October 16, 2019

3294 words 16 mins read

Paper Group ANR 1040

DeepGauge: Multi-Granularity Testing Criteria for Deep Learning Systems. Adversarial Extreme Multi-label Classification. Loss Functions, Axioms, and Peer Review. Learning and Generalizing Motion Primitives from Driving Data for Path-Tracking Applications. WikiConv: A Corpus of the Complete Conversational History of a Large Online Collaborative Comm …

DeepGauge: Multi-Granularity Testing Criteria for Deep Learning Systems


Title	DeepGauge: Multi-Granularity Testing Criteria for Deep Learning Systems
Authors	Lei Ma, Felix Juefei-Xu, Fuyuan Zhang, Jiyuan Sun, Minhui Xue, Bo Li, Chunyang Chen, Ting Su, Li Li, Yang Liu, Jianjun Zhao, Yadong Wang
Abstract	Deep learning (DL) defines a new data-driven programming paradigm that constructs the internal system logic of a crafted neuron network through a set of training data. We have seen wide adoption of DL in many safety-critical scenarios. However, a plethora of studies have shown that the state-of-the-art DL systems suffer from various vulnerabilities which can lead to severe consequences when applied to real-world applications. Currently, the testing adequacy of a DL system is usually measured by the accuracy of test data. Considering the limitation of accessible high quality test data, good accuracy performance on test data can hardly provide confidence to the testing adequacy and generality of DL systems. Unlike traditional software systems that have clear and controllable logic and functionality, the lack of interpretability in a DL system makes system analysis and defect detection difficult, which could potentially hinder its real-world deployment. In this paper, we propose DeepGauge, a set of multi-granularity testing criteria for DL systems, which aims at rendering a multi-faceted portrayal of the testbed. The in-depth evaluation of our proposed testing criteria is demonstrated on two well-known datasets, five DL systems, and with four state-of-the-art adversarial attack techniques against DL. The potential usefulness of DeepGauge sheds light on the construction of more generic and robust DL systems.
Tasks	Adversarial Attack
Published	2018-03-20
URL	http://arxiv.org/abs/1803.07519v4
PDF	http://arxiv.org/pdf/1803.07519v4.pdf
PWC	https://paperswithcode.com/paper/deepgauge-multi-granularity-testing-criteria
Repo
Framework

Adversarial Extreme Multi-label Classification


Title	Adversarial Extreme Multi-label Classification
Authors	Rohit Babbar, Bernhard Schölkopf
Abstract	The goal in extreme multi-label classification is to learn a classifier which can assign a small subset of relevant labels to an instance from an extremely large set of target labels. Datasets in extreme classification exhibit a long tail of labels which have small number of positive training instances. In this work, we pose the learning task in extreme classification with large number of tail-labels as learning in the presence of adversarial perturbations. This view motivates a robust optimization framework and equivalence to a corresponding regularized objective. Under the proposed robustness framework, we demonstrate efficacy of Hamming loss for tail-label detection in extreme classification. The equivalent regularized objective, in combination with proximal gradient based optimization, performs better than state-of-the-art methods on propensity scored versions of precision@k and nDCG@k(upto 20% relative improvement over PFastreXML - a leading tree-based approach and 60% relative improvement over SLEEC - a leading label-embedding approach). Furthermore, we also highlight the sub-optimality of a sparse solver in a widely used package for large-scale linear classification, which is interesting in its own right. We also investigate the spectral properties of label graphs for providing novel insights towards understanding the conditions governing the performance of Hamming loss based one-vs-rest scheme vis-`a-vis label embedding methods.
Tasks	Extreme Multi-Label Classification, Multi-Label Classification
Published	2018-03-05
URL	http://arxiv.org/abs/1803.01570v1
PDF	http://arxiv.org/pdf/1803.01570v1.pdf
PWC	https://paperswithcode.com/paper/adversarial-extreme-multi-label
Repo
Framework

Loss Functions, Axioms, and Peer Review


Title	Loss Functions, Axioms, and Peer Review
Authors	Ritesh Noothigattu, Nihar B. Shah, Ariel D. Procaccia
Abstract	It is common to see a handful of reviewers reject a highly novel paper, because they view, say, extensive experiments as far more important than novelty, whereas the community as a whole would have embraced the paper. More generally, the disparate mapping of criteria scores to final recommendations by different reviewers is a major source of inconsistency in peer review. In this paper we present a framework inspired by empirical risk minimization (ERM) for learning the community’s aggregate mapping. The key challenge that arises is the specification of a loss function for ERM. We consider the class of $L(p,q)$ loss functions, which is a matrix-extension of the standard class of $L_p$ losses on vectors; here the choice of the loss function amounts to choosing the hyperparameters $p, q \in [1,\infty]$. To deal with the absence of ground truth in our problem, we instead draw on computational social choice to identify desirable values of the hyperparameters $p$ and $q$. Specifically, we characterize $p=q=1$ as the only choice of these hyperparameters that satisfies three natural axiomatic properties. Finally, we implement and apply our approach to reviews from IJCAI 2017.
Tasks
Published	2018-08-27
URL	https://arxiv.org/abs/1808.09057v2
PDF	https://arxiv.org/pdf/1808.09057v2.pdf
PWC	https://paperswithcode.com/paper/choosing-how-to-choose-papers
Repo
Framework

Learning and Generalizing Motion Primitives from Driving Data for Path-Tracking Applications


Title	Learning and Generalizing Motion Primitives from Driving Data for Path-Tracking Applications
Authors	Boyang Wang, Zirui Li, Jianwei Gong, Yidi Liu, Huiyan Chen, Chao Lu
Abstract	Considering the driving habits which are learned from the naturalistic driving data in the path-tracking system can significantly improve the acceptance of intelligent vehicles. Therefore, the goal of this paper is to generate the prediction results of lateral commands with confidence regions according to the reference based on the learned motion primitives. We present a two-level structure for learning and generalizing motion primitives through demonstrations. The lower-level motion primitives are generated under the path segmentation and clustering layer in the upper-level. The Gaussian Mixture Model(GMM) is utilized to represent the primitives and Gaussian Mixture Regression (GMR) is selected to generalize the motion primitives. We show how the upper-level can help to improve the prediction accuracy and evaluate the influence of different time scales and the number of Gaussian components. The model is trained and validated by using the driving data collected from the Beijing Institute of Technology (BIT) intelligent vehicle platform. Experiment results show that the proposed method can extract the motion primitives from the driving data and predict the future lateral control commands with high accuracy.
Tasks
Published	2018-06-02
URL	http://arxiv.org/abs/1806.00711v2
PDF	http://arxiv.org/pdf/1806.00711v2.pdf
PWC	https://paperswithcode.com/paper/learning-and-generalizing-motion-primitives
Repo
Framework

WikiConv: A Corpus of the Complete Conversational History of a Large Online Collaborative Community


Title	WikiConv: A Corpus of the Complete Conversational History of a Large Online Collaborative Community
Authors	Yiqing Hua, Cristian Danescu-Niculescu-Mizil, Dario Taraborelli, Nithum Thain, Jeffery Sorensen, Lucas Dixon
Abstract	We present a corpus that encompasses the complete history of conversations between contributors to Wikipedia, one of the largest online collaborative communities. By recording the intermediate states of conversations—including not only comments and replies, but also their modifications, deletions and restorations—this data offers an unprecedented view of online conversation. This level of detail supports new research questions pertaining to the process (and challenges) of large-scale online collaboration. We illustrate the corpus’ potential with two case studies that highlight new perspectives on earlier work. First, we explore how a person’s conversational behavior depends on how they relate to the discussion’s venue. Second, we show that community moderation of toxic behavior happens at a higher rate than previously estimated. Finally the reconstruction framework is designed to be language agnostic, and we show that it can extract high quality conversational data in both Chinese and English.
Tasks
Published	2018-10-31
URL	http://arxiv.org/abs/1810.13181v1
PDF	http://arxiv.org/pdf/1810.13181v1.pdf
PWC	https://paperswithcode.com/paper/wikiconv-a-corpus-of-the-complete
Repo
Framework

Dropout-based Active Learning for Regression


Title	Dropout-based Active Learning for Regression
Authors	Evgenii Tsymbalov, Maxim Panov, Alexander Shapeev
Abstract	Active learning is relevant and challenging for high-dimensional regression models when the annotation of the samples is expensive. Yet most of the existing sampling methods cannot be applied to large-scale problems, consuming too much time for data processing. In this paper, we propose a fast active learning algorithm for regression, tailored for neural network models. It is based on uncertainty estimation from stochastic dropout output of the network. Experiments on both synthetic and real-world datasets show comparable or better performance (depending on the accuracy metric) as compared to the baselines. This approach can be generalized to other deep learning architectures. It can be used to systematically improve a machine-learning model as it offers a computationally efficient way of sampling additional data.
Tasks	Active Learning
Published	2018-06-26
URL	http://arxiv.org/abs/1806.09856v2
PDF	http://arxiv.org/pdf/1806.09856v2.pdf
PWC	https://paperswithcode.com/paper/dropout-based-active-learning-for-regression
Repo
Framework

NRC-Canada at SMM4H Shared Task: Classifying Tweets Mentioning Adverse Drug Reactions and Medication Intake


Title	NRC-Canada at SMM4H Shared Task: Classifying Tweets Mentioning Adverse Drug Reactions and Medication Intake
Authors	Svetlana Kiritchenko, Saif M. Mohammad, Jason Morin, Berry de Bruijn
Abstract	Our team, NRC-Canada, participated in two shared tasks at the AMIA-2017 Workshop on Social Media Mining for Health Applications (SMM4H): Task 1 - classification of tweets mentioning adverse drug reactions, and Task 2 - classification of tweets describing personal medication intake. For both tasks, we trained Support Vector Machine classifiers using a variety of surface-form, sentiment, and domain-specific features. With nine teams participating in each task, our submissions ranked first on Task 1 and third on Task 2. Handling considerable class imbalance proved crucial for Task 1. We applied an under-sampling technique to reduce class imbalance (from about 1:10 to 1:2). Standard n-gram features, n-grams generalized over domain terms, as well as general-domain and domain-specific word embeddings had a substantial impact on the overall performance in both tasks. On the other hand, including sentiment lexicon features did not result in any improvement.
Tasks	Word Embeddings
Published	2018-05-11
URL	http://arxiv.org/abs/1805.04558v1
PDF	http://arxiv.org/pdf/1805.04558v1.pdf
PWC	https://paperswithcode.com/paper/nrc-canada-at-smm4h-shared-task-classifying
Repo
Framework

Joint registration and synthesis using a probabilistic model for alignment of MRI and histological sections


Title	Joint registration and synthesis using a probabilistic model for alignment of MRI and histological sections
Authors	Juan Eugenio Iglesias, Marc Modat, Loic Peter, Allison Stevens, Roberto Annunziata, Tom Vercauteren, Ed Lein, Bruce Fischl, Sebastien Ourselin
Abstract	Nonlinear registration of 2D histological sections with corresponding slices of MRI data is a critical step of 3D histology reconstruction. This task is difficult due to the large differences in image contrast and resolution, as well as the complex nonrigid distortions produced when sectioning the sample and mounting it on the glass slide. It has been shown in brain MRI registration that better spatial alignment across modalities can be obtained by synthesizing one modality from the other and then using intra-modality registration metrics, rather than by using mutual information (MI) as metric. However, such an approach typically requires a database of aligned images from the two modalities, which is very difficult to obtain for histology/MRI. Here, we overcome this limitation with a probabilistic method that simultaneously solves for registration and synthesis directly on the target images, without any training data. In our model, the MRI slice is assumed to be a contrast-warped, spatially deformed version of the histological section. We use approximate Bayesian inference to iteratively refine the probabilistic estimate of the synthesis and the registration, while accounting for each other’s uncertainty. Moreover, manually placed landmarks can be seamlessly integrated in the framework for increased performance. Experiments on a synthetic dataset show that, compared with MI, the proposed method makes it possible to use a much more flexible deformation model in the registration to improve its accuracy, without compromising robustness. Moreover, our framework also exploits information in manually placed landmarks more efficiently than MI, since landmarks inform both synthesis and registration - as opposed to registration alone. Finally, we show qualitative results on the public Allen atlas, in which the proposed method provides a clear improvement over MI based registration.
Tasks	Bayesian Inference
Published	2018-01-16
URL	http://arxiv.org/abs/1801.05284v1
PDF	http://arxiv.org/pdf/1801.05284v1.pdf
PWC	https://paperswithcode.com/paper/joint-registration-and-synthesis-using-a
Repo
Framework

Spatial Logics and Model Checking for Medical Imaging (Extended Version)


Title	Spatial Logics and Model Checking for Medical Imaging (Extended Version)
Authors	Fabrizio Banci Buonamici, Gina Belmonte, Vincenzo Ciancia, Diego Latella, Mieke Massink
Abstract	Recent research on spatial and spatio-temporal model checking provides novel image analysis methodologies, rooted in logical methods for topological spaces. Medical Imaging (MI) is a field where such methods show potential for ground-breaking innovation. Our starting point is SLCS, the Spatial Logic for Closure Spaces – Closure Spaces being a generalisation of topological spaces, covering also discrete space structures – and topochecker, a model-checker for SLCS (and extensions thereof). We introduce the logical language ImgQL (“Image Query Language”). ImgQL extends SLCS with logical operators describing distance and region similarity. The spatio-temporal model checker topochecker is correspondingly enhanced with state-of-the-art algorithms, borrowed from computational image processing, for efficient implementation of distancebased operators, namely distance transforms. Similarity between regions is defined by means of a statistical similarity operator, based on notions from statistical texture analysis. We illustrate our approach by means of two examples of analysis of Magnetic Resonance images: segmentation of glioblastoma and its oedema, and segmentation of rectal carcinoma.
Tasks	Texture Classification
Published	2018-11-14
URL	http://arxiv.org/abs/1811.06065v1
PDF	http://arxiv.org/pdf/1811.06065v1.pdf
PWC	https://paperswithcode.com/paper/spatial-logics-and-model-checking-for-medical
Repo
Framework

Early Fusion for Goal Directed Robotic Vision


Title	Early Fusion for Goal Directed Robotic Vision
Authors	Aaron Walsman, Yonatan Bisk, Saadia Gabriel, Dipendra Misra, Yoav Artzi, Yejin Choi, Dieter Fox
Abstract	Building perceptual systems for robotics which perform well under tight computational budgets requires novel architectures which rethink the traditional computer vision pipeline. Modern vision architectures require the agent to build a summary representation of the entire scene, even if most of the input is irrelevant to the agent’s current goal. In this work, we flip this paradigm, by introducing EarlyFusion vision models that condition on a goal to build custom representations for downstream tasks. We show that these goal specific representations can be learned more quickly, are substantially more parameter efficient, and more robust than existing attention mechanisms in our domain. We demonstrate the effectiveness of these methods on a simulated robotic item retrieval problem that is trained in a fully end-to-end manner via imitation learning.
Tasks	Imitation Learning
Published	2018-11-21
URL	https://arxiv.org/abs/1811.08824v3
PDF	https://arxiv.org/pdf/1811.08824v3.pdf
PWC	https://paperswithcode.com/paper/early-fusion-for-goal-directed-robotic-vision
Repo
Framework

NestDNN: Resource-Aware Multi-Tenant On-Device Deep Learning for Continuous Mobile Vision


Title	NestDNN: Resource-Aware Multi-Tenant On-Device Deep Learning for Continuous Mobile Vision
Authors	Biyi Fang, Xiao Zeng, Mi Zhang
Abstract	Mobile vision systems such as smartphones, drones, and augmented-reality headsets are revolutionizing our lives. These systems usually run multiple applications concurrently and their available resources at runtime are dynamic due to events such as starting new applications, closing existing applications, and application priority changes. In this paper, we present NestDNN, a framework that takes the dynamics of runtime resources into account to enable resource-aware multi-tenant on-device deep learning for mobile vision systems. NestDNN enables each deep learning model to offer flexible resource-accuracy trade-offs. At runtime, it dynamically selects the optimal resource-accuracy trade-off for each deep learning model to fit the model’s resource demand to the system’s available runtime resources. In doing so, NestDNN efficiently utilizes the limited resources in mobile vision systems to jointly maximize the performance of all the concurrently running applications. Our experiments show that compared to the resource-agnostic status quo approach, NestDNN achieves as much as 4.2% increase in inference accuracy, 2.0x increase in video frame processing rate and 1.7x reduction on energy consumption.
Tasks
Published	2018-10-23
URL	http://arxiv.org/abs/1810.10090v1
PDF	http://arxiv.org/pdf/1810.10090v1.pdf
PWC	https://paperswithcode.com/paper/nestdnn-resource-aware-multi-tenant-on-device
Repo
Framework

Batch Selection for Parallelisation of Bayesian Quadrature


Title	Batch Selection for Parallelisation of Bayesian Quadrature
Authors	Ed Wagstaff, Saad Hamid, Michael Osborne
Abstract	Integration over non-negative integrands is a central problem in machine learning (e.g. for model averaging, (hyper-)parameter marginalisation, and computing posterior predictive distributions). Bayesian Quadrature is a probabilistic numerical integration technique that performs promisingly when compared to traditional Markov Chain Monte Carlo methods. However, in contrast to easily-parallelised MCMC methods, Bayesian Quadrature methods have, thus far, been essentially serial in nature, selecting a single point to sample at each step of the algorithm. We deliver methods to select batches of points at each step, based upon those recently presented in the Batch Bayesian Optimisation literature. Such parallelisation significantly reduces computation time, especially when the integrand is expensive to sample.
Tasks	Bayesian Optimisation
Published	2018-12-04
URL	http://arxiv.org/abs/1812.01553v1
PDF	http://arxiv.org/pdf/1812.01553v1.pdf
PWC	https://paperswithcode.com/paper/batch-selection-for-parallelisation-of
Repo
Framework

SGD and Hogwild! Convergence Without the Bounded Gradients Assumption


Title	SGD and Hogwild! Convergence Without the Bounded Gradients Assumption
Authors	Lam M. Nguyen, Phuong Ha Nguyen, Marten van Dijk, Peter Richtárik, Katya Scheinberg, Martin Takáč
Abstract	Stochastic gradient descent (SGD) is the optimization algorithm of choice in many machine learning applications such as regularized empirical risk minimization and training deep neural networks. The classical convergence analysis of SGD is carried out under the assumption that the norm of the stochastic gradient is uniformly bounded. While this might hold for some loss functions, it is always violated for cases where the objective function is strongly convex. In (Bottou et al.,2016), a new analysis of convergence of SGD is performed under the assumption that stochastic gradients are bounded with respect to the true gradient norm. Here we show that for stochastic problems arising in machine learning such bound always holds; and we also propose an alternative convergence analysis of SGD with diminishing learning rate regime, which results in more relaxed conditions than those in (Bottou et al.,2016). We then move on the asynchronous parallel setting, and prove convergence of Hogwild! algorithm in the same regime, obtaining the first convergence results for this method in the case of diminished learning rate.
Tasks
Published	2018-02-11
URL	http://arxiv.org/abs/1802.03801v2
PDF	http://arxiv.org/pdf/1802.03801v2.pdf
PWC	https://paperswithcode.com/paper/sgd-and-hogwild-convergence-without-the
Repo
Framework

Semi-convolutional Operators for Instance Segmentation


Title	Semi-convolutional Operators for Instance Segmentation
Authors	David Novotny, Samuel Albanie, Diane Larlus, Andrea Vedaldi
Abstract	Object detection and instance segmentation are dominated by region-based methods such as Mask RCNN. However, there is a growing interest in reducing these problems to pixel labeling tasks, as the latter could be more efficient, could be integrated seamlessly in image-to-image network architectures as used in many other tasks, and could be more accurate for objects that are not well approximated by bounding boxes. In this paper we show theoretically and empirically that constructing dense pixel embeddings that can separate object instances cannot be easily achieved using convolutional operators. At the same time, we show that simple modifications, which we call semi-convolutional, have a much better chance of succeeding at this task. We use the latter to show a connection to Hough voting as well as to a variant of the bilateral kernel that is spatially steered by a convolutional network. We demonstrate that these operators can also be used to improve approaches such as Mask RCNN, demonstrating better segmentation of complex biological shapes and PASCAL VOC categories than achievable by Mask RCNN alone.
Tasks	Instance Segmentation, Object Detection, Semantic Segmentation
Published	2018-07-27
URL	http://arxiv.org/abs/1807.10712v1
PDF	http://arxiv.org/pdf/1807.10712v1.pdf
PWC	https://paperswithcode.com/paper/semi-convolutional-operators-for-instance
Repo
Framework

Operator-in-the-Loop Deep Sequential Multi-camera Feature Fusion for Person Re-identification


Title	Operator-in-the-Loop Deep Sequential Multi-camera Feature Fusion for Person Re-identification
Authors	K L Navaneet, Ravi Kiran Sarvadevabhatla, Shashank Shekhar, R. Venkatesh Babu, Anirban Chakraborty
Abstract	Given a target image as query, person re-identification systems retrieve a ranked list of candidate matches on a per-camera basis. In deployed systems, a human operator scans these lists and labels sighted targets by touch or mouse-based selection. However, classical re-id approaches generate per-camera lists independently. Therefore, target identifications by operator in a subset of cameras cannot be utilized to improve ranking of the target in remaining set of network cameras. To address this shortcoming, we propose a novel sequential multi-camera re-id approach. The proposed approach can accommodate human operator inputs and provides early gains via a monotonic improvement in target ranking. At the heart of our approach is a fusion function which operates on deep feature representations of query and candidate matches. We formulate an optimization procedure custom-designed to incrementally improve query representation. Since existing evaluation methods cannot be directly adopted to our setting, we also propose two novel evaluation protocols. The results on two large-scale re-id datasets (Market-1501, DukeMTMC-reID) demonstrate that our multi-camera method significantly outperforms baselines and other popular feature fusion schemes. Additionally, we conduct a comparative subject-based study of human operator performance. The superior operator performance enabled by our approach makes a compelling case for its integration into deployable video-surveillance systems.
Tasks	Person Re-Identification
Published	2018-07-19
URL	https://arxiv.org/abs/1807.07295v4
PDF	https://arxiv.org/pdf/1807.07295v4.pdf
PWC	https://paperswithcode.com/paper/operator-in-the-loop-deep-sequential-multi
Repo
Framework