April 1, 2020

2968 words 14 mins read

Paper Group ANR 465

The Automated Inspection of Opaque Liquid Vaccines. ZSTAD: Zero-Shot Temporal Activity Detection. Higher order co-occurrence tensors for hypergraphs via face-splitting. Scan2Plan: Efficient Floorplan Generation from 3D Scans of Indoor Scenes. It’s Not What Machines Can Learn, It’s What We Cannot Teach. Multi-Graph Convolution Collaborative Filterin …

The Automated Inspection of Opaque Liquid Vaccines


Title	The Automated Inspection of Opaque Liquid Vaccines
Authors	Gregory Palmer, Benjamin Schnieders, Rahul Savani, Karl Tuyls, Joscha-David Fossel, Harry Flore
Abstract	In the pharmaceutical industry the screening of opaque vaccines containing suspensions is currently a manual task carried out by trained human visual inspectors. We show that deep learning can be used to effectively automate this process. A moving contrast is required to distinguish anomalies from other particles, reflections and dust resting on a vial’s surface. We train 3D-ConvNets to predict the likelihood of 20-frame video samples containing anomalies. Our unaugmented dataset consists of hand-labelled samples, recorded using vials provided by the HAL Allergy Group, a pharmaceutical company. We trained ten randomly initialized 3D-ConvNets to provide a benchmark, observing mean AUROC scores of 0.94 and 0.93 for positive samples (containing anomalies) and negative (anomaly-free) samples, respectively. Using Frame-Completion Generative Adversarial Networks we: (i) introduce an algorithm for computing saliency maps, which we use to verify that the 3D-ConvNets are indeed identifying anomalies; (ii) propose a novel self-training approach using the saliency maps to determine if multiple networks agree on the location of anomalies. Our self-training approach allows us to augment our data set by labelling 217,888 additional samples. 3D-ConvNets trained with our augmented dataset improve on the results we get when we train only on the unaugmented dataset.
Tasks
Published	2020-02-21
URL	https://arxiv.org/abs/2002.09406v1
PDF	https://arxiv.org/pdf/2002.09406v1.pdf
PWC	https://paperswithcode.com/paper/the-automated-inspection-of-opaque-liquid
Repo
Framework

ZSTAD: Zero-Shot Temporal Activity Detection


Title	ZSTAD: Zero-Shot Temporal Activity Detection
Authors	Lingling Zhang, Xiaojun Chang, Jun Liu, Minnan Luo, Sen Wang, Zongyuan Ge, Alexander Hauptmann
Abstract	An integral part of video analysis and surveillance is temporal activity detection, which means to simultaneously recognize and localize activities in long untrimmed videos. Currently, the most effective methods of temporal activity detection are based on deep learning, and they typically perform very well with large scale annotated videos for training. However, these methods are limited in real applications due to the unavailable videos about certain activity classes and the time-consuming data annotation. To solve this challenging problem, we propose a novel task setting called zero-shot temporal activity detection (ZSTAD), where activities that have never been seen in training can still be detected. We design an end-to-end deep network based on R-C3D as the architecture for this solution. The proposed network is optimized with an innovative loss function that considers the embeddings of activity labels and their super-classes while learning the common semantics of seen and unseen activities. Experiments on both the THUMOS14 and the Charades datasets show promising performance in terms of detecting unseen activities.
Tasks	Action Detection, Activity Detection
Published	2020-03-12
URL	https://arxiv.org/abs/2003.05583v1
PDF	https://arxiv.org/pdf/2003.05583v1.pdf
PWC	https://paperswithcode.com/paper/zstad-zero-shot-temporal-activity-detection
Repo
Framework

Higher order co-occurrence tensors for hypergraphs via face-splitting


Title	Higher order co-occurrence tensors for hypergraphs via face-splitting
Authors	Bryan Bischof
Abstract	A popular trick for computing a pairwise co-occurrence matrix is the product of an incidence matrix and its transpose. We present an analog for higher order tuple co-occurrences using the face-splitting product, or alternately known as the transpose Khatri-Rao product. These higher order co-occurrences encode the commonality of tokens in the company of other tokens, and thus generalize the mutual information commonly studied. We demonstrate this tensor’s use via a popular NLP model, and hypergraph models of similarity.
Tasks
Published	2020-02-15
URL	https://arxiv.org/abs/2002.06285v1
PDF	https://arxiv.org/pdf/2002.06285v1.pdf
PWC	https://paperswithcode.com/paper/higher-order-co-occurrence-tensors-for
Repo
Framework

Scan2Plan: Efficient Floorplan Generation from 3D Scans of Indoor Scenes


Title	Scan2Plan: Efficient Floorplan Generation from 3D Scans of Indoor Scenes
Authors	Ameya Phalak, Vijay Badrinarayanan, Andrew Rabinovich
Abstract	We introduce Scan2Plan, a novel approach for accurate estimation of a floorplan from a 3D scan of the structural elements of indoor environments. The proposed method incorporates a two-stage approach where the initial stage clusters an unordered point cloud representation of the scene into room instances and wall instances using a deep neural network based voting approach. The subsequent stage estimates a closed perimeter, parameterized by a simple polygon, for each individual room by finding the shortest path along the predicted room and wall keypoints. The final floorplan is simply an assembly of all such room perimeters in the global co-ordinate system. The Scan2Plan pipeline produces accurate floorplans for complex layouts, is highly parallelizable and extremely efficient compared to existing methods. The voting module is trained only on synthetic data and evaluated on publicly available Structured3D and BKE datasets to demonstrate excellent qualitative and quantitative results outperforming state-of-the-art techniques.
Tasks
Published	2020-03-16
URL	https://arxiv.org/abs/2003.07356v1
PDF	https://arxiv.org/pdf/2003.07356v1.pdf
PWC	https://paperswithcode.com/paper/scan2plan-efficient-floorplan-generation-from
Repo
Framework

It’s Not What Machines Can Learn, It’s What We Cannot Teach


Title	It’s Not What Machines Can Learn, It’s What We Cannot Teach
Authors	Gal Yehuda, Moshe Gabel, Assaf Schuster
Abstract	Can deep neural networks learn to solve any task, and in particular problems of high complexity? This question attracts a lot of interest, with recent works tackling computationally hard tasks such as the traveling salesman problem and satisfiability. In this work we offer a different perspective on this question. Given the common assumption that $\textit{NP} \neq \textit{coNP}$ we prove that any polynomial-time sample generator for an $\textit{NP}$-hard problem samples, in fact, from an easier sub-problem. We empirically explore a case study, Conjunctive Query Containment, and show how common data generation techniques generate biased datasets that lead practitioners to over-estimate model accuracy. Our results suggest that machine learning approaches that require training on a dense uniform sampling from the target distribution cannot be used to solve computationally hard problems, the reason being the difficulty of generating sufficiently large and unbiased training sets.
Tasks
Published	2020-02-21
URL	https://arxiv.org/abs/2002.09398v1
PDF	https://arxiv.org/pdf/2002.09398v1.pdf
PWC	https://paperswithcode.com/paper/its-not-what-machines-can-learn-its-what-we
Repo
Framework

Multi-Graph Convolution Collaborative Filtering


Title	Multi-Graph Convolution Collaborative Filtering
Authors	Jianing Sun, Yingxue Zhang, Chen Ma, Mark Coates, Huifeng Guo, Ruiming Tang, Xiuqiang He
Abstract	Personalized recommendation is ubiquitous, playing an important role in many online services. Substantial research has been dedicated to learning vector representations of users and items with the goal of predicting a user’s preference for an item based on the similarity of the representations. Techniques range from classic matrix factorization to more recent deep learning based methods. However, we argue that existing methods do not make full use of the information that is available from user-item interaction data and the similarities between user pairs and item pairs. In this work, we develop a graph convolution-based recommendation framework, named Multi-Graph Convolution Collaborative Filtering (Multi-GCCF), which explicitly incorporates multiple graphs in the embedding learning process. Multi-GCCF not only expressively models the high-order information via a partite user-item interaction graph, but also integrates the proximal information by building and processing user-user and item-item graphs. Furthermore, we consider the intrinsic difference between user nodes and item nodes when performing graph convolution on the bipartite graph. We conduct extensive experiments on four publicly accessible benchmarks, showing significant improvements relative to several state-of-the-art collaborative filtering and graph neural network-based recommendation models. Further experiments quantitatively verify the effectiveness of each component of our proposed model and demonstrate that the learned embeddings capture the important relationship structure.
Tasks
Published	2020-01-01
URL	https://arxiv.org/abs/2001.00267v1
PDF	https://arxiv.org/pdf/2001.00267v1.pdf
PWC	https://paperswithcode.com/paper/multi-graph-convolution-collaborative
Repo
Framework

Learned Enrichment of Top-View Grid Maps Improves Object Detection


Title	Learned Enrichment of Top-View Grid Maps Improves Object Detection
Authors	Sascha Wirges, Ye Yang, Sven Richter, Haohao Hu, Christoph Stiller
Abstract	We propose an object detector for top-view grid maps which is additionally trained to generate an enriched version of its input. Our goal in the joint model is to improve generalization by regularizing towards structural knowledge in form of a map fused from multiple adjacent range sensor measurements. This training data can be generated in an automatic fashion, thus does not require manual annotations. We present an evidential framework to generate training data, investigate different model architectures and show that predicting enriched inputs as an additional task can improve object detection performance.
Tasks	Object Detection
Published	2020-03-02
URL	https://arxiv.org/abs/2003.00710v2
PDF	https://arxiv.org/pdf/2003.00710v2.pdf
PWC	https://paperswithcode.com/paper/learned-enrichment-of-top-view-grid-maps
Repo
Framework

Efficient, Effective and Well Justified Estimation of Active Nodes within a Cluster


Title	Efficient, Effective and Well Justified Estimation of Active Nodes within a Cluster
Authors	Md Mahmudul Hasan, Shuangqing Wei, Ramachandran Vaidyanathan
Abstract	Reliable and efficient estimation of the size of a dynamically changing cluster in an IoT network is critical in its nominal operation. Most previous estimation schemes worked with relatively smaller frame size and large number of rounds. Here we propose a new estimator named \textquotedblleft Gaussian Estimator of Active Nodes,\textquotedblright (GEAN), that works with large enough frame size under which testing statistics is well approximated as a Gaussian variable, thereby requiring less number of frames, and thus less total number of channel slots to attain a desired accuracy in estimation. More specifically, the selection of the frame size is done according to Triangular Array Central Limit Theorem which also enables us to quantify the approximation error. Larger frame size helps the statistical average to converge faster to the ensemble mean of the estimator and the quantification of the approximation error helps to determine the number of rounds to keep up with the accuracy requirements. We present the analysis of our scheme under two different channel models i.e. $ {0,1 } $ and $ {0,1,e } $, whereas all previous schemes worked only under $ {0,1 } $ channel model. The overall performance of GEAN is better than the previously proposed schemes considering the number of slots required for estimation to achieve a given level of estimation accuracy.
Tasks
Published	2020-01-26
URL	https://arxiv.org/abs/2001.09494v1
PDF	https://arxiv.org/pdf/2001.09494v1.pdf
PWC	https://paperswithcode.com/paper/efficient-effective-and-well-justified
Repo
Framework

Neural network wave functions and the sign problem


Title	Neural network wave functions and the sign problem
Authors	Attila Szabó, Claudio Castelnovo
Abstract	Neural quantum states (NQS) are a promising approach to study many-body quantum physics. However, they face a major challenge when applied to lattice models: Convolutional networks struggle to converge to ground states with a nontrivial sign structure. We tackle this problem by proposing a neural network architecture with a simple, explicit, and interpretable phase ansatz, which can robustly represent such states and achieve state-of-the-art variational energies for both conventional and frustrated antiferromagnets. In the latter case, our approach uncovers low-energy states that exhibit the Marshall sign rule and are therefore inconsistent with the expected ground state. Such states are the likely cause of the obstruction for NQS-based variational Monte Carlo to access the true ground states of these systems. We discuss the implications of this observation and suggest potential strategies to overcome the problem.
Tasks
Published	2020-02-11
URL	https://arxiv.org/abs/2002.04613v2
PDF	https://arxiv.org/pdf/2002.04613v2.pdf
PWC	https://paperswithcode.com/paper/neural-network-wave-functions-and-the-sign
Repo
Framework

Following Instructions by Imagining and Reaching Visual Goals


Title	Following Instructions by Imagining and Reaching Visual Goals
Authors	John Kanu, Eadom Dessalene, Xiaomin Lin, Cornelia Fermuller, Yiannis Aloimonos
Abstract	While traditional methods for instruction-following typically assume prior linguistic and perceptual knowledge, many recent works in reinforcement learning (RL) have proposed learning policies end-to-end, typically by training neural networks to map joint representations of observations and instructions directly to actions. In this work, we present a novel framework for learning to perform temporally extended tasks using spatial reasoning in the RL framework, by sequentially imagining visual goals and choosing appropriate actions to fulfill imagined goals. Our framework operates on raw pixel images, assumes no prior linguistic or perceptual knowledge, and learns via intrinsic motivation and a single extrinsic reward signal measuring task completion. We validate our method in two environments with a robot arm in a simulated interactive 3D environment. Our method outperforms two flat architectures with raw-pixel and ground-truth states, and a hierarchical architecture with ground-truth states on object arrangement tasks.
Tasks
Published	2020-01-25
URL	https://arxiv.org/abs/2001.09373v1
PDF	https://arxiv.org/pdf/2001.09373v1.pdf
PWC	https://paperswithcode.com/paper/following-instructions-by-imagining-and
Repo
Framework

Adaptive Direction-Guided Structure Tensor Total Variation


Title	Adaptive Direction-Guided Structure Tensor Total Variation
Authors	Ezgi Demircan-Tureyen, Mustafa E. Kamasak
Abstract	Direction-guided structure tensor total variation (DSTV) is a recently proposed regularization term that aims at increasing the sensitivity of the structure tensor total variation (STV) to the changes towards a predetermined direction. Despite of the plausible results obtained on the uni-directional images, the DSTV model is not applicable to the multi-directional images of real-world. In this study, we build a two-stage framework that brings adaptivity to DSTV. We design an alternative to STV, which encodes the first-order information within a local neighborhood under the guidance of spatially varying directional descriptors (i.e., orientation and the dose of anisotropy). In order to estimate those descriptors, we propose an efficient preprocessor that captures the local geometry based on the structure tensor. Through the extensive experiments, we demonstrate how beneficial the involvement of the directional information in STV is, by comparing the proposed method with the state-of-the-art analysis-based denoising models, both in terms of restoration quality and computational efficiency.
Tasks	Art Analysis, Denoising
Published	2020-01-16
URL	https://arxiv.org/abs/2001.05717v1
PDF	https://arxiv.org/pdf/2001.05717v1.pdf
PWC	https://paperswithcode.com/paper/adaptive-direction-guided-structure-tensor
Repo
Framework

Blockchain-based Smart-IoT Trust Zone Measurement Architecture


Title	Blockchain-based Smart-IoT Trust Zone Measurement Architecture
Authors	Jawad Ali, Toqeer Ali, Yazed Alsaawy, Ahmad Shahrafidz Khalid, Shahrulniza Musa
Abstract	With a rapid growth in the IT industry, Internet of Things (IoT) has gained a tremendous attention and become a central aspect of our environment. In IoT the things (devices) communicate and exchange the data without the act of human intervention. Such autonomy and proliferation of IoT ecosystem make the devices more vulnerable to attacks. In this paper, we propose a behavior monitor in IoT-Blockchain setup which can provide trust-confidence to outside networks. Behavior monitor extracts the activity of each device and analyzes the behavior using deep auto-encoders. In addition, we also incorporate Trusted Execution Technology (Intel SGX) in order to provide a secure execution environment for applications and data on blockchain. Finally, in evaluation we analyze three IoT devices data that is infected by mirai attack. The evaluation results demonstrate the ability of our proposed method in terms of accuracy and time required for detection.
Tasks
Published	2020-01-08
URL	https://arxiv.org/abs/2001.03002v1
PDF	https://arxiv.org/pdf/2001.03002v1.pdf
PWC	https://paperswithcode.com/paper/blockchain-based-smart-iot-trust-zone
Repo
Framework

Robust Optimization for Fairness with Noisy Protected Groups


Title	Robust Optimization for Fairness with Noisy Protected Groups
Authors	Serena Wang, Wenshuo Guo, Harikrishna Narasimhan, Andrew Cotter, Maya Gupta, Michael I. Jordan
Abstract	Many existing fairness criteria for machine learning involve equalizing or achieving some metric across \textit{protected groups} such as race or gender groups. However, practitioners trying to audit or enforce such group-based criteria can easily face the problem of noisy or biased protected group information. We study this important practical problem in two ways. First, we study the consequences of na{"i}vely only relying on noisy protected groups: we provide an upper bound on the fairness violations on the true groups $G$ when the fairness criteria are satisfied on noisy groups $\hat{G}$. Second, we introduce two new approaches using robust optimization that, unlike the na{"i}ve approach of only relying on $\hat{G}$, are guaranteed to satisfy fairness criteria on the true protected groups $G$ while minimizing a training objective. We provide theoretical guarantees that one such approach converges to an optimal feasible solution. Using two case studies, we empirically show that the robust approaches achieve better true group fairness guarantees than the na{"i}ve approach.
Tasks
Published	2020-02-21
URL	https://arxiv.org/abs/2002.09343v1
PDF	https://arxiv.org/pdf/2002.09343v1.pdf
PWC	https://paperswithcode.com/paper/robust-optimization-for-fairness-with-noisy
Repo
Framework

Edge-based sequential graph generation with recurrent neural networks


Title	Edge-based sequential graph generation with recurrent neural networks
Authors	Davide Bacciu, Alessio Micheli, Marco Podda
Abstract	Graph generation with Machine Learning is an open problem with applications in various research fields. In this work, we propose to cast the generative process of a graph into a sequential one, relying on a node ordering procedure. We use this sequential process to design a novel generative model composed of two recurrent neural networks that learn to predict the edges of graphs: the first network generates one endpoint of each edge, while the second network generates the other endpoint conditioned on the state of the first. We test our approach extensively on five different datasets, comparing with two well-known baselines coming from graph literature, and two recurrent approaches, one of which holds state of the art performances. Evaluation is conducted considering quantitative and qualitative characteristics of the generated samples. Results show that our approach is able to yield novel, and unique graphs originating from very different distributions, while retaining structural properties very similar to those in the training sample. Under the proposed evaluation framework, our approach is able to reach performances comparable to the current state of the art on the graph generation task.
Tasks	Graph Generation
Published	2020-01-31
URL	https://arxiv.org/abs/2002.00102v1
PDF	https://arxiv.org/pdf/2002.00102v1.pdf
PWC	https://paperswithcode.com/paper/edge-based-sequential-graph-generation-with
Repo
Framework

Spatial Pyramid Based Graph Reasoning for Semantic Segmentation


Title	Spatial Pyramid Based Graph Reasoning for Semantic Segmentation
Authors	Xia Li, Yibo Yang, Qijie Zhao, Tiancheng Shen, Zhouchen Lin, Hong Liu
Abstract	The convolution operation suffers from a limited receptive filed, while global modeling is fundamental to dense prediction tasks, such as semantic segmentation. In this paper, we apply graph convolution into the semantic segmentation task and propose an improved Laplacian. The graph reasoning is directly performed in the original feature space organized as a spatial pyramid. Different from existing methods, our Laplacian is data-dependent and we introduce an attention diagonal matrix to learn a better distance metric. It gets rid of projecting and re-projecting processes, which makes our proposed method a light-weight module that can be easily plugged into current computer vision architectures. More importantly, performing graph reasoning directly in the feature space retains spatial relationships and makes spatial pyramid possible to explore multiple long-range contextual patterns from different scales. Experiments on Cityscapes, COCO Stuff, PASCAL Context and PASCAL VOC demonstrate the effectiveness of our proposed methods on semantic segmentation. We achieve comparable performance with advantages in computational and memory overhead.
Tasks	Semantic Segmentation
Published	2020-03-23
URL	https://arxiv.org/abs/2003.10211v1
PDF	https://arxiv.org/pdf/2003.10211v1.pdf
PWC	https://paperswithcode.com/paper/spatial-pyramid-based-graph-reasoning-for
Repo
Framework