April 1, 2020

2706 words 13 mins read

Paper Group ANR 407

Online Algorithms for Multi-shop Ski Rental with Machine Learned Predictions. NETNet: Neighbor Erasing and Transferring Network for Better Single Shot Object Detection. Faster SVM Training via Conjugate SMO. Intent Classification in Question-Answering Using LSTM Architectures. Giving Commands to a Self-driving Car: A Multimodal Reasoner for Visual …

Online Algorithms for Multi-shop Ski Rental with Machine Learned Predictions


Title	Online Algorithms for Multi-shop Ski Rental with Machine Learned Predictions
Authors	Shufan Wang, Jian Li, Shiqiang Wang
Abstract	We study the problem of augmenting online algorithms with machine learned (ML) predictions. In particular, we consider the \emph{multi-shop ski rental} (MSSR) problem, which is a generalization of the classical ski rental problem. In MSSR, each shop has different prices for buying and renting a pair of skis, and a skier has to make decisions on when and where to buy. We obtain both deterministic and randomized online algorithms with provably improved performance when either a single or multiple ML predictions are used to make decisions. These online algorithms have no knowledge about the quality or the prediction error type of the ML predictions. The performance of these online algorithms are robust to the poor performance of the predictors, but improve with better predictions. We numerically evaluate the performance of our proposed online algorithms in practice.
Tasks
Published	2020-02-13
URL	https://arxiv.org/abs/2002.05808v1
PDF	https://arxiv.org/pdf/2002.05808v1.pdf
PWC	https://paperswithcode.com/paper/online-algorithms-for-multi-shop-ski-rental
Repo
Framework

NETNet: Neighbor Erasing and Transferring Network for Better Single Shot Object Detection


Title	NETNet: Neighbor Erasing and Transferring Network for Better Single Shot Object Detection
Authors	Yazhao Li, Yanwei Pang, Jianbing Shen, Jiale Cao, Ling Shao
Abstract	Due to the advantages of real-time detection and improved performance, single-shot detectors have gained great attention recently. To solve the complex scale variations, single-shot detectors make scale-aware predictions based on multiple pyramid layers. However, the features in the pyramid are not scale-aware enough, which limits the detection performance. Two common problems in single-shot detectors caused by object scale variations can be observed: (1) small objects are easily missed; (2) the salient part of a large object is sometimes detected as an object. With this observation, we propose a new Neighbor Erasing and Transferring (NET) mechanism to reconfigure the pyramid features and explore scale-aware features. In NET, a Neighbor Erasing Module (NEM) is designed to erase the salient features of large objects and emphasize the features of small objects in shallow layers. A Neighbor Transferring Module (NTM) is introduced to transfer the erased features and highlight large objects in deep layers. With this mechanism, a single-shot network called NETNet is constructed for scale-aware object detection. In addition, we propose to aggregate nearest neighboring pyramid features to enhance our NET. NETNet achieves 38.5% AP at a speed of 27 FPS and 32.0% AP at a speed of 55 FPS on MS COCO dataset. As a result, NETNet achieves a better trade-off for real-time and accurate object detection.
Tasks	Object Detection
Published	2020-01-18
URL	https://arxiv.org/abs/2001.06690v1
PDF	https://arxiv.org/pdf/2001.06690v1.pdf
PWC	https://paperswithcode.com/paper/netnet-neighbor-erasing-and-transferring
Repo
Framework

Faster SVM Training via Conjugate SMO


Title	Faster SVM Training via Conjugate SMO
Authors	Alberto Torres-Barrán, Carlos Alaíz, José R. Dorronsoro
Abstract	We propose an improved version of the SMO algorithm for training classification and regression SVMs, based on a Conjugate Descent procedure. This new approach only involves a modest increase on the computational cost of each iteration but, in turn, usually results in a substantial decrease in the number of iterations required to converge to a given precision. Besides, we prove convergence of the iterates of this new Conjugate SMO as well as a linear rate when the kernel matrix is positive definite. We have implemented Conjugate SMO within the LIBSVM library and show experimentally that it is faster for many hyper-parameter configurations, being often a better option than second order SMO when performing a grid-search for SVM tuning.
Tasks
Published	2020-03-19
URL	https://arxiv.org/abs/2003.08719v1
PDF	https://arxiv.org/pdf/2003.08719v1.pdf
PWC	https://paperswithcode.com/paper/faster-svm-training-via-conjugate-smo
Repo
Framework

Intent Classification in Question-Answering Using LSTM Architectures


Title	Intent Classification in Question-Answering Using LSTM Architectures
Authors	Giovanni Di Gennaro, Amedeo Buonanno, Antonio Di Girolamo, Armando Ospedale, Francesco A. N. Palmieri
Abstract	Question-answering (QA) is certainly the best known and probably also one of the most complex problem within Natural Language Processing (NLP) and artificial intelligence (AI). Since the complete solution to the problem of finding a generic answer still seems far away, the wisest thing to do is to break down the problem by solving single simpler parts. Assuming a modular approach to the problem, we confine our research to intent classification for an answer, given a question. Through the use of an LSTM network, we show how this type of classification can be approached effectively and efficiently, and how it can be properly used within a basic prototype responder.
Tasks	Intent Classification, Question Answering
Published	2020-01-25
URL	https://arxiv.org/abs/2001.09330v1
PDF	https://arxiv.org/pdf/2001.09330v1.pdf
PWC	https://paperswithcode.com/paper/intent-classification-in-question-answering
Repo
Framework

Giving Commands to a Self-driving Car: A Multimodal Reasoner for Visual Grounding


Title	Giving Commands to a Self-driving Car: A Multimodal Reasoner for Visual Grounding
Authors	Thierry Deruyttere, Guillem Collell, Marie-Francine Moens
Abstract	We propose a new spatial memory module and a spatial reasoner for the Visual Grounding (VG) task. The goal of this task is to find a certain object in an image based on a given textual query. Our work focuses on integrating the regions of a Region Proposal Network (RPN) into a new multi-step reasoning model which we have named a Multimodal Spatial Region Reasoner (MSRR). The introduced model uses the object regions from an RPN as initialization of a 2D spatial memory and then implements a multi-step reasoning process scoring each region according to the query, hence why we call it a multimodal reasoner. We evaluate this new model on challenging datasets and our experiments show that our model that jointly reasons over the object regions of the image and words of the query largely improves accuracy compared to current state-of-the-art models.
Tasks
Published	2020-03-19
URL	https://arxiv.org/abs/2003.08717v1
PDF	https://arxiv.org/pdf/2003.08717v1.pdf
PWC	https://paperswithcode.com/paper/giving-commands-to-a-self-driving-car-a
Repo
Framework

Evaluating complexity and resilience trade-offs in emerging memory inference machines


Title	Evaluating complexity and resilience trade-offs in emerging memory inference machines
Authors	Christopher H. Bennett, Ryan Dellana, T. Patrick Xiao, Ben Feinberg, Sapan Agarwal, Suma Cardwell, Matthew J. Marinella, William Severa, Brad Aimone
Abstract	Neuromorphic-style inference only works well if limited hardware resources are maximized properly, e.g. accuracy continues to scale with parameters and complexity in the face of potential disturbance. In this work, we use realistic crossbar simulations to highlight that compact implementations of deep neural networks are unexpectedly susceptible to collapse from multiple system disturbances. Our work proposes a middle path towards high performance and strong resilience utilizing the Mosaics framework, and specifically by re-using synaptic connections in a recurrent neural network implementation that possesses a natural form of noise-immunity.
Tasks
Published	2020-02-25
URL	https://arxiv.org/abs/2003.10396v1
PDF	https://arxiv.org/pdf/2003.10396v1.pdf
PWC	https://paperswithcode.com/paper/evaluating-complexity-and-resilience-trade
Repo
Framework

Algorithms for Optimizing Fleet Staging of Air Ambulances


Title	Algorithms for Optimizing Fleet Staging of Air Ambulances
Authors	Joseph Tassone, Geoffrey Pond, Salimur Choudhury
Abstract	In a disaster situation, air ambulance rapid response will often be the determining factor in patient survival. Obstacles intensify this circumstance, with geographical remoteness and limitations in vehicle placement making it an arduous task. Considering these elements, the arrangement of responders is a critical decision of the utmost importance. Utilizing real mission data, this research structured an optimal coverage problem with integer linear programming. For accurate comparison, the Gurobi optimizer was programmed with the developed model and timed for performance. A solution implementing base ranking followed by both local and Tabu search-based algorithms was created. The local search algorithm proved insufficient for maximizing coverage, while the Tabu search achieved near-optimal results. In the latter case, the total vehicle travel distance was minimized and the runtime significantly outperformed the one generated by Gurobi. Furthermore, variations utilizing parallel CUDA processing further decreased the algorithmic runtime. These proved superior as the number of test missions increased, while also maintaining the same minimized distance.
Tasks
Published	2020-01-10
URL	https://arxiv.org/abs/2001.05291v2
PDF	https://arxiv.org/pdf/2001.05291v2.pdf
PWC	https://paperswithcode.com/paper/algorithms-for-optimizing-fleet-staging-of
Repo
Framework

Bayesian optimization for backpropagation in Monte-Carlo tree search


Title	Bayesian optimization for backpropagation in Monte-Carlo tree search
Authors	Yueqin Li, Nengli Lim
Abstract	In large domains, Monte-Carlo tree search (MCTS) is required to estimate the values of the states as efficiently and accurately as possible. However, the standard update rule in backpropagation assumes a stationary distribution for the returns, and particularly in min-max trees, convergence to the true value can be slow because of averaging. We present two methods, Softmax MCTS and Monotone MCTS, which generalize previous attempts to improve upon the backpropagation strategy. We demonstrate that both methods reduce to finding optimal monotone functions, which we do so by performing Bayesian optimization with a Gaussian process (GP) prior. We conduct experiments on computer Go, where the returns are given by a deep value neural network, and show that our proposed framework outperforms previous methods.
Tasks
Published	2020-01-25
URL	https://arxiv.org/abs/2001.09325v1
PDF	https://arxiv.org/pdf/2001.09325v1.pdf
PWC	https://paperswithcode.com/paper/bayesian-optimization-for-backpropagation-in
Repo
Framework

Magic: the Gathering is as Hard as Arithmetic


Title	Magic: the Gathering is as Hard as Arithmetic
Authors	Stella Biderman
Abstract	Magic: the Gathering is a popular and famously complicated card game about magical combat. Recently, several authors including Chatterjee and Ibsen-Jensen (2016) and Churchill, Biderman, and Herrick (2019) have investigated the computational complexity of playing Magic optimally. In this paper we show that the ``mate-in-$n$’’ problem for Magic is $\Delta^0_n$-hard and that optimal play in two-player Magic is non-arithmetic in general. These results apply to how real Magic is played, can be achieved using standard-size tournament legal decks, and do not rely on stochasticity or hidden information. Our paper builds upon the construction that Churchill, Biderman, and Herrick (2019) used to show that this problem was at least as hard as the halting problem. \|
Tasks
Published	2020-03-11
URL	https://arxiv.org/abs/2003.05119v1
PDF	https://arxiv.org/pdf/2003.05119v1.pdf
PWC	https://paperswithcode.com/paper/magic-the-gathering-is-as-hard-as-arithmetic
Repo
Framework

Deep Learning on Radar Centric 3D Object Detection


Title	Deep Learning on Radar Centric 3D Object Detection
Authors	Seungjun Lee
Abstract	Even though many existing 3D object detection algorithms rely mostly on camera and LiDAR, camera and LiDAR are prone to be affected by harsh weather and lighting conditions. On the other hand, radar is resistant to such conditions. However, research has found only recently to apply deep neural networks on radar data. In this paper, we introduce a deep learning approach to 3D object detection with radar only. To the best of our knowledge, we are the first ones to demonstrate a deep learning-based 3D object detection model with radar only that was trained on the public radar dataset. To overcome the lack of radar labeled data, we propose a novel way of making use of abundant LiDAR data by transforming it into radar-like point cloud data and aggressive radar augmentation techniques.
Tasks	3D Object Detection, Object Detection
Published	2020-02-27
URL	https://arxiv.org/abs/2003.00851v1
PDF	https://arxiv.org/pdf/2003.00851v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-on-radar-centric-3d-object
Repo
Framework

Canadian Adverse Driving Conditions Dataset


Title	Canadian Adverse Driving Conditions Dataset
Authors	Matthew Pitropov, Danson Garcia, Jason Rebello, Michael Smart, Carlos Wang, Krzysztof Czarnecki, Steven Waslander
Abstract	The Canadian Adverse Driving Conditions (CADC) dataset was collected with the Autonomoose autonomous vehicle platform, based on a modified Lincoln MKZ. The dataset, collected during winter within the Region of Waterloo, Canada, is the first autonomous vehicle dataset that focuses on adverse driving conditions specifically. It contains 7,000 frames collected through a variety of winter weather conditions of annotated data from 8 cameras (Ximea MQ013CG-E2), Lidar (VLP-32C) and a GNSS+INS system (Novatel OEM638). The sensors are time synchronized and calibrated with the intrinsic and extrinsic calibrations included in the dataset. Lidar frame annotations that represent ground truth for 3D object detection and tracking have been provided by Scale AI.
Tasks	3D Object Detection, Object Detection
Published	2020-01-27
URL	https://arxiv.org/abs/2001.10117v3
PDF	https://arxiv.org/pdf/2001.10117v3.pdf
PWC	https://paperswithcode.com/paper/canadian-adverse-driving-conditions-dataset
Repo
Framework

Knowledge Cores in Large Formal Contexts


Title	Knowledge Cores in Large Formal Contexts
Authors	Tom Hanika, Johannes Hirth
Abstract	Knowledge computation tasks are often infeasible for large data sets. This is in particular true when deriving knowledge bases in formal concept analysis (FCA). Hence, it is essential to come up with techniques to cope with this problem. Many successful methods are based on random processes to reduce the size of the investigated data set. This, however, makes them hardly interpretable with respect to the discovered knowledge. Other approaches restrict themselves to highly supported subsets and omit rare and interesting patterns. An essentially different approach is used in network science, called $k$-cores. These are able to reflect rare patterns if they are well connected in the data set. In this work, we study $k$-cores in the realm of FCA by exploiting the natural correspondence to bi-partite graphs. This structurally motivated approach leads to a comprehensible extraction of knowledge cores from large formal contexts data sets.
Tasks
Published	2020-02-26
URL	https://arxiv.org/abs/2002.11776v1
PDF	https://arxiv.org/pdf/2002.11776v1.pdf
PWC	https://paperswithcode.com/paper/knowledge-cores-in-large-formal-contexts
Repo
Framework

Reject Illegal Inputs with Generative Classifier Derived from Any Discriminative Classifier


Title	Reject Illegal Inputs with Generative Classifier Derived from Any Discriminative Classifier
Authors	Xin Wang
Abstract	Generative classifiers have been shown promising to detect illegal inputs including adversarial examples and out-of-distribution samples. Supervised Deep Infomax~(SDIM) is a scalable end-to-end framework to learn generative classifiers. In this paper, we propose a modification of SDIM termed SDIM-\emph{logit}. Instead of training generative classifier from scratch, SDIM-\emph{logit} first takes as input the logits produced any given discriminative classifier, and generate logit representations; then a generative classifier is derived by imposing statistical constraints on logit representations. SDIM-\emph{logit} could inherit the performance of the discriminative classifier without loss. SDIM-\emph{logit} incurs a negligible number of additional parameters, and can be efficiently trained with base classifiers fixed. We perform \emph{classification with rejection}, where test samples whose class conditionals are smaller than pre-chosen thresholds will be rejected without predictions. Experiments on illegal inputs, including adversarial examples, samples with common corruptions, and out-of-distribution~(OOD) samples show that allowed to reject a portion of test samples, SDIM-\emph{logit} significantly improves the performance on the left test sets.
Tasks
Published	2020-01-02
URL	https://arxiv.org/abs/2001.00483v1
PDF	https://arxiv.org/pdf/2001.00483v1.pdf
PWC	https://paperswithcode.com/paper/reject-illegal-inputs-with-generative
Repo
Framework

Rethinking the Route Towards Weakly Supervised Object Localization


Title	Rethinking the Route Towards Weakly Supervised Object Localization
Authors	Chen-Lin Zhang, Yun-Hao Cao, Jianxin Wu
Abstract	Weakly supervised object localization (WSOL) aims to localize objects with only image-level labels. Previous methods often try to utilize feature maps and classification weights to localize objects using image level annotations indirectly. In this paper, we demonstrate that weakly supervised object localization should be divided into two parts: class-agnostic object localization and object classification. For class-agnostic object localization, we should use class-agnostic methods to generate noisy pseudo annotations and then perform bounding box regression on them without class labels. We propose the pseudo supervised object localization (PSOL) method as a new way to solve WSOL. Our PSOL models have good transferability across different datasets without fine-tuning. With generated pseudo bounding boxes, we achieve 58.00% localization accuracy on ImageNet and 74.97% localization accuracy on CUB-200, which have a large edge over previous models.
Tasks	Object Classification, Object Localization, Weakly-Supervised Object Localization
Published	2020-02-26
URL	https://arxiv.org/abs/2002.11359v2
PDF	https://arxiv.org/pdf/2002.11359v2.pdf
PWC	https://paperswithcode.com/paper/rethinking-the-route-towards-weakly
Repo
Framework

Lightweight Residual Densely Connected Convolutional Neural Network


Title	Lightweight Residual Densely Connected Convolutional Neural Network
Authors	Fahimeh Fooladgar, Shohreh Kasaei
Abstract	Extremely efficient convolutional neural network architectures are one of the most important requirements for limited computing power devices (such as embedded and mobile devices). Recently, some architectures have been proposed to overcome this limitation by considering specific hardware-software equipment. In this paper, the residual densely connected blocks are proposed to guaranty the deep supervision, efficient gradient flow, and feature reuse abilities of convolutional neural network. The proposed method decreases the cost of training and inference processes without using any special hardware-software equipment by just reducing the number of parameters and computational operations while achieving a feasible accuracy. Extensive experimental results demonstrate that the proposed architecture is more efficient than the AlexNet and VGGNet in terms of model size, required parameters, and even accuracy. The proposed model is evaluated on the ImageNet, MNIST, Fashion MNIST, SVHN, CIFAR-10, and CIFAR-100. It achieves state-of-the-art results on the Fashion MNIST dataset and reasonable results on the others. The obtained results show that the proposed model is superior to efficient models such as the SqueezNet and is also comparable with the state-of-the-art efficient models such as CondenseNet and ShuffleNet.
Tasks
Published	2020-01-02
URL	https://arxiv.org/abs/2001.00526v1
PDF	https://arxiv.org/pdf/2001.00526v1.pdf
PWC	https://paperswithcode.com/paper/lightweight-residual-densely-connected
Repo
Framework