February 2, 2020

3437 words 17 mins read

Paper Group AWR 23

CenterMask : Real-Time Anchor-Free Instance Segmentation. Real-time Evasion Attacks with Physical Constraints on Deep Learning-based Anomaly Detectors in Industrial Control Systems. SG-NN: Sparse Generative Neural Networks for Self-Supervised Scene Completion of RGB-D Scans. Defending Against Neural Fake News. Deep Kernel Transfer in Gaussian Proce …

CenterMask : Real-Time Anchor-Free Instance Segmentation


Title	CenterMask : Real-Time Anchor-Free Instance Segmentation
Authors	Youngwan Lee, Jongyoul Park
Abstract	We propose a simple yet efficient anchor-free instance segmentation, called CenterMask, that adds a novel spatial attention-guided mask (SAG-Mask) branch to anchor-free one stage object detector (FCOS) in the same vein with Mask R-CNN. Plugged into the FCOS object detector, the SAG-Mask branch predicts a segmentation mask on each box with the spatial attention map that helps to focus on informative pixels and suppress noise. We also present an improved backbone networks, VoVNetV2, with two effective strategies: (1) residual connection for alleviating the optimization problem of larger VoVNet \cite{lee2019energy} and (2) effective Squeeze-Excitation (eSE) dealing with the channel information loss problem of original SE. With SAG-Mask and VoVNetV2, we deign CenterMask and CenterMask-Lite that are targeted to large and small models, respectively. Using the same ResNet-101-FPN backbone, CenterMask achieves 38.3%, surpassing all previous state-of-the-art methods while at a much faster speed. CenterMask-Lite also outperforms the state-of-the-art by large margins at over 35fps on Titan Xp. We hope that CenterMask and VoVNetV2 can serve as a solid baseline of real-time instance segmentation and backbone network for various vision tasks, respectively. The Code is available at https://github.com/youngwanLEE/CenterMask.
Tasks	Instance Segmentation, Object Detection, Panoptic Segmentation, Real-time Instance Segmentation, Real-Time Object Detection, Semantic Segmentation
Published	2019-11-15
URL	https://arxiv.org/abs/1911.06667v5
PDF	https://arxiv.org/pdf/1911.06667v5.pdf
PWC	https://paperswithcode.com/paper/centermask-real-time-anchor-free-instance-1
Repo	https://github.com/youngwanLEE/centermask2
Framework	pytorch

Real-time Evasion Attacks with Physical Constraints on Deep Learning-based Anomaly Detectors in Industrial Control Systems


Title	Real-time Evasion Attacks with Physical Constraints on Deep Learning-based Anomaly Detectors in Industrial Control Systems
Authors	Alessandro Erba, Riccardo Taormina, Stefano Galelli, Marcello Pogliani, Michele Carminati, Stefano Zanero, Nils Ole Tippenhauer
Abstract	Recently, a number of deep learning-based anomaly detection algorithms were proposed to detect attacks in dynamic industrial control systems. The detectors operate on measured sensor data, leveraging physical process models learned a priori. Evading detection by such systems is challenging, as an attacker needs to manipulate a constrained number of sensor readings in real-time with realistic perturbations according to the current state of the system. In this work, we propose a number of evasion attacks (with different assumptions on the attacker’s knowledge), and compare the attacks’ cost and efficiency against replay attacks. In particular, we show that a replay attack on a subset of sensor values can be detected easily as it violates physical constraints. In contrast, our proposed attacks leverage manipulated sensor readings that observe learned physical constraints of the system. Our proposed white box attacker uses an optimization approach with a detection oracle, while our black box attacker uses an autoencoder (or a convolutional neural network) to translate anomalous data into normal data. Our proposed approaches are implemented and evaluated on two different datasets pertaining to the domain of water distribution networks. We then demonstrated the efficacy of the real-time attack on a realistic testbed. Results show that the accuracy of the detection algorithms can be significantly reduced through real-time adversarial actions: for the BATADAL dataset, the attacker can reduce the detection accuracy from 0.6 to 0.14. In addition, we discuss and implement an Availability attack, in which the attacker introduces detection events with minimal changes of the reported data, in order to reduce confidence in the detector.
Tasks	Anomaly Detection
Published	2019-07-17
URL	https://arxiv.org/abs/1907.07487v2
PDF	https://arxiv.org/pdf/1907.07487v2.pdf
PWC	https://paperswithcode.com/paper/real-time-evasion-attacks-with-physical
Repo	https://github.com/scy-phy/ICS-Evasion-Attacks
Framework	tf

SG-NN: Sparse Generative Neural Networks for Self-Supervised Scene Completion of RGB-D Scans


Title	SG-NN: Sparse Generative Neural Networks for Self-Supervised Scene Completion of RGB-D Scans
Authors	Angela Dai, Christian Diller, Matthias Nießner
Abstract	We present a novel approach that converts partial and noisy RGB-D scans into high-quality 3D scene reconstructions by inferring unobserved scene geometry. Our approach is fully self-supervised and can hence be trained solely on real-world, incomplete scans. To achieve self-supervision, we remove frames from a given (incomplete) 3D scan in order to make it even more incomplete; self-supervision is then formulated by correlating the two levels of partialness of the same scan while masking out regions that have never been observed. Through generalization across a large training set, we can then predict 3D scene completion without ever seeing any 3D scan of entirely complete geometry. Combined with a new 3D sparse generative neural network architecture, our method is able to predict highly-detailed surfaces in a coarse-to-fine hierarchical fashion, generating 3D scenes at 2cm resolution, more than twice the resolution of existing state-of-the-art methods as well as outperforming them by a significant margin in reconstruction quality.
Tasks
Published	2019-11-29
URL	https://arxiv.org/abs/1912.00036v2
PDF	https://arxiv.org/pdf/1912.00036v2.pdf
PWC	https://paperswithcode.com/paper/sg-nn-sparse-generative-neural-networks-for
Repo	https://github.com/angeladai/sgnn
Framework	pytorch

Defending Against Neural Fake News


Title	Defending Against Neural Fake News
Authors	Rowan Zellers, Ari Holtzman, Hannah Rashkin, Yonatan Bisk, Ali Farhadi, Franziska Roesner, Yejin Choi
Abstract	Recent progress in natural language generation has raised dual-use concerns. While applications like summarization and translation are positive, the underlying technology also might enable adversaries to generate neural fake news: targeted propaganda that closely mimics the style of real news. Modern computer security relies on careful threat modeling: identifying potential threats and vulnerabilities from an adversary’s point of view, and exploring potential mitigations to these threats. Likewise, developing robust defenses against neural fake news requires us first to carefully investigate and characterize the risks of these models. We thus present a model for controllable text generation called Grover. Given a headline like `Link Found Between Vaccines and Autism,’ Grover can generate the rest of the article; humans find these generations to be more trustworthy than human-written disinformation. Developing robust verification techniques against generators like Grover is critical. We find that best current discriminators can classify neural fake news from real, human-written, news with 73% accuracy, assuming access to a moderate level of training data. Counterintuitively, the best defense against Grover turns out to be Grover itself, with 92% accuracy, demonstrating the importance of public release of strong generators. We investigate these results further, showing that exposure bias – and sampling strategies that alleviate its effects – both leave artifacts that similar discriminators can pick up on. We conclude by discussing ethical issues regarding the technology, and plan to release Grover publicly, helping pave the way for better detection of neural fake news. \|
Tasks	Fake News Detection, Text Generation
Published	2019-05-29
URL	https://arxiv.org/abs/1905.12616v2
PDF	https://arxiv.org/pdf/1905.12616v2.pdf
PWC	https://paperswithcode.com/paper/defending-against-neural-fake-news
Repo	https://github.com/rowanz/grover
Framework	tf

Deep Kernel Transfer in Gaussian Processes for Few-shot Learning


Title	Deep Kernel Transfer in Gaussian Processes for Few-shot Learning
Authors	Massimiliano Patacchiola, Jack Turner, Elliot J. Crowley, Michael O’Boyle, Amos Storkey
Abstract	Humans tackle new problems by making inferences that go far beyond the information available, reusing what they have previously learned, and weighing different alternatives in the face of uncertainty. Incorporating these abilities in an artificial system is a major objective in machine learning. Towards this goal, we adapt Gaussian Processes (GPs) to tackle the problem of few-shot learning. We propose a simple, yet effective variant of deep kernel learning in which the kernel is transferred across tasks, which we call deep kernel transfer. This approach is straightforward to implement, provides uncertainty quantification, and does not require estimation of task-specific parameters. We empirically demonstrate that the proposed method outperforms several state-of-the-art algorithms in few-shot regression, classification, and cross-domain adaptation.
Tasks	Bayesian Inference, Domain Adaptation, Few-Shot Image Classification, Few-Shot Learning, few-shot regression, Gaussian Processes
Published	2019-10-11
URL	https://arxiv.org/abs/1910.05199v2
PDF	https://arxiv.org/pdf/1910.05199v2.pdf
PWC	https://paperswithcode.com/paper/deep-kernel-transfer-in-gaussian-processes
Repo	https://github.com/hhl60492/deep-kernel-transfer
Framework	pytorch

Mapping Hearthstone Deck Spaces through MAP-Elites with Sliding Boundaries


Title	Mapping Hearthstone Deck Spaces through MAP-Elites with Sliding Boundaries
Authors	Matthew C. Fontaine, Scott Lee, L. B. Soros, Fernando De Mesentier Silva, Julian Togelius, Amy K. Hoover
Abstract	Quality diversity (QD) algorithms such as MAP-Elites have emerged as a powerful alternative to traditional single-objective optimization methods. They were initially applied to evolutionary robotics problems such as locomotion and maze navigation, but have yet to see widespread application. We argue that these algorithms are perfectly suited to the rich domain of video games, which contains many relevant problems with a multitude of successful strategies and often also multiple dimensions along which solutions can vary. This paper introduces a novel modification of the MAP-Elites algorithm called MAP-Elites with Sliding Boundaries (MESB) and applies it to the design and rebalancing of Hearthstone, a popular collectible card game chosen for its number of multidimensional behavior features relevant to particular styles of play. To avoid overpopulating cells with conflated behaviors, MESB slides the boundaries of cells based on the distribution of evolved individuals. Experiments in this paper demonstrate the performance of MESB in Hearthstone. Results suggest MESB finds diverse ways of playing the game well along the selected behavioral dimensions. Further analysis of the evolved strategies reveals common patterns that recur across behavioral dimensions and explores how MESB can help rebalance the game.
Tasks
Published	2019-04-24
URL	http://arxiv.org/abs/1904.10656v1
PDF	http://arxiv.org/pdf/1904.10656v1.pdf
PWC	https://paperswithcode.com/paper/mapping-hearthstone-deck-spaces-through-map
Repo	https://github.com/DanieleGravina/divergence-and-quality-diversity
Framework	none

Modeling Fluency and Faithfulness for Diverse Neural Machine Translation


Title	Modeling Fluency and Faithfulness for Diverse Neural Machine Translation
Authors	Yang Feng, Wanying Xie, Shuhao Gu, Chenze Shao, Wen Zhang, Zhengxin Yang, Dong Yu
Abstract	Neural machine translation models usually adopt the teacher forcing strategy for training which requires the predicted sequence matches ground truth word by word and forces the probability of each prediction to approach a 0-1 distribution. However, the strategy casts all the portion of the distribution to the ground truth word and ignores other words in the target vocabulary even when the ground truth word cannot dominate the distribution. To address the problem of teacher forcing, we propose a method to introduce an evaluation module to guide the distribution of the prediction. The evaluation module accesses each prediction from the perspectives of fluency and faithfulness to encourage the model to generate the word which has a fluent connection with its past and future translation and meanwhile tends to form a translation equivalent in meaning to the source. The experiments on multiple translation tasks show that our method can achieve significant improvements over strong baselines.
Tasks	Machine Translation
Published	2019-11-30
URL	https://arxiv.org/abs/1912.00178v1
PDF	https://arxiv.org/pdf/1912.00178v1.pdf
PWC	https://paperswithcode.com/paper/modeling-fluency-and-faithfulness-for-diverse
Repo	https://github.com/ictnlp/DiverseNMT
Framework	pytorch

Learning 3D Human Shape and Pose from Dense Body Parts


Title	Learning 3D Human Shape and Pose from Dense Body Parts
Authors	Hongwen Zhang, Jie Cao, Guo Lu, Wanli Ouyang, Zhenan Sun
Abstract	Reconstructing 3D human shape and pose from a monocular image is challenging despite the promising results achieved by the most recent learning-based methods. The commonly occurred misalignment comes from the facts that the mapping from images to the model space is highly non-linear and the rotation-based pose representation of the body model is prone to result in the drift of joint positions. In this work, we investigate learning 3D human shape and pose from dense correspondences of body parts and propose a Decompose-and-aggregate Network (DaNet) to address these issues. DaNet adopts the dense correspondence maps, which densely build a bridge between 2D pixels and 3D vertexes, as intermediate representations to facilitate the learning of 2D-to-3D mapping. The prediction modules of DaNet are decomposed into one global stream and multiple local streams to enable global and fine-grained perceptions for the shape and pose predictions, respectively. Messages from local streams are further aggregated to enhance the robust prediction of the rotation-based poses, where a position-aided rotation feature refinement strategy is proposed to exploit spatial relationships between body joints. Moreover, a Part-based Dropout (PartDrop) strategy is introduced to drop out dense information from intermediate representations during training, encouraging the network to focus on more complementary body parts as well as adjacent position features. The effectiveness of our method is validated on both in-door and real-world datasets including the Human3.6M, UP3D, and DensePose-COCO datasets. Experimental results show that the proposed method significantly improves the reconstruction performance in comparison with previous state-of-the-art methods. Our code will be made publicly available at https://hongwenzhang.github.io/dense2mesh .
Tasks
Published	2019-12-31
URL	https://arxiv.org/abs/1912.13344v1
PDF	https://arxiv.org/pdf/1912.13344v1.pdf
PWC	https://paperswithcode.com/paper/learning-3d-human-shape-and-pose-from-dense
Repo	https://github.com/chingswy/HumanPoseMemo
Framework	pytorch

Momentum Contrast for Unsupervised Visual Representation Learning


Title	Momentum Contrast for Unsupervised Visual Representation Learning
Authors	Kaiming He, Haoqi Fan, Yuxin Wu, Saining Xie, Ross Girshick
Abstract	We present Momentum Contrast (MoCo) for unsupervised visual representation learning. From a perspective on contrastive learning as dictionary look-up, we build a dynamic dictionary with a queue and a moving-averaged encoder. This enables building a large and consistent dictionary on-the-fly that facilitates contrastive unsupervised learning. MoCo provides competitive results under the common linear protocol on ImageNet classification. More importantly, the representations learned by MoCo transfer well to downstream tasks. MoCo can outperform its supervised pre-training counterpart in 7 detection/segmentation tasks on PASCAL VOC, COCO, and other datasets, sometimes surpassing it by large margins. This suggests that the gap between unsupervised and supervised representation learning has been largely closed in many vision tasks.
Tasks	Representation Learning, Self-Supervised Image Classification
Published	2019-11-13
URL	https://arxiv.org/abs/1911.05722v3
PDF	https://arxiv.org/pdf/1911.05722v3.pdf
PWC	https://paperswithcode.com/paper/momentum-contrast-for-unsupervised-visual
Repo	https://github.com/ppwwyyxx/moco.tensorflow
Framework	tf

Disfluencies and Human Speech Transcription Errors


Title	Disfluencies and Human Speech Transcription Errors
Authors	Vicky Zayats, Trang Tran, Richard Wright, Courtney Mansfield, Mari Ostendorf
Abstract	This paper explores contexts associated with errors in transcrip-tion of spontaneous speech, shedding light on human perceptionof disfluencies and other conversational speech phenomena. Anew version of the Switchboard corpus is provided with disfluency annotations for careful speech transcripts, together with results showing the impact of transcription errors on evaluation of automatic disfluency detection.
Tasks
Published	2019-04-08
URL	http://arxiv.org/abs/1904.04398v1
PDF	http://arxiv.org/pdf/1904.04398v1.pdf
PWC	https://paperswithcode.com/paper/disfluencies-and-human-speech-transcription
Repo	https://github.com/vickyzayats/switchboard_corrected_reannotated
Framework	none

Learning under Model Misspecification: Applications to Variational and Ensemble methods


Title	Learning under Model Misspecification: Applications to Variational and Ensemble methods
Authors	Andres R. Masegosa
Abstract	This paper provides a novel theoretical analysis of the problem of learning from i.i.d. data under model misspecification. To analyze this problem, we build on PAC-Bayes and second-order Jensen bounds. We then show that Bayesian model averaging is not an optimal method for learning under these settings because it does not properly optimize the generalization performance of the posterior predictive distribution over unseen data samples. Based on these insights, we introduce novel variational and ensemble learning methods based on the (approximate) minimization of a novel family of second-order PAC-Bayes bounds over the generalization performance of the posterior predictive. This theoretical analysis provides novel explanations of why diversity is key for the performance of model averaging methods. Experiments on toy and real data sets with Bayesian neural networks illustrate these learning algorithms.
Tasks
Published	2019-12-18
URL	https://arxiv.org/abs/1912.08335v3
PDF	https://arxiv.org/pdf/1912.08335v3.pdf
PWC	https://paperswithcode.com/paper/learning-from-iid-data-under-model-miss
Repo	https://github.com/PGM-Lab/PAC2BAYES
Framework	none

A Unified Framework for Random Forest Prediction Error Estimation


Title	A Unified Framework for Random Forest Prediction Error Estimation
Authors	Benjamin Lu, Johanna Hardin
Abstract	We introduce a unified framework for random forest prediction error estimation based on a novel estimator of the conditional prediction error distribution function. Our framework enables immediate estimation of key parameters often of interest, including conditional mean squared prediction errors, conditional biases, and conditional quantiles, by a straightforward plug-in routine. Our approach is particularly well-adapted for prediction interval estimation, which has received less attention in the random forest literature despite its practical utility; we show via simulations that our proposed prediction intervals are competitive with, and in some settings outperform, existing methods. To establish theoretical grounding for our framework, we prove pointwise uniform consistency of a more stringent version of our estimator of the conditional prediction error distribution. In addition to providing a suite of measures of prediction uncertainty, our general framework is applicable to many variants of the random forest algorithm. The estimators introduced here are implemented in the R package forestError.
Tasks
Published	2019-12-16
URL	https://arxiv.org/abs/1912.07435v2
PDF	https://arxiv.org/pdf/1912.07435v2.pdf
PWC	https://paperswithcode.com/paper/a-unified-framework-for-random-forest
Repo	https://github.com/benjilu/forestError
Framework	none

What do AI algorithms actually learn? - On false structures in deep learning


Title	What do AI algorithms actually learn? - On false structures in deep learning
Authors	Laura Thesing, Vegard Antun, Anders C. Hansen
Abstract	There are two big unsolved mathematical questions in artificial intelligence (AI): (1) Why is deep learning so successful in classification problems and (2) why are neural nets based on deep learning at the same time universally unstable, where the instabilities make the networks vulnerable to adversarial attacks. We present a solution to these questions that can be summed up in two words; false structures. Indeed, deep learning does not learn the original structures that humans use when recognising images (cats have whiskers, paws, fur, pointy ears, etc), but rather different false structures that correlate with the original structure and hence yield the success. However, the false structure, unlike the original structure, is unstable. The false structure is simpler than the original structure, hence easier to learn with less data and the numerical algorithm used in the training will more easily converge to the neural network that captures the false structure. We formally define the concept of false structures and formulate the solution as a conjecture. Given that trained neural networks always are computed with approximations, this conjecture can only be established through a combination of theoretical and computational results similar to how one establishes a postulate in theoretical physics (e.g. the speed of light is constant). Establishing the conjecture fully will require a vast research program characterising the false structures. We provide the foundations for such a program establishing the existence of the false structures in practice. Finally, we discuss the far reaching consequences the existence of the false structures has on state-of-the-art AI and Smale’s 18th problem.
Tasks
Published	2019-06-04
URL	https://arxiv.org/abs/1906.01478v1
PDF	https://arxiv.org/pdf/1906.01478v1.pdf
PWC	https://paperswithcode.com/paper/what-do-ai-algorithms-actually-learn-on-false
Repo	https://github.com/vegarant/false_structures
Framework	tf

Deep Feature Selection using a Teacher-Student Network


Title	Deep Feature Selection using a Teacher-Student Network
Authors	Ali Mirzaei, Vahid Pourahmadi, Mehran Soltani, Hamid Sheikhzadeh
Abstract	High-dimensional data in many machine learning applications leads to computational and analytical complexities. Feature selection provides an effective way for solving these problems by removing irrelevant and redundant features, thus reducing model complexity and improving accuracy and generalization capability of the model. In this paper, we present a novel teacher-student feature selection (TSFS) method in which a ‘teacher’ (a deep neural network or a complicated dimension reduction method) is first employed to learn the best representation of data in low dimension. Then a ‘student’ network (a simple neural network) is used to perform feature selection by minimizing the reconstruction error of low dimensional representation. Although the teacher-student scheme is not new, to the best of our knowledge, it is the first time that this scheme is employed for feature selection. The proposed TSFS can be used for both supervised and unsupervised feature selection. This method is evaluated on different datasets and is compared with state-of-the-art existing feature selection methods. The results show that TSFS performs better in terms of classification and clustering accuracies and reconstruction error. Moreover, experimental evaluations demonstrate a low degree of sensitivity to parameter selection in the proposed method.
Tasks	Dimensionality Reduction, Feature Selection
Published	2019-03-17
URL	http://arxiv.org/abs/1903.07045v1
PDF	http://arxiv.org/pdf/1903.07045v1.pdf
PWC	https://paperswithcode.com/paper/deep-feature-selection-using-a-teacher
Repo	https://github.com/alimirzaei/TSFS
Framework	none

An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detection


Title	An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detection
Authors	Youngwan Lee, Joong-won Hwang, Sangrok Lee, Yuseok Bae, Jongyoul Park
Abstract	As DenseNet conserves intermediate features with diverse receptive fields by aggregating them with dense connection, it shows good performance on the object detection task. Although feature reuse enables DenseNet to produce strong features with a small number of model parameters and FLOPs, the detector with DenseNet backbone shows rather slow speed and low energy efficiency. We find the linearly increasing input channel by dense connection leads to heavy memory access cost, which causes computation overhead and more energy consumption. To solve the inefficiency of DenseNet, we propose an energy and computation efficient architecture called VoVNet comprised of One-Shot Aggregation (OSA). The OSA not only adopts the strength of DenseNet that represents diversified features with multi receptive fields but also overcomes the inefficiency of dense connection by aggregating all features only once in the last feature maps. To validate the effectiveness of VoVNet as a backbone network, we design both lightweight and large-scale VoVNet and apply them to one-stage and two-stage object detectors. Our VoVNet based detectors outperform DenseNet based ones with 2x faster speed and the energy consumptions are reduced by 1.6x - 4.1x. In addition to DenseNet, VoVNet also outperforms widely used ResNet backbone with faster speed and better energy efficiency. In particular, the small object detection performance has been significantly improved over DenseNet and ResNet.
Tasks	Object Detection, Real-Time Object Detection, Semantic Segmentation, Small Object Detection
Published	2019-04-22
URL	http://arxiv.org/abs/1904.09730v1
PDF	http://arxiv.org/pdf/1904.09730v1.pdf
PWC	https://paperswithcode.com/paper/an-energy-and-gpu-computation-efficient
Repo	https://github.com/2anchao/VovJpu
Framework	pytorch