February 1, 2020

3369 words 16 mins read

Paper Group AWR 207

Practical License Plate Recognition in Unconstrained Surveillance Systems with Adversarial Super-Resolution. Federated Neuromorphic Learning of Spiking Neural Networks for Low-Power Edge Intelligence. AlphaX: eXploring Neural Architectures with Deep Neural Networks and Monte Carlo Tree Search. Deep Landscape Forecasting for Real-time Bidding Advert …

Practical License Plate Recognition in Unconstrained Surveillance Systems with Adversarial Super-Resolution


Title	Practical License Plate Recognition in Unconstrained Surveillance Systems with Adversarial Super-Resolution
Authors	Younkwan Lee, Jiwon Jun, Yoojin Hong, Moongu Jeon
Abstract	Although most current license plate (LP) recognition applications have been significantly advanced, they are still limited to ideal environments where training data are carefully annotated with constrained scenes. In this paper, we propose a novel license plate recognition method to handle unconstrained real world traffic scenes. To overcome these difficulties, we use adversarial super-resolution (SR), and one-stage character segmentation and recognition. Combined with a deep convolutional network based on VGG-net, our method provides simple but reasonable training procedure. Moreover, we introduce GIST-LP, a challenging LP dataset where image samples are effectively collected from unconstrained surveillance scenes. Experimental results on AOLP and GIST-LP dataset illustrate that our method, without any scene-specific adaptation, outperforms current LP recognition approaches in accuracy and provides visual enhancement in our SR results that are easier to understand than original data.
Tasks	License Plate Recognition, Super-Resolution
Published	2019-10-10
URL	https://arxiv.org/abs/1910.04324v1
PDF	https://arxiv.org/pdf/1910.04324v1.pdf
PWC	https://paperswithcode.com/paper/practical-license-plate-recognition-in
Repo	https://github.com/brightyoun/LPSR-Recognition
Framework	tf

Federated Neuromorphic Learning of Spiking Neural Networks for Low-Power Edge Intelligence


Title	Federated Neuromorphic Learning of Spiking Neural Networks for Low-Power Edge Intelligence
Authors	Nicolas Skatchkovsky, Hyeryung Jang, Osvaldo Simeone
Abstract	Spiking Neural Networks (SNNs) offer a promising alternative to conventional Artificial Neural Networks (ANNs) for the implementation of on-device low-power online learning and inference. On-device training is, however, constrained by the limited amount of data available at each device. In this paper, we propose to mitigate this problem via cooperative training through Federated Learning (FL). To this end, we introduce an online FL-based learning rule for networked on-device SNNs, which we refer to as FL-SNN. FL-SNN leverages local feedback signals within each SNN, in lieu of backpropagation, and global feedback through communication via a base station. The scheme demonstrates significant advantages over separate training and features a flexible trade-off between communication load and accuracy via the selective exchange of synaptic weights.
Tasks
Published	2019-10-21
URL	https://arxiv.org/abs/1910.09594v1
PDF	https://arxiv.org/pdf/1910.09594v1.pdf
PWC	https://paperswithcode.com/paper/federated-neuromorphic-learning-of-spiking
Repo	https://github.com/kclip/FL-SNN
Framework	pytorch

AlphaX: eXploring Neural Architectures with Deep Neural Networks and Monte Carlo Tree Search


Title	AlphaX: eXploring Neural Architectures with Deep Neural Networks and Monte Carlo Tree Search
Authors	Linnan Wang, Yiyang Zhao, Yuu Jinnai, Yuandong Tian, Rodrigo Fonseca
Abstract	Neural Architecture Search (NAS) has shown great success in automating the design of neural networks, but the prohibitive amount of computations behind current NAS methods requires further investigations in improving the sample efficiency and the network evaluation cost to get better results in a shorter time. In this paper, we present a novel scalable Monte Carlo Tree Search (MCTS) based NAS agent, named AlphaX, to tackle these two aspects. AlphaX improves the search efficiency by adaptively balancing the exploration and exploitation at the state level, and by a Meta-Deep Neural Network (DNN) to predict network accuracies for biasing the search toward a promising region. To amortize the network evaluation cost, AlphaX accelerates MCTS rollouts with a distributed design and reduces the number of epochs in evaluating a network by transfer learning guided with the tree structure in MCTS. In 12 GPU days and 1000 samples, AlphaX found an architecture that reaches 97.84% top-1 accuracy on CIFAR-10, and 75.5% top-1 accuracy on ImageNet, exceeding SOTA NAS methods in both the accuracy and sampling efficiency. Particularly, we also evaluate AlphaX on NASBench-101, a large scale NAS dataset; AlphaX is 3x and 2.8x more sample efficient than Random Search and Regularized Evolution in finding the global optimum. Finally, we show the searched architecture improves a variety of vision applications from Neural Style Transfer, to Image Captioning and Object Detection.
Tasks	Image Captioning, Neural Architecture Search, Object Detection, Style Transfer, Transfer Learning
Published	2019-03-26
URL	https://arxiv.org/abs/1903.11059v2
PDF	https://arxiv.org/pdf/1903.11059v2.pdf
PWC	https://paperswithcode.com/paper/alphax-exploring-neural-architectures-with-1
Repo	https://github.com/linnanwang/AlphaX-NASBench101
Framework	none

Deep Landscape Forecasting for Real-time Bidding Advertising


Title	Deep Landscape Forecasting for Real-time Bidding Advertising
Authors	Kan Ren, Jiarui Qin, Lei Zheng, Zhengyu Yang, Weinan Zhang, Yong Yu
Abstract	The emergence of real-time auction in online advertising has drawn huge attention of modeling the market competition, i.e., bid landscape forecasting. The problem is formulated as to forecast the probability distribution of market price for each ad auction. With the consideration of the censorship issue which is caused by the second-price auction mechanism, many researchers have devoted their efforts on bid landscape forecasting by incorporating survival analysis from medical research field. However, most existing solutions mainly focus on either counting-based statistics of the segmented sample clusters, or learning a parameterized model based on some heuristic assumptions of distribution forms. Moreover, they neither consider the sequential patterns of the feature over the price space. In order to capture more sophisticated yet flexible patterns at fine-grained level of the data, we propose a Deep Landscape Forecasting (DLF) model which combines deep learning for probability distribution forecasting and survival analysis for censorship handling. Specifically, we utilize a recurrent neural network to flexibly model the conditional winning probability w.r.t. each bid price. Then we conduct the bid landscape forecasting through probability chain rule with strict mathematical derivations. And, in an end-to-end manner, we optimize the model by minimizing two negative likelihood losses with comprehensive motivations. Without any specific assumption for the distribution form of bid landscape, our model shows great advantages over previous works on fitting various sophisticated market price distributions. In the experiments over two large-scale real-world datasets, our model significantly outperforms the state-of-the-art solutions under various metrics.
Tasks	Survival Analysis
Published	2019-05-07
URL	https://arxiv.org/abs/1905.03028v2
PDF	https://arxiv.org/pdf/1905.03028v2.pdf
PWC	https://paperswithcode.com/paper/deep-landscape-forecasting-for-real-time
Repo	https://github.com/rk2900/DLF
Framework	tf

Nearest Neighbor and Kernel Survival Analysis: Nonasymptotic Error Bounds and Strong Consistency Rates


Title	Nearest Neighbor and Kernel Survival Analysis: Nonasymptotic Error Bounds and Strong Consistency Rates
Authors	George H. Chen
Abstract	We establish the first nonasymptotic error bounds for Kaplan-Meier-based nearest neighbor and kernel survival probability estimators where feature vectors reside in metric spaces. Our bounds imply rates of strong consistency for these nonparametric estimators and, up to a log factor, match an existing lower bound for conditional CDF estimation. Our proof strategy also yields nonasymptotic guarantees for nearest neighbor and kernel variants of the Nelson-Aalen cumulative hazards estimator. We experimentally compare these methods on four datasets. We find that for the kernel survival estimator, a good choice of kernel is one learned using random survival forests.
Tasks	Survival Analysis
Published	2019-05-13
URL	https://arxiv.org/abs/1905.05285v1
PDF	https://arxiv.org/pdf/1905.05285v1.pdf
PWC	https://paperswithcode.com/paper/nearest-neighbor-and-kernel-survival-analysis
Repo	https://github.com/georgehc/npsurvival
Framework	none

Effectiveness of random deep feature selection for securing image manipulation detectors against adversarial examples


Title	Effectiveness of random deep feature selection for securing image manipulation detectors against adversarial examples
Authors	Mauro Barni, Ehsan Nowroozi, Benedetta Tondi, Bowen Zhang
Abstract	We investigate if the random feature selection approach proposed in [1] to improve the robustness of forensic detectors to targeted attacks, can be extended to detectors based on deep learning features. In particular, we study the transferability of adversarial examples targeting an original CNN image manipulation detector to other detectors (a fully connected neural network and a linear SVM) that rely on a random subset of the features extracted from the flatten layer of the original network. The results we got by considering three image manipulation detection tasks (resizing, median filtering and adaptive histogram equalization), two original network architectures and three classes of attacks, show that feature randomization helps to hinder attack transferability, even if, in some cases, simply changing the architecture of the detector, or even retraining the detector is enough to prevent the transferability of the attacks.
Tasks	Feature Selection, Image Manipulation Detection
Published	2019-10-25
URL	https://arxiv.org/abs/1910.12392v2
PDF	https://arxiv.org/pdf/1910.12392v2.pdf
PWC	https://paperswithcode.com/paper/effectiveness-of-random-deep-feature
Repo	https://github.com/ehsannowroozi/RDFS
Framework	none

Learning Universal Graph Neural Network Embeddings With Aid Of Transfer Learning


Title	Learning Universal Graph Neural Network Embeddings With Aid Of Transfer Learning
Authors	Saurabh Verma, Zhi-Li Zhang
Abstract	Learning powerful data embeddings has become a center piece in machine learning, especially in natural language processing and computer vision domains. The crux of these embeddings is that they are pretrained on huge corpus of data in a unsupervised fashion, sometimes aided with transfer learning. However currently in the graph learning domain, embeddings learned through existing graph neural networks (GNNs) are task dependent and thus cannot be shared across different datasets. In this paper, we present a first powerful and theoretically guaranteed graph neural network that is designed to learn task-independent graph embeddings, thereafter referred to as deep universal graph embedding (DUGNN). Our DUGNN model incorporates a novel graph neural network (as a universal graph encoder) and leverages rich Graph Kernels (as a multi-task graph decoder) for both unsupervised learning and (task-specific) adaptive supervised learning. By learning task-independent graph embeddings across diverse datasets, DUGNN also reaps the benefits of transfer learning. Through extensive experiments and ablation studies, we show that the proposed DUGNN model consistently outperforms both the existing state-of-art GNN models and Graph Kernels by an increased accuracy of 3% - 8% on graph classification benchmark datasets.
Tasks	Graph Classification, Graph Embedding, Transfer Learning
Published	2019-09-22
URL	https://arxiv.org/abs/1909.10086v3
PDF	https://arxiv.org/pdf/1909.10086v3.pdf
PWC	https://paperswithcode.com/paper/190910086
Repo	https://github.com/vermaMachineLearning/Universal-Graph-Embedding-Neural-Network
Framework	pytorch

Measuring group-separability in geometrical space for evaluation of pattern recognition and embedding algorithms


Title	Measuring group-separability in geometrical space for evaluation of pattern recognition and embedding algorithms
Authors	A. Acevedo, S. Ciucci, MJ. Kuo, C. Duran, CV. Cannistraci
Abstract	Evaluating data separation in a geometrical space is fundamental for pattern recognition. A plethora of dimensionality reduction (DR) algorithms have been developed in order to reveal the emergence of geometrical patterns in a low dimensional visible representation space, in which high-dimensional samples similarities are approximated by geometrical distances. However, statistical measures to evaluate directly in the low dimensional geometrical space the sample group separability attaiend by these DR algorithms are missing. Certainly, these separability measures could be used both to compare algorithms performance and to tune algorithms parameters. Here, we propose three statistical measures (named as PSI-ROC, PSI-PR, and PSI-P) that have origin from the Projection Separability (PS) rationale introduced in this study, which is expressly designed to assess group separability of data samples in a geometrical space. Traditional cluster validity indices (CVIs) might be applied in this context but they show limitations because they are not specifically tailored for DR. Our PS measures are compared to six baseline cluster validity indices, using five non-linear datasets and six different DR algorithms. The results provide clear evidence that statistical-based measures based on PS rationale are more accurate than CVIs and can be adopted to control the tuning of parameter-dependent DR algorithms.
Tasks	Dimensionality Reduction
Published	2019-12-28
URL	https://arxiv.org/abs/1912.12418v1
PDF	https://arxiv.org/pdf/1912.12418v1.pdf
PWC	https://paperswithcode.com/paper/measuring-group-separability-in-geometrical
Repo	https://github.com/biomedical-cybernetics/projection-separability-indices
Framework	none

Can Adversarial Networks Hallucinate Occluded People With a Plausible Aspect?


Title	Can Adversarial Networks Hallucinate Occluded People With a Plausible Aspect?
Authors	Federico Fulgeri, Matteo Fabbri, Stefano Alletto, Simone Calderara, Rita Cucchiara
Abstract	When you see a person in a crowd, occluded by other persons, you miss visual information that can be used to recognize, re-identify or simply classify him or her. You can imagine its appearance given your experience, nothing more. Similarly, AI solutions can try to hallucinate missing information with specific deep learning architectures, suitably trained with people with and without occlusions. The goal of this work is to generate a complete image of a person, given an occluded version in input, that should be a) without occlusion b) similar at pixel level to a completely visible people shape c) capable to conserve similar visual attributes (e.g. male/female) of the original one. For the purpose, we propose a new approach by integrating the state-of-the-art of neural network architectures, namely U-nets and GANs, as well as discriminative attribute classification nets, with an architecture specifically designed to de-occlude people shapes. The network is trained to optimize a Loss function which could take into account the aforementioned objectives. As well we propose two datasets for testing our solution: the first one, occluded RAP, created automatically by occluding real shapes of the RAP dataset (which collects also attributes of the people aspect); the second is a large synthetic dataset, AiC, generated in computer graphics with data extracted from the GTA video game, that contains 3D data of occluded objects by construction. Results are impressive and outperform any other previous proposal. This result could be an initial step to many further researches to recognize people and their behavior in an open crowded world.
Tasks
Published	2019-01-23
URL	http://arxiv.org/abs/1901.08097v1
PDF	http://arxiv.org/pdf/1901.08097v1.pdf
PWC	https://paperswithcode.com/paper/can-adversarial-networks-hallucinate-occluded
Repo	https://github.com/fabbrimatteo/AiC-Dataset
Framework	none

Deep Learning without Weight Transport


Title	Deep Learning without Weight Transport
Authors	Mohamed Akrout, Collin Wilson, Peter C. Humphreys, Timothy Lillicrap, Douglas Tweed
Abstract	Current algorithms for deep learning probably cannot run in the brain because they rely on weight transport, where forward-path neurons transmit their synaptic weights to a feedback path, in a way that is likely impossible biologically. An algorithm called feedback alignment achieves deep learning without weight transport by using random feedback weights, but it performs poorly on hard visual-recognition tasks. Here we describe two mechanisms - a neural circuit called a weight mirror and a modification of an algorithm proposed by Kolen and Pollack in 1994 - both of which let the feedback path learn appropriate synaptic weights quickly and accurately even in large networks, without weight transport or complex wiring.Tested on the ImageNet visual-recognition task, these mechanisms outperform both feedback alignment and the newer sign-symmetry method, and nearly match backprop, the standard algorithm of deep learning, which uses weight transport.
Tasks
Published	2019-04-10
URL	https://arxiv.org/abs/1904.05391v5
PDF	https://arxiv.org/pdf/1904.05391v5.pdf
PWC	https://paperswithcode.com/paper/using-weight-mirrors-to-improve-feedback
Repo	https://github.com/makrout/Deep-Learning-without-Weight-Transport
Framework	tf


Title	Navigation Agents for the Visually Impaired: A Sidewalk Simulator and Experiments
Authors	Martin Weiss, Simon Chamorro, Roger Girgis, Margaux Luck, Samira E. Kahou, Joseph P. Cohen, Derek Nowrouzezahrai, Doina Precup, Florian Golemo, Chris Pal
Abstract	Millions of blind and visually-impaired (BVI) people navigate urban environments every day, using smartphones for high-level path-planning and white canes or guide dogs for local information. However, many BVI people still struggle to travel to new places. In our endeavor to create a navigation assistant for the BVI, we found that existing Reinforcement Learning (RL) environments were unsuitable for the task. This work introduces SEVN, a sidewalk simulation environment and a neural network-based approach to creating a navigation agent. SEVN contains panoramic images with labels for house numbers, doors, and street name signs, and formulations for several navigation tasks. We study the performance of an RL algorithm (PPO) in this setting. Our policy model fuses multi-modal observations in the form of variable resolution images, visible text, and simulated GPS data to navigate to a goal door. We hope that this dataset, simulator, and experimental results will provide a foundation for further research into the creation of agents that can assist members of the BVI community with outdoor navigation.
Tasks
Published	2019-10-29
URL	https://arxiv.org/abs/1910.13249v1
PDF	https://arxiv.org/pdf/1910.13249v1.pdf
PWC	https://paperswithcode.com/paper/191013249
Repo	https://github.com/mweiss17/SEVN
Framework	none

Sato: Contextual Semantic Type Detection in Tables


Title	Sato: Contextual Semantic Type Detection in Tables
Authors	Dan Zhang, Yoshihiko Suhara, Jinfeng Li, Madelon Hulsebos, Çağatay Demiralp, Wang-Chiew Tan
Abstract	Detecting the semantic types of data columns in relational tables is important for various data preparation and information retrieval tasks such as data cleaning, schema matching, data discovery, and semantic search. However, existing detection approaches either perform poorly with dirty data, support only a limited number of semantic types, fail to incorporate the table context of columns or rely on large sample sizes in the training data. We introduce Sato, a hybrid machine learning model to automatically detect the semantic types of columns in tables, exploiting the signals from the context as well as the column values. Sato combines a deep learning model trained on a large-scale table corpus with topic modeling and structured prediction to achieve support-weighted and macro average F1 scores of 0.925 and 0.735, respectively, exceeding the state-of-the-art performance by a significant margin. We extensively analyze the overall and per-type performance of Sato, discussing how individual modeling components, as well as feature categories, contribute to its performance.
Tasks	Information Retrieval, Structured Prediction
Published	2019-11-14
URL	https://arxiv.org/abs/1911.06311v2
PDF	https://arxiv.org/pdf/1911.06311v2.pdf
PWC	https://paperswithcode.com/paper/sato-contextual-semantic-type-detection-in
Repo	https://github.com/megagonlabs/sato
Framework	none

JumpReLU: A Retrofit Defense Strategy for Adversarial Attacks


Title	JumpReLU: A Retrofit Defense Strategy for Adversarial Attacks
Authors	N. Benjamin Erichson, Zhewei Yao, Michael W. Mahoney
Abstract	It has been demonstrated that very simple attacks can fool highly-sophisticated neural network architectures. In particular, so-called adversarial examples, constructed from perturbations of input data that are small or imperceptible to humans but lead to different predictions, may lead to an enormous risk in certain critical applications. In light of this, there has been a great deal of work on developing adversarial training strategies to improve model robustness. These training strategies are very expensive, in both human and computational time. To complement these approaches, we propose a very simple and inexpensive strategy which can be used to ``retrofit’’ a previously-trained network to improve its resilience to adversarial attacks. More concretely, we propose a new activation function—the JumpReLU—which, when used in place of a ReLU in an already-trained model, leads to a trade-off between predictive accuracy and robustness. This trade-off is controlled by the jump size, a hyper-parameter which can be tuned during the validation stage. Our empirical results demonstrate that this increases model robustness, protecting against adversarial attacks with substantially increased levels of perturbations. This is accomplished simply by retrofitting existing networks with our JumpReLU activation function, without the need for retraining the model. Additionally, we demonstrate that adversarially trained (robust) models can greatly benefit from retrofitting. \|
Tasks
Published	2019-04-07
URL	http://arxiv.org/abs/1904.03750v1
PDF	http://arxiv.org/pdf/1904.03750v1.pdf
PWC	https://paperswithcode.com/paper/jumprelu-a-retrofit-defense-strategy-for
Repo	https://github.com/erichson/JumpReLU
Framework	pytorch

Efficient Optimization of Echo State Networks for Time Series Datasets


Title	Efficient Optimization of Echo State Networks for Time Series Datasets
Authors	Jacob Reinier Maat, Nikos Gianniotis, Pavlos Protopapas
Abstract	Echo State Networks (ESNs) are recurrent neural networks that only train their output layer, thereby precluding the need to backpropagate gradients through time, which leads to significant computational gains. Nevertheless, a common issue in ESNs is determining its hyperparameters, which are crucial in instantiating a well performing reservoir, but are often set manually or using heuristics. In this work we optimize the ESN hyperparameters using Bayesian optimization which, given a limited budget of function evaluations, outperforms a grid search strategy. In the context of large volumes of time series data, such as light curves in the field of astronomy, we can further reduce the optimization cost of ESNs. In particular, we wish to avoid tuning hyperparameters per individual time series as this is costly; instead, we want to find ESNs with hyperparameters that perform well not just on individual time series but rather on groups of similar time series without sacrificing predictive performance significantly. This naturally leads to a notion of clusters, where each cluster is represented by an ESN tuned to model a group of time series of similar temporal behavior. We demonstrate this approach both on synthetic datasets and real world light curves from the MACHO survey. We show that our approach results in a significant reduction in the number of ESN models required to model a whole dataset, while retaining predictive performance for the series in each cluster.
Tasks	Time Series
Published	2019-03-12
URL	http://arxiv.org/abs/1903.05071v1
PDF	http://arxiv.org/pdf/1903.05071v1.pdf
PWC	https://paperswithcode.com/paper/efficient-optimization-of-echo-state-networks
Repo	https://github.com/1Reinier/Reservoir
Framework	none

edGNN: a Simple and Powerful GNN for Directed Labeled Graphs


Title	edGNN: a Simple and Powerful GNN for Directed Labeled Graphs
Authors	Guillaume Jaume, An-phi Nguyen, María Rodríguez Martínez, Jean-Philippe Thiran, Maria Gabrani
Abstract	The ability of a graph neural network (GNN) to leverage both the graph topology and graph labels is fundamental to building discriminative node and graph embeddings. Building on previous work, we theoretically show that edGNN, our model for directed labeled graphs, is as powerful as the Weisfeiler-Lehman algorithm for graph isomorphism. Our experiments support our theoretical findings, confirming that graph neural networks can be used effectively for inference problems on directed graphs with both node and edge labels. Code available at https://github.com/guillaumejaume/edGNN.
Tasks	Graph Classification
Published	2019-04-18
URL	https://arxiv.org/abs/1904.08745v2
PDF	https://arxiv.org/pdf/1904.08745v2.pdf
PWC	https://paperswithcode.com/paper/edgnn-a-simple-and-powerful-gnn-for-directed
Repo	https://github.com/guillaumejaume/edGNN
Framework	pytorch