January 29, 2020

2973 words 14 mins read

Paper Group ANR 636

Intelligent Autonomous Things on the Battlefield. Fairness criteria through the lens of directed acyclic graphical models. Rethinking Loss Design for Large-scale 3D Shape Retrieval. An Attentional Neural Network Architecture for Folk Song Classification. Revocable Federated Learning: A Benchmark of Federated Forest. Streaming Batch Eigenupdates for …

Intelligent Autonomous Things on the Battlefield


Title	Intelligent Autonomous Things on the Battlefield
Authors	Alexander Kott, Ethan Stump
Abstract	Numerous, artificially intelligent, networked things will populate the battlefield of the future, operating in close collaboration with human warfighters, and fighting as teams in highly adversarial environments. This chapter explores the characteristics, capabilities and intelli-gence required of such a network of intelligent things and humans - Internet of Battle Things (IOBT). The IOBT will experience unique challenges that are not yet well addressed by the current generation of AI and machine learning.
Tasks
Published	2019-02-26
URL	http://arxiv.org/abs/1902.10086v1
PDF	http://arxiv.org/pdf/1902.10086v1.pdf
PWC	https://paperswithcode.com/paper/intelligent-autonomous-things-on-the
Repo
Framework

Fairness criteria through the lens of directed acyclic graphical models


Title	Fairness criteria through the lens of directed acyclic graphical models
Authors	Benjamin R. Baer, Daniel E. Gilbert, Martin T. Wells
Abstract	A substantial portion of the literature on fairness in algorithms proposes, analyzes, and operationalizes simple formulaic criteria for assessing fairness. Two of these criteria, Equalized Odds and Calibration by Group, have gained significant attention for their simplicity and intuitive appeal, but also for their incompatibility. This chapter provides a perspective on the meaning and consequences of these and other fairness criteria using graphical models which reveals Equalized Odds and related criteria to be ultimately misleading. An assessment of various graphical models suggests that fairness criteria should ultimately be case-specific and sensitive to the nature of the information the algorithm processes.
Tasks	Calibration
Published	2019-06-26
URL	https://arxiv.org/abs/1906.11333v1
PDF	https://arxiv.org/pdf/1906.11333v1.pdf
PWC	https://paperswithcode.com/paper/fairness-criteria-through-the-lens-of
Repo
Framework

Rethinking Loss Design for Large-scale 3D Shape Retrieval


Title	Rethinking Loss Design for Large-scale 3D Shape Retrieval
Authors	Zhaoqun Li, Cheng Xu, Biao Leng
Abstract	Learning discriminative shape representations is a crucial issue for large-scale 3D shape retrieval. In this paper, we propose the Collaborative Inner Product Loss (CIP Loss) to obtain ideal shape embedding that discriminative among different categories and clustered within the same class. Utilizing simple inner product operation, CIP loss explicitly enforces the features of the same class to be clustered in a linear subspace, while inter-class subspaces are constrained to be at least orthogonal. Compared to previous metric loss functions, CIP loss could provide more clear geometric interpretation for the embedding than Euclidean margin, and is easy to implement without normalization operation referring to cosine margin. Moreover, our proposed loss term can combine with other commonly used loss functions and can be easily plugged into existing off-the-shelf architectures. Extensive experiments conducted on the two public 3D object retrieval datasets, ModelNet and ShapeNetCore 55, demonstrate the effectiveness of our proposal, and our method has achieved state-of-the-art results on both datasets.
Tasks	3D Object Retrieval, 3D Shape Retrieval
Published	2019-06-03
URL	https://arxiv.org/abs/1906.00546v1
PDF	https://arxiv.org/pdf/1906.00546v1.pdf
PWC	https://paperswithcode.com/paper/190600546
Repo
Framework

An Attentional Neural Network Architecture for Folk Song Classification


Title	An Attentional Neural Network Architecture for Folk Song Classification
Authors	Aitor Arronte-Alvarez, Francisco Gomez-Martin
Abstract	In this paper we present an attentional neural network for folk song classification. We introduce the concept of musical motif embedding, and show how using melodic local context we are able to model monophonic folk song motifs using the skipgram version of the word2vec algorithm. We use the motif embeddings to represent folk songs from Germany, China, and Sweden, and classify them using an attentional neural network that is able to discern relevant motifs in a song. The results show how the network obtains state of the art accuracy in a completely unsupervised manner, and how motif embeddings produce high quality motif representations from folk songs. We conjecture on the advantages of this type of representation in large symbolic music corpora, and how it can be helpful in the musicological analysis of folk song collections from different cultures and geographical areas.
Tasks
Published	2019-04-24
URL	http://arxiv.org/abs/1904.11074v1
PDF	http://arxiv.org/pdf/1904.11074v1.pdf
PWC	https://paperswithcode.com/paper/an-attentional-neural-network-architecture
Repo
Framework

Revocable Federated Learning: A Benchmark of Federated Forest


Title	Revocable Federated Learning: A Benchmark of Federated Forest
Authors	Yang Liu, Zhuo Ma, Ximeng Liu, Zhuzhu Wang, Siqi Ma, Ken Ren
Abstract	A learning federation is composed of multiple participants who use the federated learning technique to collaboratively train a machine learning model without directly revealing the local data. Nevertheless, the existing federated learning frameworks have a serious defect that even a participant is revoked, its data are still remembered by the trained model. In a company-level cooperation, allowing the remaining companies to use a trained model that contains the memories from a revoked company is obviously unacceptable, because it can lead to a big conflict of interest. Therefore, we emphatically discuss the participant revocation problem of federated learning and design a revocable federated random forest (RF) framework, RevFRF, to further illustrate the concept of revocable federated learning. In RevFRF, we first define the security problems to be resolved by a revocable federated RF. Then, a suite of homomorphic encryption based secure protocols are designed for federated RF construction, prediction and revocation. Through theoretical analysis and experiments, we show that the protocols can securely and efficiently implement collaborative training of an RF and ensure that the memories of a revoked participant in the trained RF are securely removed.
Tasks
Published	2019-11-08
URL	https://arxiv.org/abs/1911.03242v1
PDF	https://arxiv.org/pdf/1911.03242v1.pdf
PWC	https://paperswithcode.com/paper/revocable-federated-learning-a-benchmark-of
Repo
Framework

Streaming Batch Eigenupdates for Hardware Neuromorphic Networks


Title	Streaming Batch Eigenupdates for Hardware Neuromorphic Networks
Authors	Brian D. Hoskins, Matthew W. Daniels, Siyuan Huang, Advait Madhavan, Gina C. Adam, Nikolai Zhitenev, Jabez J. McClelland, Mark D. Stiles
Abstract	Neuromorphic networks based on nanodevices, such as metal oxide memristors, phase change memories, and flash memory cells, have generated considerable interest for their increased energy efficiency and density in comparison to graphics processing units (GPUs) and central processing units (CPUs). Though immense acceleration of the training process can be achieved by leveraging the fact that the time complexity of training does not scale with the network size, it is limited by the space complexity of stochastic gradient descent, which grows quadratically. The main objective of this work is to reduce this space complexity by using low-rank approximations of stochastic gradient descent. This low spatial complexity combined with streaming methods allows for significant reductions in memory and compute overhead, opening the doors for improvements in area, time and energy efficiency of training. We refer to this algorithm and architecture to implement it as the streaming batch eigenupdate (SBE) approach.
Tasks
Published	2019-03-05
URL	http://arxiv.org/abs/1903.01635v1
PDF	http://arxiv.org/pdf/1903.01635v1.pdf
PWC	https://paperswithcode.com/paper/streaming-batch-eigenupdates-for-hardware
Repo
Framework

HPILN: A feature learning framework for cross-modality person re-identification


Title	HPILN: A feature learning framework for cross-modality person re-identification
Authors	Jian-Wu Lin, Hao Li
Abstract	Most video surveillance systems use both RGB and infrared cameras, making it a vital technique to re-identify a person cross the RGB and infrared modalities. This task can be challenging due to both the cross-modality variations caused by heterogeneous images in RGB and infrared, and the intra-modality variations caused by the heterogeneous human poses, camera views, light brightness, etc. To meet these challenges a novel feature learning framework, HPILN, is proposed. In the framework existing single-modality re-identification models are modified to fit for the cross-modality scenario, following which specifically designed hard pentaplet loss and identity loss are used to improve the performance of the modified cross-modality re-identification models. Based on the benchmark of the SYSU-MM01 dataset, extensive experiments have been conducted, which show that the proposed method outperforms all existing methods in terms of Cumulative Match Characteristic curve (CMC) and Mean Average Precision (MAP).
Tasks	Person Re-Identification
Published	2019-06-07
URL	https://arxiv.org/abs/1906.03142v2
PDF	https://arxiv.org/pdf/1906.03142v2.pdf
PWC	https://paperswithcode.com/paper/hpiln-a-feature-learning-framework-for-cross
Repo
Framework

Microlens array grid estimation, light field decoding, and calibration


Title	Microlens array grid estimation, light field decoding, and calibration
Authors	Maximilian Schambach, Fernando Puente León
Abstract	We quantitatively investigate multiple algorithms for microlens array grid estimation for microlens array-based light field cameras. Explicitly taking into account natural and mechanical vignetting effects, we propose a new method for microlens array grid estimation that outperforms the ones previously discussed in the literature. To quantify the performance of the algorithms, we propose an evaluation pipeline utilizing application-specific ray-traced white images with known microlens positions. Using a large dataset of synthesized white images, we thoroughly compare the performance of the different estimation algorithms. As an example, we apply our results to the decoding and calibration of light fields taken with a Lytro Illum camera. We observe that decoding as well as calibration benefit from a more accurate, vignetting-aware grid estimation, especially in peripheral subapertures of the light field.
Tasks	Calibration
Published	2019-12-31
URL	https://arxiv.org/abs/1912.13298v1
PDF	https://arxiv.org/pdf/1912.13298v1.pdf
PWC	https://paperswithcode.com/paper/microlens-array-grid-estimation-light-field
Repo
Framework

TOCO: A Framework for Compressing Neural Network Models Based on Tolerance Analysis


Title	TOCO: A Framework for Compressing Neural Network Models Based on Tolerance Analysis
Authors	Soroosh Khoram, Jing Li
Abstract	Neural network compression methods have enabled deploying large models on emerging edge devices with little cost, by adapting already-trained models to the constraints of these devices. The rapid development of AI-capable edge devices with limited computation and storage requires streamlined methodologies that can efficiently satisfy the constraints of different devices. In contrast, existing methods often rely on heuristic and manual adjustments to maintain accuracy, support only coarse compression policies, or target specific device constraints that limit their applicability. We address these limitations by proposing the TOlerance-based COmpression (TOCO) framework. TOCO uses an in-depth analysis of the model, to maintain the accuracy, in an active learning system. The results of the analysis are tolerances that can be used to perform compression in a fine-grained manner. Finally, by decoupling compression from the tolerance analysis, TOCO allows flexibility to changes in the hardware.
Tasks	Active Learning, Neural Network Compression
Published	2019-12-18
URL	https://arxiv.org/abs/1912.08792v2
PDF	https://arxiv.org/pdf/1912.08792v2.pdf
PWC	https://paperswithcode.com/paper/toco-a-framework-for-compressing-neural
Repo
Framework

Single-Shot Panoptic Segmentation


Title	Single-Shot Panoptic Segmentation
Authors	Mark Weber, Jonathon Luiten, Bastian Leibe
Abstract	We present a novel end-to-end single-shot method that segments countable object instances (things) as well as background regions (stuff) into a non-overlapping panoptic segmentation at almost video frame rate. Current state-of-the-art methods are far from reaching video frame rate and mostly rely on merging instance segmentation with semantic background segmentation. Our approach relaxes this requirement by using an object detector but is still able to resolve inter- and intra-class overlaps to achieve a non-overlapping segmentation. On top of a shared encoder-decoder backbone, we utilize multiple branches for semantic segmentation, object detection, and instance center prediction. Finally, our panoptic head combines all outputs into a panoptic segmentation and can even handle conflicting predictions between branches as well as certain false predictions. Our network achieves 32.6% PQ on MS-COCO at 21.8 FPS, opening up panoptic segmentation to a broader field of applications.
Tasks	Instance Segmentation, Object Detection, Panoptic Segmentation, Semantic Segmentation
Published	2019-11-02
URL	https://arxiv.org/abs/1911.00764v1
PDF	https://arxiv.org/pdf/1911.00764v1.pdf
PWC	https://paperswithcode.com/paper/single-shot-panoptic-segmentation
Repo
Framework

Integration of Text-maps in Convolutional Neural Networks for Region Detection among Different Textual Categories


Title	Integration of Text-maps in Convolutional Neural Networks for Region Detection among Different Textual Categories
Authors	Roberto Arroyo, Javier Tovar, Francisco J. Delgado, Emilio J. Almazán, Diego G. Serrador, Antonio Hurtado
Abstract	In this work, we propose a new technique that combines appearance and text in a Convolutional Neural Network (CNN), with the aim of detecting regions of different textual categories. We define a novel visual representation of the semantic meaning of text that allows a seamless integration in a standard CNN architecture. This representation, referred to as text-map, is integrated with the actual image to provide a much richer input to the network. Text-maps are colored with different intensities depending on the relevance of the words recognized over the image. Concretely, these words are previously extracted using Optical Character Recognition (OCR) and they are colored according to the probability of belonging to a textual category of interest. In this sense, this solution is especially relevant in the context of item coding for supermarket products, where different types of textual categories must be identified, such as ingredients or nutritional facts. We evaluated our solution in the proprietary item coding dataset of Nielsen Brandbank, which contains more than 10,000 images for train and 2,000 images for test. The reported results demonstrate that our approach focused on visual and textual data outperforms state-of-the-art algorithms only based on appearance, such as standard Faster R-CNN. These enhancements are reflected in precision and recall, which are improved in 42 and 33 points respectively.
Tasks	Optical Character Recognition
Published	2019-05-26
URL	https://arxiv.org/abs/1905.10858v1
PDF	https://arxiv.org/pdf/1905.10858v1.pdf
PWC	https://paperswithcode.com/paper/integration-of-text-maps-in-convolutional
Repo
Framework

An Ensemble Approach toward Automated Variable Selection for Network Anomaly Detection


Title	An Ensemble Approach toward Automated Variable Selection for Network Anomaly Detection
Authors	Makiya Nakashima, Alex Sim, Youngsoo Kim, Jonghyun Kim, Jinoh Kim
Abstract	While variable selection is essential to optimize the learning complexity by prioritizing features, automating the selection process is preferred since it requires laborious efforts with intensive analysis otherwise. However, it is not an easy task to enable the automation due to several reasons. First, selection techniques often need a condition to terminate the reduction process, for example, by using a threshold or the number of features to stop, and searching an adequate stopping condition is highly challenging. Second, it is uncertain that the reduced variable set would work well; our preliminary experimental result shows that well-known selection techniques produce different sets of variables as a result of reduction (even with the same termination condition), and it is hard to estimate which of them would work the best in future testing. In this paper, we demonstrate the potential power of our approach to the automation of selection process that incorporates well-known selection methods identifying important variables. Our experimental results with two public network traffic data (UNSW-NB15 and IDS2017) show that our proposed method identifies a small number of core variables, with which it is possible to approximate the performance to the one with the entire variables.
Tasks	Anomaly Detection
Published	2019-10-28
URL	https://arxiv.org/abs/1910.12806v1
PDF	https://arxiv.org/pdf/1910.12806v1.pdf
PWC	https://paperswithcode.com/paper/an-ensemble-approach-toward-automated
Repo
Framework

Collecting Indicators of Compromise from Unstructured Text of Cybersecurity Articles using Neural-Based Sequence Labelling


Title	Collecting Indicators of Compromise from Unstructured Text of Cybersecurity Articles using Neural-Based Sequence Labelling
Authors	Zi Long, Lianzhi Tan, Shengping Zhou, Chaoyang He, Xin Liu
Abstract	Indicators of Compromise (IOCs) are artifacts observed on a network or in an operating system that can be utilized to indicate a computer intrusion and detect cyber-attacks in an early stage. Thus, they exert an important role in the field of cybersecurity. However, state-of-the-art IOCs detection systems rely heavily on hand-crafted features with expert knowledge of cybersecurity, and require large-scale manually annotated corpora to train an IOC classifier. In this paper, we propose using an end-to-end neural-based sequence labelling model to identify IOCs automatically from cybersecurity articles without expert knowledge of cybersecurity. By using a multi-head self-attention module and contextual features, we find that the proposed model is capable of gathering contextual information from texts of cybersecurity articles and performs better in the task of IOC identification. Experiments show that the proposed model outperforms other sequence labelling models, achieving the average F1-score of 89.0% on English cybersecurity article test set, and approximately the average F1-score of 81.8% on Chinese test set.
Tasks
Published	2019-07-04
URL	https://arxiv.org/abs/1907.02636v2
PDF	https://arxiv.org/pdf/1907.02636v2.pdf
PWC	https://paperswithcode.com/paper/collecting-indicators-of-compromise-from
Repo
Framework

Age of Information-Aware Radio Resource Management in Vehicular Networks: A Proactive Deep Reinforcement Learning Perspective


Title	Age of Information-Aware Radio Resource Management in Vehicular Networks: A Proactive Deep Reinforcement Learning Perspective
Authors	Xianfu Chen, Celimuge Wu, Tao Chen, Honggang Zhang, Zhi Liu, Yan Zhang, Mehdi Bennis
Abstract	In this paper, we investigate the problem of age of information (AoI)-aware radio resource management for expected long-term performance optimization in a Manhattan grid vehicle-to-vehicle network. With the observation of global network state at each scheduling slot, the roadside unit (RSU) allocates the frequency bands and schedules packet transmissions for all vehicle user equipment-pairs (VUE-pairs). We model the stochastic decision-making procedure as a discrete-time single-agent Markov decision process (MDP). The technical challenges in solving the optimal control policy originate from high spatial mobility and temporally varying traffic information arrivals of the VUE-pairs. To make the problem solving tractable, we first decompose the original MDP into a series of per-VUE-pair MDPs. Then we propose a proactive algorithm based on long short-term memory and deep reinforcement learning techniques to address the partial observability and the curse of high dimensionality in local network state space faced by each VUE-pair. With the proposed algorithm, the RSU makes the optimal frequency band allocation and packet scheduling decision at each scheduling slot in a decentralized way in accordance with the partial observations of the global network state at the VUE-pairs. Numerical experiments validate the theoretical analysis and demonstrate the significant performance improvements from the proposed algorithm.
Tasks	Decision Making
Published	2019-08-06
URL	https://arxiv.org/abs/1908.02047v2
PDF	https://arxiv.org/pdf/1908.02047v2.pdf
PWC	https://paperswithcode.com/paper/age-of-information-aware-radio-resource
Repo
Framework

Stuck? No worries!: Task-aware Command Recommendation and Proactive Help for Analysts


Title	Stuck? No worries!: Task-aware Command Recommendation and Proactive Help for Analysts
Authors	Aadhavan M. Nambhi, Bhanu Prakash Reddy, Aarsh Prakash Agarwal, Gaurav Verma, Harvineet Singh, Iftikhar Ahamath Burhanuddin
Abstract	Data analytics software applications have become an integral part of the decision-making process of analysts. Users of such a software face challenges due to insufficient product and domain knowledge, and find themselves in need of help. To alleviate this, we propose a task-aware command recommendation system, to guide the user on what commands could be executed next. We rely on topic modeling techniques to incorporate information about user’s task into our models. We also present a help prediction model to detect if a user is in need of help, in which case the system proactively provides the aforementioned command recommendations. We leverage the log data of a web-based analytics software to quantify the superior performance of our neural models, in comparison to competitive baselines.
Tasks	Decision Making
Published	2019-06-21
URL	https://arxiv.org/abs/1906.08973v1
PDF	https://arxiv.org/pdf/1906.08973v1.pdf
PWC	https://paperswithcode.com/paper/stuck-no-worries-task-aware-command
Repo
Framework