January 30, 2020

3096 words 15 mins read

Paper Group ANR 456

Learning Backtrackless Aligned-Spatial Graph Convolutional Networks for Graph Classification. PAG-Net: Progressive Attention Guided Depth Super-resolution Network. Eye-based Continuous Affect Prediction. Fast Task-Aware Architecture Inference. SRM : A Style-based Recalibration Module for Convolutional Neural Networks. Scalable Variational Gaussian …

Learning Backtrackless Aligned-Spatial Graph Convolutional Networks for Graph Classification


Title	Learning Backtrackless Aligned-Spatial Graph Convolutional Networks for Graph Classification
Authors	Lu Bail, Lixin Cui, Yuhang Jiao, Luca Rossi, Edwin R. Hancock
Abstract	In this paper, we develop a novel Backtrackless Aligned-Spatial Graph Convolutional Network (BASGCN) model to learn effective features for graph classification. Our idea is to transform arbitrary-sized graphs into fixed-sized backtrackless aligned grid structures and define a new spatial graph convolution operation associated with the grid structures. We show that the proposed BASGCN model not only reduces the problems of information loss and imprecise information representation arising in existing spatially-based Graph Convolutional Network (GCN) models, but also bridges the theoretical gap between traditional Convolutional Neural Network (CNN) models and spatially-based GCN models. Furthermore, the proposed BASGCN model can both adaptively discriminate the importance between specified vertices during the convolution process and reduce the notorious tottering problem of existing spatially-based GCNs related to the Weisfeiler-Lehman algorithm, explaining the effectiveness of the proposed model. Experiments on standard graph datasets demonstrate the effectiveness of the proposed model.
Tasks	Graph Classification
Published	2019-04-06
URL	https://arxiv.org/abs/1904.04238v2
PDF	https://arxiv.org/pdf/1904.04238v2.pdf
PWC	https://paperswithcode.com/paper/learning-aligned-spatial-graph-convolutional
Repo
Framework

PAG-Net: Progressive Attention Guided Depth Super-resolution Network


Title	PAG-Net: Progressive Attention Guided Depth Super-resolution Network
Authors	Arpit Bansal, Sankaraganesh Jonna, Rajiv R. Sahay
Abstract	In this paper, we propose a novel method for the challenging problem of guided depth map super-resolution, called PAGNet. It is based on residual dense networks and involves the attention mechanism to suppress the texture copying problem arises due to improper guidance by RGB images. The attention module mainly involves providing the spatial attention to guidance image based on the depth features. We evaluate the proposed trained models on test dataset and provide comparisons with the state-of-the-art depth super-resolution methods.
Tasks	Depth Map Super-Resolution, Super-Resolution
Published	2019-11-22
URL	https://arxiv.org/abs/1911.09878v1
PDF	https://arxiv.org/pdf/1911.09878v1.pdf
PWC	https://paperswithcode.com/paper/pag-net-progressive-attention-guided-depth
Repo
Framework

Eye-based Continuous Affect Prediction


Title	Eye-based Continuous Affect Prediction
Authors	Jonny O’Dwyer, Niall Murray, Ronan Flynn
Abstract	Eye-based information channels include the pupils, gaze, saccades, fixational movements, and numerous forms of eye opening and closure. Pupil size variation indicates cognitive load and emotion, while a person’s gaze direction is said to be congruent with the motivation to approach or avoid stimuli. The eyelids are involved in facial expressions that can encode basic emotions. Additionally, eye-based cues can have implications for human annotators of emotions or feelings. Despite these facts, the use of eye-based cues in affective computing is in its infancy, however, and this work is intended to start to address this. Eye-based feature sets, incorporating data from all of the aforementioned information channels, that can be estimated from video are proposed. Feature set refinement is provided by way of continuous arousal and valence learning and prediction experiments on the RECOLA validation set. The eye-based features are then combined with a speech feature set to provide confirmation of their usefulness and assess affect prediction performance compared with group-of-humans-level performance on the RECOLA test set. The core contribution of this paper, a refined eye-based feature set, is shown to provide benefits for affect prediction. It is hoped that this work stimulates further research into eye-based affective computing.
Tasks
Published	2019-07-23
URL	https://arxiv.org/abs/1907.09896v2
PDF	https://arxiv.org/pdf/1907.09896v2.pdf
PWC	https://paperswithcode.com/paper/eye-based-continuous-affect-prediction
Repo
Framework

Fast Task-Aware Architecture Inference


Title	Fast Task-Aware Architecture Inference
Authors	Efi Kokiopoulou, Anja Hauth, Luciano Sbaiz, Andrea Gesmundo, Gabor Bartok, Jesse Berent
Abstract	Neural architecture search has been shown to hold great promise towards the automation of deep learning. However in spite of its potential, neural architecture search remains quite costly. To this point, we propose a novel gradient-based framework for efficient architecture search by sharing information across several tasks. We start by training many model architectures on several related (training) tasks. When a new unseen task is presented, the framework performs architecture inference in order to quickly identify a good candidate architecture, before any model is trained on the new task. At the core of our framework lies a deep value network that can predict the performance of input architectures on a task by utilizing task meta-features and the previous model training experiments performed on related tasks. We adopt a continuous parametrization of the model architecture which allows for efficient gradient-based optimization. Given a new task, an effective architecture is quickly identified by maximizing the estimated performance with respect to the model architecture parameters with simple gradient ascent. It is key to point out that our goal is to achieve reasonable performance at the lowest cost. We provide experimental results showing the effectiveness of the framework despite its high computational efficiency.
Tasks	Neural Architecture Search
Published	2019-02-15
URL	http://arxiv.org/abs/1902.05781v1
PDF	http://arxiv.org/pdf/1902.05781v1.pdf
PWC	https://paperswithcode.com/paper/fast-task-aware-architecture-inference
Repo
Framework

SRM : A Style-based Recalibration Module for Convolutional Neural Networks


Title	SRM : A Style-based Recalibration Module for Convolutional Neural Networks
Authors	HyunJae Lee, Hyo-Eun Kim, Hyeonseob Nam
Abstract	Following the advance of style transfer with Convolutional Neural Networks (CNNs), the role of styles in CNNs has drawn growing attention from a broader perspective. In this paper, we aim to fully leverage the potential of styles to improve the performance of CNNs in general vision tasks. We propose a Style-based Recalibration Module (SRM), a simple yet effective architectural unit, which adaptively recalibrates intermediate feature maps by exploiting their styles. SRM first extracts the style information from each channel of the feature maps by style pooling, then estimates per-channel recalibration weight via channel-independent style integration. By incorporating the relative importance of individual styles into feature maps, SRM effectively enhances the representational ability of a CNN. The proposed module is directly fed into existing CNN architectures with negligible overhead. We conduct comprehensive experiments on general image recognition as well as tasks related to styles, which verify the benefit of SRM over recent approaches such as Squeeze-and-Excitation (SE). To explain the inherent difference between SRM and SE, we provide an in-depth comparison of their representational properties.
Tasks	Image Classification, Style Transfer
Published	2019-03-26
URL	http://arxiv.org/abs/1903.10829v1
PDF	http://arxiv.org/pdf/1903.10829v1.pdf
PWC	https://paperswithcode.com/paper/srm-a-style-based-recalibration-module-for
Repo
Framework

Scalable Variational Gaussian Processes for Crowdsourcing: Glitch Detection in LIGO


Title	Scalable Variational Gaussian Processes for Crowdsourcing: Glitch Detection in LIGO
Authors	Pablo Morales-Álvarez, Pablo Ruiz, Scott Coughlin, Rafael Molina, Aggelos K. Katsaggelos
Abstract	In the last years, crowdsourcing is transforming the way classification training sets are obtained. Instead of relying on a single expert annotator, crowdsourcing shares the labelling effort among a large number of collaborators. For instance, this is being applied to the data acquired by the laureate Laser Interferometer Gravitational Waves Observatory (LIGO), in order to detect glitches which might hinder the identification of true gravitational-waves. The crowdsourcing scenario poses new challenging difficulties, as it deals with different opinions from a heterogeneous group of annotators with unknown degrees of expertise. Probabilistic methods, such as Gaussian Processes (GP), have proven successful in modeling this setting. However, GPs do not scale well to large data sets, which hampers their broad adoption in real practice (in particular at LIGO). This has led to the recent introduction of deep learning based crowdsourcing methods, which have become the state-of-the-art. However, the accurate uncertainty quantification of GPs has been partially sacrificed. This is an important aspect for astrophysicists in LIGO, since a glitch detection system should provide very accurate probability distributions of its predictions. In this work, we leverage the most popular sparse GP approximation to develop a novel GP based crowdsourcing method that factorizes into mini-batches. This makes it able to cope with previously-prohibitive data sets. The approach, which we refer to as Scalable Variational Gaussian Processes for Crowdsourcing (SVGPCR), brings back GP-based methods to the state-of-the-art, and excels at uncertainty quantification. SVGPCR is shown to outperform deep learning based methods and previous probabilistic approaches when applied to the LIGO data. Moreover, its behavior and main properties are carefully analyzed in a controlled experiment based on the MNIST data set.
Tasks	Gaussian Processes
Published	2019-11-05
URL	https://arxiv.org/abs/1911.01915v1
PDF	https://arxiv.org/pdf/1911.01915v1.pdf
PWC	https://paperswithcode.com/paper/scalable-variational-gaussian-processes-for
Repo
Framework

Vector and Line Quantization for Billion-scale Similarity Search on GPUs


Title	Vector and Line Quantization for Billion-scale Similarity Search on GPUs
Authors	Wei Chen, Jincai Chen, Fuhao Zou, Yuan-Fang Li, Ping Lu, Qiang Wang, Wei Zhao
Abstract	Billion-scale high-dimensional approximate nearest neighbour (ANN) search has become an important problem for searching similar objects among the vast amount of images and videos available online. The existing ANN methods are usually characterized by their specific indexing structures, including the inverted index and the inverted multi-index structure. The inverted index structure is amenable to GPU-based implementations, and the state-of-the-art systems such as Faiss are able to exploit the massive parallelism offered by GPUs. However, the inverted index requires high memory overhead to index the dataset effectively. The inverted multi-index structure is difficult to implement for GPUs, and also ineffective in dealing with database with different data distributions. In this paper we propose a novel hierarchical inverted index structure generated by vector and line quantization methods. Our quantization method improves both search efficiency and accuracy, while maintaining comparable memory consumption. This is achieved by reducing search space and increasing the number of indexed regions. We introduce a new ANN search system, VLQ-ADC, that is based on the proposed inverted index, and perform extensive evaluation on two public billion-scale benchmark datasets SIFT1B and DEEP1B. Our evaluation shows that VLQ-ADC significantly outperforms the state-of-the-art GPU- and CPU-based systems in terms of both accuracy and search speed. The source code of VLQ-ADC is available at https://github.com/zjuchenwei/vector-line-quantization.
Tasks	Quantization
Published	2019-01-02
URL	http://arxiv.org/abs/1901.00275v2
PDF	http://arxiv.org/pdf/1901.00275v2.pdf
PWC	https://paperswithcode.com/paper/vector-and-line-quantization-for-billion
Repo
Framework

Single Pixel Reconstruction for One-stage Instance Segmentation


Title	Single Pixel Reconstruction for One-stage Instance Segmentation
Authors	Jun Yu, Jinghan Yao, Jian Zhang, Zhou Yu, Dacheng Tao
Abstract	Object instance segmentation is one of the most fundamental but challenging tasks in computer vision, and it requires the pixel-level image understanding. Most existing approaches address this problem by adding a mask prediction branch to a two-stage object detector with the Region Proposal Network (RPN). Although producing good segmentation results, the efficiency of these two-stage approaches is far from satisfactory, restricting their applicability in practice. In this paper, we propose a one-stage framework, SPRNet, which performs efficient instance segmentation by introducing a single pixel reconstruction (SPR) branch to off-the-shelf one-stage detectors. The added SPR branch reconstructs the pixel-level mask from every single pixel in the convolution feature map directly. Using the same ResNet-50 backbone, SPRNet achieves comparable mask AP to Mask R-CNN at a higher inference speed, and gains all-round improvements on box AP at every scale comparing with RetinaNet.
Tasks	Instance Segmentation, Semantic Segmentation
Published	2019-04-16
URL	https://arxiv.org/abs/1904.07426v3
PDF	https://arxiv.org/pdf/1904.07426v3.pdf
PWC	https://paperswithcode.com/paper/single-pixel-reconstruction-for-one-stage
Repo
Framework

The Riddle of Togelby


Title	The Riddle of Togelby
Authors	Daniel Ashlock, Christoph Salge
Abstract	At the 2017 Artificial and Computational Intelligence in Games meeting at Dagstuhl, Julian Togelius asked how to make spaces where every way of filling in the details yielded a good game. This study examines the possibility of enriching search spaces so that they contain very high rates of interesting objects, specifically game elements. While we do not answer the full challenge of finding good games throughout the space, this study highlights a number of potential avenues. These include naturally rich spaces, a simple technique for modifying a representation to search only rich parts of a larger search space, and representations that are highly expressive and so exhibit highly restricted and consequently enriched search spaces.
Tasks
Published	2019-06-10
URL	https://arxiv.org/abs/1906.03997v1
PDF	https://arxiv.org/pdf/1906.03997v1.pdf
PWC	https://paperswithcode.com/paper/the-riddle-of-togelby
Repo
Framework

Scalable Inference for Nonparametric Hawkes Process Using Pólya-Gamma Augmentation


Title	Scalable Inference for Nonparametric Hawkes Process Using Pólya-Gamma Augmentation
Authors	Feng Zhou, Zhidong Li, Xuhui Fan, Yang Wang, Arcot Sowmya, Fang Chen
Abstract	In this paper, we consider the sigmoid Gaussian Hawkes process model: the baseline intensity and triggering kernel of Hawkes process are both modeled as the sigmoid transformation of random trajectories drawn from Gaussian processes (GP). By introducing auxiliary latent random variables (branching structure, P'{o}lya-Gamma random variables and latent marked Poisson processes), the likelihood is converted to two decoupled components with a Gaussian form which allows for an efficient conjugate analytical inference. Using the augmented likelihood, we derive an expectation-maximization (EM) algorithm to obtain the maximum a posteriori (MAP) estimate. Furthermore, we extend the EM algorithm to an efficient approximate Bayesian inference algorithm: mean-field variational inference. We demonstrate the performance of two algorithms on simulated fictitious data. Experiments on real data show that our proposed inference algorithms can recover well the underlying prompting characteristics efficiently.
Tasks	Bayesian Inference, Gaussian Processes
Published	2019-10-29
URL	https://arxiv.org/abs/1910.13052v1
PDF	https://arxiv.org/pdf/1910.13052v1.pdf
PWC	https://paperswithcode.com/paper/scalable-inference-for-nonparametric-hawkes
Repo
Framework

Certified Data Removal from Machine Learning Models


Title	Certified Data Removal from Machine Learning Models
Authors	Chuan Guo, Tom Goldstein, Awni Hannun, Laurens van der Maaten
Abstract	Good data stewardship requires removal of data at the request of the data’s owner. This raises the question if and how a trained machine-learning model, which implicitly stores information about its training data, should be affected by such a removal request. Is it possible to “remove” data from a machine-learning model? We study this problem by defining certified removal: a very strong theoretical guarantee that a model from which data is removed cannot be distinguished from a model that never observed the data to begin with. We develop a certified-removal mechanism for linear classifiers and empirically study learning settings in which this mechanism is practical.
Tasks
Published	2019-11-08
URL	https://arxiv.org/abs/1911.03030v3
PDF	https://arxiv.org/pdf/1911.03030v3.pdf
PWC	https://paperswithcode.com/paper/certified-data-removal-from-machine-learning
Repo
Framework

Incremental Semantic Mapping with Unsupervised On-line Learning


Title	Incremental Semantic Mapping with Unsupervised On-line Learning
Authors	Ygor C. N. Sousa, Hansenclever F. Bassani
Abstract	This paper introduces an incremental semantic mapping approach, with on-line unsupervised learning, based on Self-Organizing Maps (SOM) for robotic agents. The method includes a mapping module, which incrementally creates a topological map of the environment, enriched with objects recognized around each topological node, and a module of places categorization, endowed with an incremental unsupervised learning SOM with on-line training. The proposed approach was tested in experiments with real-world data, in which it demonstrates promising capabilities of incremental acquisition of topological maps enriched with semantic information, and for clustering together similar places based on this information. The approach was also able to continue learning from newly visited environments without degrading the information previously learned.
Tasks
Published	2019-07-09
URL	https://arxiv.org/abs/1907.04001v2
PDF	https://arxiv.org/pdf/1907.04001v2.pdf
PWC	https://paperswithcode.com/paper/incremental-semantic-mapping-with
Repo
Framework

Beyond the proton drip line: Bayesian analysis of proton-emitting nuclei


Title	Beyond the proton drip line: Bayesian analysis of proton-emitting nuclei
Authors	Léo Neufcourt, Yuchen Cao, Samuel Giuliani, Witold Nazarewicz, Erik Olsen, Oleg B. Tarasov
Abstract	The limits of the nuclear landscape are determined by nuclear binding energies. Beyond the proton drip lines, where the separation energy becomes negative, there is not enough binding energy to prevent protons from escaping the nucleus. Predicting properties of unstable nuclear states in the vast territory of proton emitters poses an appreciable challenge for nuclear theory as it often involves far extrapolations. In addition, significant discrepancies between nuclear models in the proton-rich territory call for quantified predictions. With the help of Bayesian methodology, we mix a family of nuclear mass models corrected with statistical emulators trained on the experimental mass measurements, in the proton-rich region of the nuclear chart. Separation energies were computed within nuclear density functional theory using several Skyrme and Gogny energy density functionals. We also considered mass predictions based on two models used in astrophysical studies. Quantified predictions were obtained for each model using Bayesian Gaussian processes trained on separation-energy residuals and combined via Bayesian model averaging. We obtained a good agreement between averaged predictions of statistically corrected models and experiment. In particular, we quantified model results for one- and two-proton separation energies and derived probabilities of proton emission. This information enabled us to produce a quantified landscape of proton-rich nuclei. The most promising candidates for two-proton decay studies have been identified. The methodology used in this work has broad applications to model-based extrapolations of various nuclear observables. It also provides a reliable uncertainty quantification of theoretical predictions.
Tasks	Gaussian Processes
Published	2019-10-28
URL	https://arxiv.org/abs/1910.12624v2
PDF	https://arxiv.org/pdf/1910.12624v2.pdf
PWC	https://paperswithcode.com/paper/beyond-the-proton-drip-line-bayesian-analysis
Repo
Framework

On Mining IoT Data for Evaluating the Operation of Public Educational Buildings


Title	On Mining IoT Data for Evaluating the Operation of Public Educational Buildings
Authors	Na Zhu, Aris Anagnostopoulos, Ioannis Chatzigiannakis
Abstract	Public educational systems operate thousands of buildings with vastly different characteristics in terms of size, age, location, construction, thermal behavior and user communities. Their strategic planning and sustainable operation is an extremely complex and requires quantitative evidence on the performance of buildings such as the interaction of indoor-outdoor environment. Internet of Things (IoT) deployments can provide the necessary data to evaluate, redesign and eventually improve the organizational and managerial measures. In this work a data mining approach is presented to analyze the sensor data collected over a period of 2 years from an IoT infrastructure deployed over 18 school buildings spread in Greece, Italy and Sweden. The real-world evaluation indicates that data mining on sensor data can provide critical insights to building managers and custodial staff about ways to lower a building’s energy footprint through effectively managing building operations.
Tasks
Published	2019-06-20
URL	https://arxiv.org/abs/1907.10818v1
PDF	https://arxiv.org/pdf/1907.10818v1.pdf
PWC	https://paperswithcode.com/paper/on-mining-iot-data-for-evaluating-the
Repo
Framework

Using Intuition from Empirical Properties to Simplify Adversarial Training Defense


Title	Using Intuition from Empirical Properties to Simplify Adversarial Training Defense
Authors	Guanxiong Liu, Issa Khalil, Abdallah Khreishah
Abstract	Due to the surprisingly good representation power of complex distributions, neural network (NN) classifiers are widely used in many tasks which include natural language processing, computer vision and cyber security. In recent works, people noticed the existence of adversarial examples. These adversarial examples break the NN classifiers’ underlying assumption that the environment is attack free and can easily mislead fully trained NN classifier without noticeable changes. Among defensive methods, adversarial training is a popular choice. However, original adversarial training with single-step adversarial examples (Single-Adv) can not defend against iterative adversarial examples. Although adversarial training with iterative adversarial examples (Iter-Adv) can defend against iterative adversarial examples, it consumes too much computational power and hence is not scalable. In this paper, we analyze Iter-Adv techniques and identify two of their empirical properties. Based on these properties, we propose modifications which enhance Single-Adv to perform competitively as Iter-Adv. Through preliminary evaluation, we show that the proposed method enhances the test accuracy of state-of-the-art (SOTA) Single-Adv defensive method against iterative adversarial examples by up to 16.93% while reducing its training cost by 28.75%.
Tasks
Published	2019-06-27
URL	https://arxiv.org/abs/1906.11729v1
PDF	https://arxiv.org/pdf/1906.11729v1.pdf
PWC	https://paperswithcode.com/paper/using-intuition-from-empirical-properties-to
Repo
Framework