January 29, 2020

3407 words 16 mins read

Paper Group ANR 736

Distant Pedestrian Detection in the Wild using Single Shot Detector with Deep Convolutional Generative Adversarial Networks. Non-congruent non-degenerate curves with identical signatures. Computing the Value of Data: Towards Applied Data Minimalism. Convolutional Recurrent Reconstructive Network for Spatiotemporal Anomaly Detection in Solder Paste …

Distant Pedestrian Detection in the Wild using Single Shot Detector with Deep Convolutional Generative Adversarial Networks


Title	Distant Pedestrian Detection in the Wild using Single Shot Detector with Deep Convolutional Generative Adversarial Networks
Authors	Ranjith Dinakaran, Philip Easom, Li Zhang, Ahmed Bouridane, Richard Jiang, Eran Edirisinghe
Abstract	In this work, we examine the feasibility of applying Deep Convolutional Generative Adversarial Networks (DCGANs) with Single Shot Detector (SSD) as data-processing technique to handle with the challenge of pedestrian detection in the wild. Specifically, we attempted to use in-fill completion (where a portion of the image is masked) to generate random transformations of images with portions missing to expand existing labelled datasets. In our work, GAN has been trained intensively on low resolution images, in order to neutralize the challenges of the pedestrian detection in the wild, and considered humans, and few other classes for detection in smart cities. The object detector experiment performed by training GAN model along with SSD provided a substantial improvement in the results. This approach presents a very interesting overview in the current state of art on GAN networks for object detection. We used Canadian Institute for Advanced Research (CIFAR), Caltech, KITTI data set for training and testing the network under different resolutions and the experimental results with comparison been showedbetween DCGAN cascaded with SSD and SSD itself.
Tasks	Object Detection, Pedestrian Detection
Published	2019-05-29
URL	https://arxiv.org/abs/1905.12759v1
PDF	https://arxiv.org/pdf/1905.12759v1.pdf
PWC	https://paperswithcode.com/paper/distant-pedestrian-detection-in-the-wild
Repo
Framework

Non-congruent non-degenerate curves with identical signatures


Title	Non-congruent non-degenerate curves with identical signatures
Authors	Eric Geiger, Irina A. Kogan
Abstract	We construct examples of non-congruent, non-degenerate simple planar closed curves with identical Euclidean signatures, thus disproving a claim made in Hickman (J. Math Imaging Vis. 43:206-213, 2012) that all such curves must be congruent. Our examples include closed $C^\infty$ curves of the same length and the same symmetry group. We show a general mechanism for constructing such examples by exploiting the self-intersection points of the signature. We state an updated congruence criterion for simple closed non-degenerate curves and confirm that for curves with simple signatures the claim made by Hickman holds.
Tasks
Published	2019-12-20
URL	https://arxiv.org/abs/1912.09597v1
PDF	https://arxiv.org/pdf/1912.09597v1.pdf
PWC	https://paperswithcode.com/paper/non-congruent-non-degenerate-curves-with
Repo
Framework

Computing the Value of Data: Towards Applied Data Minimalism


Title	Computing the Value of Data: Towards Applied Data Minimalism
Authors	Michaela Regneri, Julia S. Georgi, Jurij Kost, Niklas Pietsch, Sabine Stamm
Abstract	We present an approach to compute the monetary value of individual data points, in context of an automated decision system. The proposed method enables us to explore and implement a paradigm of data minimalism for large-scale machine learning systems. Data minimalistic implementations enhance scalability, while maintaining or even optimizing a system’s performance. Using two types of recommender systems, we first demonstrate how much data is ineffective in both settings. We then present a general account of computing data value via sensitivity analysis, and how, in theory, individual data points can be priced according to their informational contribution to automated decisions. We further exemplify this method to lab-scale recommender systems and outline further steps towards commercial data-minimalistic applications.
Tasks	Recommendation Systems
Published	2019-07-29
URL	https://arxiv.org/abs/1907.12404v1
PDF	https://arxiv.org/pdf/1907.12404v1.pdf
PWC	https://paperswithcode.com/paper/computing-the-value-of-data-towards-applied
Repo
Framework

Convolutional Recurrent Reconstructive Network for Spatiotemporal Anomaly Detection in Solder Paste Inspection


Title	Convolutional Recurrent Reconstructive Network for Spatiotemporal Anomaly Detection in Solder Paste Inspection
Authors	Yong-Ho Yoo, Ue-Hwan Kim, Jong-Hwan Kim
Abstract	Surface mount technology (SMT) is a process for producing printed circuit boards. Solder paste printer (SPP), package mounter, and solder reflow oven are used for SMT. The board on which the solder paste is deposited from the SPP is monitored by solder paste inspector (SPI). If SPP malfunctions due to the printer defects, the SPP produces defective products, and then abnormal patterns are detected by SPI. In this paper, we propose a convolutional recurrent reconstructive network (CRRN), which decomposes the anomaly patterns generated by the printer defects, from SPI data. CRRN learns only normal data and detects anomaly pattern through reconstruction error. CRRN consists of a spatial encoder (S-Encoder), a spatiotemporal encoder and decoder (ST-Encoder-Decoder), and a spatial decoder (S-Decoder). The ST-Encoder-Decoder consists of multiple convolutional spatiotemporal memories (CSTMs) with ST-Attention mechanism. CSTM is developed to extract spatiotemporal patterns efficiently. Additionally, a spatiotemporal attention (ST-Attention) mechanism is designed to facilitate transmitting information from the ST-Encoder to the ST-Decoder, which can solve the long-term dependency problem. We demonstrate the proposed CRRN outperforms the other conventional models in anomaly detection. Moreover, we show the discriminative power of the anomaly map decomposed by the proposed CRRN through the printer defect classification.
Tasks	Anomaly Detection
Published	2019-08-22
URL	https://arxiv.org/abs/1908.08204v1
PDF	https://arxiv.org/pdf/1908.08204v1.pdf
PWC	https://paperswithcode.com/paper/convolutional-recurrent-reconstructive
Repo
Framework

Normalization of breast MRIs using Cycle-Consistent Generative Adversarial Networks


Title	Normalization of breast MRIs using Cycle-Consistent Generative Adversarial Networks
Authors	Gourav Modanwal, Adithya Vellal, Maciej A. Mazurowski
Abstract	Dynamic Contrast Enhanced-Magnetic Resonance Imaging (DCE-MRI) is widely used to complement ultrasound examinations and x-ray mammography during the early detection and diagnosis of breast cancer. However, images generated by various MRI scanners (e.g. GE Healthcare vs Siemens) differ both in intensity and noise distribution, preventing algorithms trained on MRIs from one scanner to generalize to data from other scanners successfully. We propose a method for image normalization to solve this problem. MRI normalization is challenging because it requires both normalizing intensity values and mapping between the noise distributions of different scanners. We utilize a cycle-consistent generative adversarial network to learn a bidirectional mapping between MRIs produced by GE Healthcare and Siemens scanners. This allows us learning the mapping between two different scanner types without matched data, which is not commonly available. To ensure the preservation of breast shape and structures within the breast, we propose two technical innovations. First, we incorporate a mutual information loss with the CycleGAN architecture to ensure that the structure of the breast is maintained. Second, we propose a modified discriminator architecture which utilizes a smaller field-of-view to ensure the preservation of finer details in the breast tissue. Quantitative and qualitative evaluations show that the second proposed method was able to consistently preserve a high level of detail in the breast structure while also performing the proper intensity normalization and noise mapping. Our results demonstrate that the proposed model can successfully learn a bidirectional mapping between MRIs produced by different vendors, potentially enabling improved accuracy of downstream computational algorithms for diagnosis and detection of breast cancer.
Tasks
Published	2019-12-16
URL	https://arxiv.org/abs/1912.08061v1
PDF	https://arxiv.org/pdf/1912.08061v1.pdf
PWC	https://paperswithcode.com/paper/normalization-of-breast-mris-using-cycle
Repo
Framework

Automatic Dataset Augmentation Using Virtual Human Simulation


Title	Automatic Dataset Augmentation Using Virtual Human Simulation
Authors	Marcelo C. Ghilardi, Leandro Dihl, Estevão Testa, Pedro Braga, João P. Pianta, Isabel H. Manssour, Soraia R. Musse
Abstract	Virtual Human Simulation has been widely used for different purposes, such as comfort or accessibility analysis. In this paper, we investigate the possibility of using this type of technique to extend the training datasets of pedestrians to be used with machine learning techniques. Our main goal is to verify if Computer Graphics (CG) images of virtual humans with a simplistic rendering can be efficient in order to augment datasets used for training machine learning methods. In fact, from a machine learning point of view, there is a need to collect and label large datasets for ground truth, which sometimes demands manual annotation. In addition, find out images and videos with real people and also provide ground truth of people detection and counting is not trivial. If CG images, which can have a ground truth automatically generated, can also be used as training in machine learning techniques for pedestrian detection and counting, it can certainly facilitate and optimize the whole process of event detection. In particular, we propose to parametrize virtual humans using a data-driven approach. Results demonstrated that using the extended datasets with CG images outperforms the results when compared to only real images sequences.
Tasks	Pedestrian Detection
Published	2019-05-01
URL	http://arxiv.org/abs/1905.00261v1
PDF	http://arxiv.org/pdf/1905.00261v1.pdf
PWC	https://paperswithcode.com/paper/automatic-dataset-augmentation-using-virtual
Repo
Framework

CBOWRA: A Representation Learning Approach for Medication Anomaly Detection


Title	CBOWRA: A Representation Learning Approach for Medication Anomaly Detection
Authors	Liang Zhao, Zhiyuan Ma, Yangming Zhou, Kai Wang, Shengping Liu, Ju Gao
Abstract	Electronic health record is an important source for clinical researches and applications, and errors inevitably occur in the data, which could lead to severe damages to both patients and hospital services. One of such error is the mismatches between diagnoses and prescriptions, which we address as ‘medication anomaly’ in the paper, and clinicians used to manually identify and correct them. With the development of machine learning techniques, researchers are able to train specific model for the task, but the process still requires expert knowledge to construct proper features, and few semantic relations are considered. In this paper, we propose a simple, yet effective detection method that tackles the problem by detecting the semantic inconsistency between diagnoses and prescriptions. Unlike traditional outlier or anomaly detection, the scheme uses continuous bag of words to construct the semantic connection between specific central words and their surrounding context. The detection of medication anomaly is transformed into identifying the least possible central word based on given context. To help distinguish the anomaly from normal context, we also incorporate a ranking accumulation strategy. The experiments were conducted on two real hospital electronic medical records, and the topN accuracy of the proposed method increased by 3.91 to 10.91% and 0.68 to 2.13% on the datasets, respectively, which is highly competitive to other traditional machine learning-based approaches.
Tasks	Anomaly Detection, Representation Learning
Published	2019-08-20
URL	https://arxiv.org/abs/1908.07147v2
PDF	https://arxiv.org/pdf/1908.07147v2.pdf
PWC	https://paperswithcode.com/paper/cbowra-a-representation-learning-approach-for
Repo
Framework

Automatic adaptation of object detectors to new domains using self-training


Title	Automatic adaptation of object detectors to new domains using self-training
Authors	Aruni RoyChowdhury, Prithvijit Chakrabarty, Ashish Singh, SouYoung Jin, Huaizu Jiang, Liangliang Cao, Erik Learned-Miller
Abstract	This work addresses the unsupervised adaptation of an existing object detector to a new target domain. We assume that a large number of unlabeled videos from this domain are readily available. We automatically obtain labels on the target data by using high-confidence detections from the existing detector, augmented with hard (misclassified) examples acquired by exploiting temporal cues using a tracker. These automatically-obtained labels are then used for re-training the original model. A modified knowledge distillation loss is proposed, and we investigate several ways of assigning soft-labels to the training examples from the target domain. Our approach is empirically evaluated on challenging face and pedestrian detection tasks: a face detector trained on WIDER-Face, which consists of high-quality images crawled from the web, is adapted to a large-scale surveillance data set; a pedestrian detector trained on clear, daytime images from the BDD-100K driving data set is adapted to all other scenarios such as rainy, foggy, night-time. Our results demonstrate the usefulness of incorporating hard examples obtained from tracking, the advantage of using soft-labels via distillation loss versus hard-labels, and show promising performance as a simple method for unsupervised domain adaptation of object detectors, with minimal dependence on hyper-parameters.
Tasks	Domain Adaptation, Pedestrian Detection, Unsupervised Domain Adaptation
Published	2019-04-15
URL	http://arxiv.org/abs/1904.07305v1
PDF	http://arxiv.org/pdf/1904.07305v1.pdf
PWC	https://paperswithcode.com/paper/automatic-adaptation-of-object-detectors-to
Repo
Framework

Unsupervised Domain Adaptation for Multispectral Pedestrian Detection


Title	Unsupervised Domain Adaptation for Multispectral Pedestrian Detection
Authors	Dayan Guan, Xing Luo, Yanpeng Cao, Jiangxin Yang, Yanlong Cao, George Vosselman, Michael Ying Yang
Abstract	Multimodal information (e.g., visible and thermal) can generate robust pedestrian detections to facilitate around-the-clock computer vision applications, such as autonomous driving and video surveillance. However, it still remains a crucial challenge to train a reliable detector working well in different multispectral pedestrian datasets without manual annotations. In this paper, we propose a novel unsupervised domain adaptation framework for multispectral pedestrian detection, by iteratively generating pseudo annotations and updating the parameters of our designed multispectral pedestrian detector on target domain. Pseudo annotations are generated using the detector trained on source domain, and then updated by fixing the parameters of detector and minimizing the cross entropy loss without back-propagation. Training labels are generated using the pseudo annotations by considering the characteristics of similarity and complementarity between well-aligned visible and infrared image pairs. The parameters of detector are updated using the generated labels by minimizing our defined multi-detection loss function with back-propagation. The optimal parameters of detector can be obtained after iteratively updating the pseudo annotations and parameters. Experimental results show that our proposed unsupervised multimodal domain adaptation method achieves significantly higher detection performance than the approach without domain adaptation, and is competitive with the supervised multispectral pedestrian detectors.
Tasks	Autonomous Driving, Domain Adaptation, Pedestrian Detection, Unsupervised Domain Adaptation
Published	2019-04-07
URL	http://arxiv.org/abs/1904.03692v1
PDF	http://arxiv.org/pdf/1904.03692v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-domain-adaptation-for
Repo
Framework

Linear Context Transform Block


Title	Linear Context Transform Block
Authors	Dongsheng Ruan, Jun Wen, Nenggan Zheng, Min Zheng
Abstract	Squeeze-and-Excitation (SE) block presents a channel attention mechanism for modeling global context via explicitly capturing dependencies across channels. However, we are still far from understanding how the SE block works. In this work, we first revisit the SE block, and then present a detailed empirical study of the relationship between global context and attention distribution, based on which we propose a simple yet effective module, called Linear Context Transform (LCT) block. We divide all channels into different groups and normalize the globally aggregated context features within each channel group, reducing the disturbance from irrelevant channels. Through linear transform of the normalized context features, we model global context for each channel independently. The LCT block is extremely lightweight and easy to be plugged into different backbone models while with negligible parameters and computational burden increase. Extensive experiments show that the LCT block outperforms the SE block in image classification task on the ImageNet and object detection/segmentation on the COCO dataset with different backbone models. Moreover, LCT yields consistent performance gains over existing state-of-the-art detection architectures, e.g., 1.5$\sim$1.7% AP$^{bbox}$ and 1.0$\sim$1.2% AP$^{mask}$ improvements on the COCO benchmark, irrespective of different baseline models of varied capacities. We hope our simple yet effective approach will shed some light on future research of attention-based models.
Tasks	Image Classification, Object Detection
Published	2019-09-06
URL	https://arxiv.org/abs/1909.03834v2
PDF	https://arxiv.org/pdf/1909.03834v2.pdf
PWC	https://paperswithcode.com/paper/linear-context-transform-block
Repo
Framework

The many Shapley values for model explanation


Title	The many Shapley values for model explanation
Authors	Mukund Sundararajan, Amir Najmi
Abstract	The Shapley value has become a popular method to attribute the prediction of a machine-learning model on an input to its base features. The use of the Shapley value is justified by citing [16] showing that it is the \emph{unique} method that satisfies certain good properties (\emph{axioms}). There are, however, a multiplicity of ways in which the Shapley value is operationalized in the attribution problem. These differ in how they reference the model, the training data, and the explanation context. These give very different results, rendering the uniqueness result meaningless. Furthermore, we find that previously proposed approaches can produce counterintuitive attributions in theory and in practice—for instance, they can assign non-zero attributions to features that are not even referenced by the model. In this paper, we use the axiomatic approach to study the differences between some of the many operationalizations of the Shapley value for attribution, and propose a technique called Baseline Shapley (BShap) that is backed by a proper uniqueness result. We also contrast BShap with Integrated Gradients, another extension of Shapley value to the continuous setting.
Tasks	Diabetes Prediction
Published	2019-08-22
URL	https://arxiv.org/abs/1908.08474v2
PDF	https://arxiv.org/pdf/1908.08474v2.pdf
PWC	https://paperswithcode.com/paper/the-many-shapley-values-for-model-explanation
Repo
Framework

A Solution for Dynamic Spectrum Management in Mission-Critical UAV Networks


Title	A Solution for Dynamic Spectrum Management in Mission-Critical UAV Networks
Authors	Alireza Shamsoshoara, Mehrdad Khaledi, Fatemeh Afghah, Abolfazl Razi, Jonathan Ashdown, Kurt Turck
Abstract	In this paper, we study the problem of spectrum scarcity in a network of unmanned aerial vehicles (UAVs) during mission-critical applications such as disaster monitoring and public safety missions, where the pre-allocated spectrum is not sufficient to offer a high data transmission rate for real-time video-streaming. In such scenarios, the UAV network can lease part of the spectrum of a terrestrial licensed network in exchange for providing relaying service. In order to optimize the performance of the UAV network and prolong its lifetime, some of the UAVs will function as a relay for the primary network while the rest of the UAVs carry out their sensing tasks. Here, we propose a team reinforcement learning algorithm performed by the UAV’s controller unit to determine the optimum allocation of sensing and relaying tasks among the UAVs as well as their relocation strategy at each time. We analyze the convergence of our algorithm and present simulation results to evaluate the system throughput in different scenarios.
Tasks
Published	2019-04-16
URL	http://arxiv.org/abs/1904.07380v1
PDF	http://arxiv.org/pdf/1904.07380v1.pdf
PWC	https://paperswithcode.com/paper/a-solution-for-dynamic-spectrum-management-in
Repo
Framework


Title	Attentive Geo-Social Group Recommendation
Authors	Fei Yu, Feiyi Fan, Shouxu Jiang, Kaiping Zheng
Abstract	Social activities play an important role in people’s daily life since they interact. For recommendations based on social activities, it is vital to have not only the activity information but also individuals’ social relations. Thanks to the geo-social networks and widespread use of location-aware mobile devices, massive geo-social data is now readily available for exploitation by the recommendation system. In this paper, a novel group recommendation method, called attentive geo-social group recommendation, is proposed to recommend the target user with both activity locations and a group of users that may join the activities. We present an attention mechanism to model the influence of the target user $u_T$ in candidate user groups that satisfy the social constraints. It helps to retrieve the optimal user group and activity topic candidates, as well as explains the group decision-making process. Once the user group and topics are retrieved, a novel efficient spatial query algorithm SPA-DF is employed to determine the activity location under the constraints of the given user group and activity topic candidates. The proposed method is evaluated in real-world datasets and the experimental results show that the proposed model significantly outperforms baseline methods.
Tasks	Decision Making
Published	2019-11-06
URL	https://arxiv.org/abs/1911.05466v2
PDF	https://arxiv.org/pdf/1911.05466v2.pdf
PWC	https://paperswithcode.com/paper/attentive-geo-social-group-recommendation
Repo
Framework

Towards Efficient Anytime Computation and Execution of Decoupled Robustness Envelopes for Temporal Plans


Title	Towards Efficient Anytime Computation and Execution of Decoupled Robustness Envelopes for Temporal Plans
Authors	Michael Cashmore, Alessandro Cimatti, Daniele Magazzeni, Andrea Micheli, Parisa Zehtabi
Abstract	One of the major limitations for the employment of model-based planning and scheduling in practical applications is the need of costly re-planning when an incongruence between the observed reality and the formal model is encountered during execution. Robustness Envelopes characterize the set of possible contingencies that a plan is able to address without re-planning, but their exact computation is extremely expensive; furthermore, general robustness envelopes are not amenable for efficient execution. In this paper, we present a novel, anytime algorithm to approximate Robustness Envelopes, making them scalable and executable. This is proven by an experimental analysis showing the efficiency of the algorithm, and by a concrete case study where the execution of robustness envelopes significantly reduces the number of re-plannings.
Tasks
Published	2019-11-17
URL	https://arxiv.org/abs/1911.07318v1
PDF	https://arxiv.org/pdf/1911.07318v1.pdf
PWC	https://paperswithcode.com/paper/towards-efficient-anytime-computation-and
Repo
Framework

Modeling the Dynamics of User Preferences for Sequence-Aware Recommendation Using Hidden Markov Models


Title	Modeling the Dynamics of User Preferences for Sequence-Aware Recommendation Using Hidden Markov Models
Authors	Farzad Eskandanian, Bamshad Mobasher
Abstract	In a variety of online settings involving interaction with end-users it is critical for the systems to adapt to changes in user preferences. User preferences on items tend to change over time due to a variety of factors such as change in context, the task being performed, or other short-term or long-term external factors. Recommender systems need to be able to capture these dynamics in user preferences in order to remain tuned to the most current interests of users. In this work we present a recommendation framework which takes into account the dynamics of user preferences. We propose an approach based on Hidden Markov Models (HMM) to identify change-points in the sequence of user interactions which reflect significant changes in preference according to the sequential behavior of all the users in the data. The proposed framework leverages the identified change points to generate recommendations using a sequence-aware non-negative matrix factorization model. We empirically demonstrate the effectiveness of the HMM-based change detection method as compared to standard baseline methods. Additionally, we evaluate the performance of the proposed recommendation method and show that it compares favorably to state-of-the-art sequence-aware recommendation models.
Tasks	Recommendation Systems
Published	2019-05-14
URL	https://arxiv.org/abs/1905.06863v1
PDF	https://arxiv.org/pdf/1905.06863v1.pdf
PWC	https://paperswithcode.com/paper/modeling-the-dynamics-of-user-preferences-for
Repo
Framework