. Building on a private key agreement formulation, the Intrinsic TE (ITE) aims to discount such synergistic information to quantify the degree to which $X$ is \emph{individually} predictive of $Y$, independent of $Y$'s past. In this paper, an estimator of the ITE is proposed that is inspired by the recently proposed Mutual Information Neural Estimation (MINE). The estimator is based on variational bound on the KL divergence, two-sample neural network classifiers, and the pathwise estimator of Monte Carlo gradients.
Tasks
Published	2019-12-16
URL	https://arxiv.org/abs/1912.07277v2
PDF	https://arxiv.org/pdf/1912.07277v2.pdf
PWC	https://paperswithcode.com/paper/itene-intrinsic-transfer-entropy-neural
Repo	https://github.com/kclip/ITENE
Framework	pytorch

Constrained optimization under uncertainty for decision-making problems: Application to Real-Time Strategy games


Title	Constrained optimization under uncertainty for decision-making problems: Application to Real-Time Strategy games
Authors	Valentin Antuori, Florian Richoux
Abstract	Decision-making problems can be modeled as combinatorial optimization problems with Constraint Programming formalisms such as Constrained Optimization Problems. However, few Constraint Programming formalisms can deal with both optimization and uncertainty at the same time, and none of them are convenient to model problems we tackle in this paper. Here, we propose a way to deal with combinatorial optimization problems under uncertainty within the classical Constrained Optimization Problems formalism by injecting the Rank Dependent Utility from decision theory. We also propose a proof of concept of our method to show it is implementable and can solve concrete decision-making problems using a regular constraint solver, and propose a bot that won the partially observable track of the 2018 {\mu}RTS AI competition. Our result shows it is possible to handle uncertainty with regular Constraint Programming solvers, without having to define a new formalism neither to develop dedicated solvers. This brings new perspective to tackle uncertainty in Constraint Programming.
Tasks	Combinatorial Optimization, Decision Making, Real-Time Strategy Games
Published	2019-01-03
URL	http://arxiv.org/abs/1901.00942v3
PDF	http://arxiv.org/pdf/1901.00942v3.pdf
PWC	https://paperswithcode.com/paper/constrained-optimization-under-uncertainty
Repo	https://github.com/richoux/microrts-uncertainty
Framework	none

Training individually fair ML models with Sensitive Subspace Robustness


Title	Training individually fair ML models with Sensitive Subspace Robustness
Authors	Mikhail Yurochkin, Amanda Bower, Yuekai Sun
Abstract	We consider training machine learning models that are fair in the sense that their performance is invariant under certain sensitive perturbations to the inputs. For example, the performance of a resume screening system should be invariant under changes to the gender and/or ethnicity of the applicant. We formalize this notion of algorithmic fairness as a variant of individual fairness and develop a distributionally robust optimization approach to enforce it during training. We also demonstrate the effectiveness of the approach on two ML tasks that are susceptible to gender and racial biases.
Tasks
Published	2019-06-28
URL	https://arxiv.org/abs/1907.00020v2
PDF	https://arxiv.org/pdf/1907.00020v2.pdf
PWC	https://paperswithcode.com/paper/learning-fair-predictors-with-sensitive
Repo	https://github.com/IBM/sensitive-subspace-robustness
Framework	none

Image Based Review Text Generation with Emotional Guidance


Title	Image Based Review Text Generation with Emotional Guidance
Authors	Xuehui Sun, Zihan Zhou, Yuda Fan
Abstract	In the current field of computer vision, automatically generating texts from given images has been a fully worked technique. Up till now, most works of this area focus on image content describing, namely image-captioning. However, rare researches focus on generating product review texts, which is ubiquitous in the online shopping malls and is crucial for online shopping selection and evaluation. Different from content describing, review texts include more subjective information of customers, which may bring difference to the results. Therefore, we aimed at a new field concerning generating review text from customers based on images together with the ratings of online shopping products, which appear as non-image attributes. We made several adjustments to the existing image-captioning model to fit our task, in which we should also take non-image features into consideration. We also did experiments based on our model and get effective primary results.
Tasks	Image Captioning, Text Generation
Published	2019-01-14
URL	http://arxiv.org/abs/1901.04140v1
PDF	http://arxiv.org/pdf/1901.04140v1.pdf
PWC	https://paperswithcode.com/paper/image-based-review-text-generation-with
Repo	https://github.com/footoredo/image-based-review-text-generation
Framework	none

Learned Step Size Quantization


Title	Learned Step Size Quantization
Authors	Steven K. Esser, Jeffrey L. McKinstry, Deepika Bablani, Rathinakumar Appuswamy, Dharmendra S. Modha
Abstract	Deep networks run with low precision operations at inference time offer power and space advantages over high precision alternatives, but need to overcome the challenge of maintaining high accuracy as precision decreases. Here, we present a method for training such networks, Learned Step Size Quantization, that achieves the highest accuracy to date on the ImageNet dataset when using models, from a variety of architectures, with weights and activations quantized to 2-, 3- or 4-bits of precision, and that can train 3-bit models that reach full precision baseline accuracy. Our approach builds upon existing methods for learning weights in quantized networks by improving how the quantizer itself is configured. Specifically, we introduce a novel means to estimate and scale the task loss gradient at each weight and activation layer’s quantizer step size, such that it can be learned in conjunction with other network parameters. This approach works using different levels of precision as needed for a given system and requires only a simple modification of existing training code.
Tasks	Quantization
Published	2019-02-21
URL	https://arxiv.org/abs/1902.08153v2
PDF	https://arxiv.org/pdf/1902.08153v2.pdf
PWC	https://paperswithcode.com/paper/learned-step-size-quantization
Repo	https://github.com/phuocphn/lsq-net
Framework	pytorch

Decoupling feature extraction from policy learning: assessing benefits of state representation learning in goal based robotics


Title	Decoupling feature extraction from policy learning: assessing benefits of state representation learning in goal based robotics
Authors	Antonin Raffin, Ashley Hill, René Traoré, Timothée Lesort, Natalia Díaz-Rodríguez, David Filliat
Abstract	Scaling end-to-end reinforcement learning to control real robots from vision presents a series of challenges, in particular in terms of sample efficiency. Against end-to-end learning, state representation learning can help learn a compact, efficient and relevant representation of states that speeds up policy learning, reducing the number of samples needed, and that is easier to interpret. We evaluate several state representation learning methods on goal based robotics tasks and propose a new unsupervised model that stacks representations and combines strengths of several of these approaches. This method encodes all the relevant features, performs on par or better than end-to-end learning with better sample efficiency, and is robust to hyper-parameters change.
Tasks	Representation Learning
Published	2019-01-24
URL	https://arxiv.org/abs/1901.08651v3
PDF	https://arxiv.org/pdf/1901.08651v3.pdf
PWC	https://paperswithcode.com/paper/decoupling-feature-extraction-from-policy
Repo	https://github.com/araffin/robotics-rl-srl
Framework	none