April 3, 2020

3248 words 16 mins read

Paper Group ANR 31

Paper Group ANR 31

Multi-Agent Reinforcement Learning for Problems with Combined Individual and Team Reward. RePAD: Real-time Proactive Anomaly Detection for Time Series. Better Boosting with Bandits for Online Learning. Dynamic ReLU. Accurately identifying vertebral levels in large datasets. Turning 30: New Ideas in Inductive Logic Programming. TGGLines: A Robust To …

Multi-Agent Reinforcement Learning for Problems with Combined Individual and Team Reward

Title Multi-Agent Reinforcement Learning for Problems with Combined Individual and Team Reward
Authors Hassam Ullah Sheikh, Ladislau Bölöni
Abstract Many cooperative multi-agent problems require agents to learn individual tasks while contributing to the collective success of the group. This is a challenging task for current state-of-the-art multi-agent reinforcement algorithms that are designed to either maximize the global reward of the team or the individual local rewards. The problem is exacerbated when either of the rewards is sparse leading to unstable learning. To address this problem, we present Decomposed Multi-Agent Deep Deterministic Policy Gradient (DE-MADDPG): a novel cooperative multi-agent reinforcement learning framework that simultaneously learns to maximize the global and local rewards. We evaluate our solution on the challenging defensive escort team problem and show that our solution achieves a significantly better and more stable performance than the direct adaptation of the MADDPG algorithm.
Tasks Multi-agent Reinforcement Learning
Published 2020-03-24
URL https://arxiv.org/abs/2003.10598v1
PDF https://arxiv.org/pdf/2003.10598v1.pdf
PWC https://paperswithcode.com/paper/multi-agent-reinforcement-learning-for-1

RePAD: Real-time Proactive Anomaly Detection for Time Series

Title RePAD: Real-time Proactive Anomaly Detection for Time Series
Authors Ming-Chang Lee, Jia-Chun Lin, Ernst Gunnar Gran
Abstract During the past decade, many anomaly detection approaches have been introduced in different fields such as network monitoring, fraud detection, and intrusion detection. However, they require understanding of data pattern and often need a long off-line period to build a model or network for the target data. Providing real-time and proactive anomaly detection for streaming time series without human intervention and domain knowledge is highly valuable since it greatly reduces human effort and enables appropriate countermeasures to be undertaken before a disastrous damage, failure, or other harmful event occurs. However, this issue has not been well studied yet. To address it, this paper proposes RePAD, which is a Real-time Proactive Anomaly Detection algorithm for streaming time series based on Long Short-Term Memory (LSTM). RePAD utilizes short-term historic data points to predict and determine whether or not the upcoming data point is a sign that an anomaly is likely to happen in the near future. By dynamically adjusting the detection threshold over time, RePAD is able to tolerate minor pattern change in time series and detect anomalies either proactively or on time. Experiments based on two time series datasets collected from the Numenta Anomaly Benchmark demonstrate that RePAD is able to proactively detect anomalies and provide early warnings in real time without human intervention and domain knowledge.
Tasks Anomaly Detection, Fraud Detection, Intrusion Detection, Time Series
Published 2020-01-24
URL https://arxiv.org/abs/2001.08922v3
PDF https://arxiv.org/pdf/2001.08922v3.pdf
PWC https://paperswithcode.com/paper/repad-real-time-proactive-anomaly-detection

Better Boosting with Bandits for Online Learning

Title Better Boosting with Bandits for Online Learning
Authors Nikolaos Nikolaou, Joseph Mellor, Nikunj C. Oza, Gavin Brown
Abstract Probability estimates generated by boosting ensembles are poorly calibrated because of the margin maximization nature of the algorithm. The outputs of the ensemble need to be properly calibrated before they can be used as probability estimates. In this work, we demonstrate that online boosting is also prone to producing distorted probability estimates. In batch learning, calibration is achieved by reserving part of the training data for training the calibrator function. In the online setting, a decision needs to be made on each round: shall the new example(s) be used to update the parameters of the ensemble or those of the calibrator. We proceed to resolve this decision with the aid of bandit optimization algorithms. We demonstrate superior performance to uncalibrated and naively-calibrated on-line boosting ensembles in terms of probability estimation. Our proposed mechanism can be easily adapted to other tasks(e.g. cost-sensitive classification) and is robust to the choice of hyperparameters of both the calibrator and the ensemble.
Tasks Calibration
Published 2020-01-16
URL https://arxiv.org/abs/2001.06105v1
PDF https://arxiv.org/pdf/2001.06105v1.pdf
PWC https://paperswithcode.com/paper/better-boosting-with-bandits-for-online

Dynamic ReLU

Title Dynamic ReLU
Authors Yinpeng Chen, Xiyang Dai, Mengchen Liu, Dongdong Chen, Lu Yuan, Zicheng Liu
Abstract Rectified linear units (ReLU) are commonly used in deep neural networks. So far ReLU and its generalizations (either non-parametric or parametric) are static, performing identically for all input samples. In this paper, we propose Dynamic ReLU (DY-ReLU), a dynamic rectifier whose parameters are input-dependent as a hyper function over all input elements. The key insight is that DY-ReLU encodes the global context into the hyper function and adapts the piecewise linear activation function accordingly. Compared to its static counterpart, DY-ReLU has negligible extra computational cost, but significantly more representation capability, especially for light-weight neural networks. By simply using DY-ReLU for MobileNetV2, the top-1 accuracy on ImageNet classification is boosted from 72.0% to 76.2% with only 5% additional FLOPs.
Published 2020-03-22
URL https://arxiv.org/abs/2003.10027v1
PDF https://arxiv.org/pdf/2003.10027v1.pdf
PWC https://paperswithcode.com/paper/dynamic-relu

Accurately identifying vertebral levels in large datasets

Title Accurately identifying vertebral levels in large datasets
Authors Daniel C. Elton, Veit Sandfort, Perry J. Pickhardt, Ronald M. Summers
Abstract The vertebral levels of the spine provide a useful coordinate system when making measurements of plaque, muscle, fat, and bone mineral density. Correctly classifying vertebral levels with high accuracy is challenging due to the similar appearance of each vertebra, the curvature of the spine, and the possibility of anomalies such as fractured vertebrae, implants, lumbarization of the sacrum, and sacralization of L5. The goal of this work is to develop a system that can accurately and robustly identify the L1 level in large heterogeneous datasets. The first approach we study is using a 3D U-Net to segment the L1 vertebra directly using the entire scan volume to provide context. We also tested models for two class segmentation of L1 and T12 and a three class segmentation of L1, T12 and the rib attached to T12. By increasing the number of training examples to 249 scans using pseudo-segmentations from an in-house segmentation tool we were able to achieve 98% accuracy with respect to identifying the L1 vertebra, with an average error of 4.5 mm in the craniocaudal level. We next developed an algorithm which performs iterative instance segmentation and classification of the entire spine with a 3D U-Net. We found the instance based approach was able to yield better segmentations of nearly the entire spine, but had lower classification accuracy for L1.
Tasks Instance Segmentation, Semantic Segmentation
Published 2020-01-28
URL https://arxiv.org/abs/2001.10503v1
PDF https://arxiv.org/pdf/2001.10503v1.pdf
PWC https://paperswithcode.com/paper/accurately-identifying-vertebral-levels-in

Turning 30: New Ideas in Inductive Logic Programming

Title Turning 30: New Ideas in Inductive Logic Programming
Authors Andrew Cropper, Sebastijan Dumančić, Stephen H. Muggleton
Abstract Common criticisms of state-of-the-art machine learning include poor generalisation, a lack of interpretability, and a need for large amounts of training data. We survey recent work in inductive logic programming (ILP), a form of machine learning that induces logic programs from data, which has shown promise at addressing these limitations. We focus on new methods for learning recursive programs that generalise from few examples, a shift from using hand-crafted background knowledge to \emph{learning} background knowledge, and the use of different technologies, notably answer set programming and neural networks. As ILP approaches 30, we also discuss directions for future research.
Published 2020-02-25
URL https://arxiv.org/abs/2002.11002v3
PDF https://arxiv.org/pdf/2002.11002v3.pdf
PWC https://paperswithcode.com/paper/turning-30-new-ideas-in-inductive-logic

TGGLines: A Robust Topological Graph Guided Line Segment Detector for Low Quality Binary Images

Title TGGLines: A Robust Topological Graph Guided Line Segment Detector for Low Quality Binary Images
Authors Ming Gong, Liping Yang, Catherine Potts, Vijayan K. Asari, Diane Oyen, Brendt Wohlberg
Abstract Line segment detection is an essential task in computer vision and image analysis, as it is the critical foundation for advanced tasks such as shape modeling and road lane line detection for autonomous driving. We present a robust topological graph guided approach for line segment detection in low quality binary images (hence, we call it TGGLines). Due to the graph-guided approach, TGGLines not only detects line segments, but also organizes the segments with a line segment connectivity graph, which means the topological relationships (e.g., intersection, an isolated line segment) of the detected line segments are captured and stored; whereas other line detectors only retain a collection of loose line segments. Our empirical results show that the TGGLines detector visually and quantitatively outperforms state-of-the-art line segment detection methods. In addition, our TGGLines approach has the following two competitive advantages: (1) our method only requires one parameter and it is adaptive, whereas almost all other line segment detection methods require multiple (non-adaptive) parameters, and (2) the line segments detected by TGGLines are organized by a line segment connectivity graph.
Tasks Autonomous Driving, Line Segment Detection
Published 2020-02-27
URL https://arxiv.org/abs/2002.12428v1
PDF https://arxiv.org/pdf/2002.12428v1.pdf
PWC https://paperswithcode.com/paper/tgglines-a-robust-topological-graph-guided

BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning

Title BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning
Authors Yeming Wen, Dustin Tran, Jimmy Ba
Abstract Ensembles, where multiple neural networks are trained individually and their predictions are averaged, have been shown to be widely successful for improving both the accuracy and predictive uncertainty of single neural networks. However, an ensemble’s cost for both training and testing increases linearly with the number of networks, which quickly becomes untenable. In this paper, we propose BatchEnsemble, an ensemble method whose computational and memory costs are significantly lower than typical ensembles. BatchEnsemble achieves this by defining each weight matrix to be the Hadamard product of a shared weight among all ensemble members and a rank-one matrix per member. Unlike ensembles, BatchEnsemble is not only parallelizable across devices, where one device trains one member, but also parallelizable within a device, where multiple ensemble members are updated simultaneously for a given mini-batch. Across CIFAR-10, CIFAR-100, WMT14 EN-DE/EN-FR translation, and out-of-distribution tasks, BatchEnsemble yields competitive accuracy and uncertainties as typical ensembles; the speedup at test time is 3X and memory reduction is 3X at an ensemble of size 4. We also apply BatchEnsemble to lifelong learning, where on Split-CIFAR-100, BatchEnsemble yields comparable performance to progressive neural networks while having a much lower computational and memory costs. We further show that BatchEnsemble can easily scale up to lifelong learning on Split-ImageNet which involves 100 sequential learning tasks.
Published 2020-02-17
URL https://arxiv.org/abs/2002.06715v2
PDF https://arxiv.org/pdf/2002.06715v2.pdf
PWC https://paperswithcode.com/paper/batchensemble-an-alternative-approach-to-1

Deep Attention Aware Feature Learning for Person Re-Identification

Title Deep Attention Aware Feature Learning for Person Re-Identification
Authors Yifan Chen, Han Wang, Xiaolu Sun, Bin Fan, Chu Tang
Abstract Visual attention has proven to be effective in improving the performance of person re-identification. Most existing methods apply visual attention heuristically by learning an additional attention map to re-weight the feature maps for person re-identification. However, this kind of methods inevitably increase the model complexity and inference time. In this paper, we propose to incorporate the attention learning as additional objectives in a person ReID network without changing the original structure, thus maintain the same inference time and model size. Two kinds of attentions have been considered to make the learned feature maps being aware of the person and related body parts respectively. Globally, a holistic attention branch (HAB) makes the feature maps obtained by backbone focus on persons so as to alleviate the influence of background. Locally, a partial attention branch (PAB) makes the extracted features be decoupled into several groups and be separately responsible for different body parts (i.e., keypoints), thus increasing the robustness to pose variation and partial occlusion. These two kinds of attentions are universal and can be incorporated into existing ReID networks. We have tested its performance on two typical networks (TriNet and Bag of Tricks) and observed significant performance improvement on five widely used datasets.
Tasks Deep Attention, Person Re-Identification
Published 2020-03-01
URL https://arxiv.org/abs/2003.00517v1
PDF https://arxiv.org/pdf/2003.00517v1.pdf
PWC https://paperswithcode.com/paper/deep-attention-aware-feature-learning-for

Personalized Federated Learning for Intelligent IoT Applications: A Cloud-Edge based Framework

Title Personalized Federated Learning for Intelligent IoT Applications: A Cloud-Edge based Framework
Authors Qiong Wu, Kaiwen He, Xu Chen
Abstract Internet of Things (IoT) have widely penetrated in different aspects of modern life and many intelligent IoT services and applications are emerging. Recently, federated learning is proposed to train a globally shared model by exploiting a massive amount of user-generated data samples on IoT devices while preventing data leakage. However, the device, statistical and model heterogeneities inherent in the complex IoT environments pose great challenges to traditional federated learning, making it unsuitable to be directly deployed. In this article we advocate a personalized federated learning framework in a cloud-edge architecture for intelligent IoT applications. To cope with the heterogeneity issues in IoT environments, we investigate emerging personalized federated learning methods which are able to mitigate the negative effects caused by heterogeneity in different aspects. With the power of edge computing, the requirements for fast-processing capacity and low latency in intelligent IoT applications can also be achieved. We finally provide a case study of IoT based human activity recognition to demonstrate the effectiveness of personalized federated learning for intelligent IoT applications.
Tasks Activity Recognition, Human Activity Recognition
Published 2020-02-25
URL https://arxiv.org/abs/2002.10671v2
PDF https://arxiv.org/pdf/2002.10671v2.pdf
PWC https://paperswithcode.com/paper/personalized-federated-learning-for

End-to-End Automatic Speech Recognition Integrated With CTC-Based Voice Activity Detection

Title End-to-End Automatic Speech Recognition Integrated With CTC-Based Voice Activity Detection
Authors Takenori Yoshimura, Tomoki Hayashi, Kazuya Takeda, Shinji Watanabe
Abstract This paper integrates a voice activity detection (VAD) function with end-to-end automatic speech recognition toward an online speech interface and transcribing very long audio recordings. We focus on connectionist temporal classification (CTC) and its extension of CTC/attention architectures. As opposed to an attention-based architecture, input-synchronous label prediction can be performed based on a greedy search with the CTC (pre-)softmax output. This prediction includes consecutive long blank labels, which can be regarded as a non-speech region. We use the labels as a cue for detecting speech segments with simple thresholding. The threshold value is directly related to the length of a non-speech region, which is more intuitive and easier to control than conventional VAD hyperparameters. Experimental results on unsegmented data show that the proposed method outperformed the baseline methods using the conventional energy-based and neural-network-based VAD methods and achieved an RTF less than 0.2. The proposed method is publicly available.
Tasks Action Detection, Activity Detection, Speech Recognition
Published 2020-02-03
URL https://arxiv.org/abs/2002.00551v2
PDF https://arxiv.org/pdf/2002.00551v2.pdf
PWC https://paperswithcode.com/paper/end-to-end-automatic-speech-recognition

Facebook Ads Monitor: An Independent Auditing System for Political Ads on Facebook

Title Facebook Ads Monitor: An Independent Auditing System for Political Ads on Facebook
Authors Márcio Silva, Lucas Santos de Oliveira, Athanasios Andreou, Pedro Olmo Vaz de Melo, Oana Goga, Fabrício Benevenuto
Abstract The 2016 United States presidential election was marked by the abuse of targeted advertising on Facebook. Concerned with the risk of the same kind of abuse to happen in the 2018 Brazilian elections, we designed and deployed an independent auditing system to monitor political ads on Facebook in Brazil. To do that we first adapted a browser plugin to gather ads from the timeline of volunteers using Facebook. We managed to convince more than 2000 volunteers to help our project and install our tool. Then, we use a Convolution Neural Network (CNN) to detect political Facebook ads using word embeddings. To evaluate our approach, we manually label a data collection of 10k ads as political or non-political and then we provide an in-depth evaluation of proposed approach for identifying political ads by comparing it with classic supervised machine learning methods. Finally, we deployed a real system that shows the ads identified as related to politics. We noticed that not all political ads we detected were present in the Facebook Ad Library for political ads. Our results emphasize the importance of enforcement mechanisms for declaring political ads and the need for independent auditing platforms.
Tasks Word Embeddings
Published 2020-01-28
URL https://arxiv.org/abs/2001.10581v2
PDF https://arxiv.org/pdf/2001.10581v2.pdf
PWC https://paperswithcode.com/paper/facebook-ads-monitor-an-independent-auditing

Cross-modality Person re-identification with Shared-Specific Feature Transfer

Title Cross-modality Person re-identification with Shared-Specific Feature Transfer
Authors Yan Lu, Yue Wu, Bin Liu, Tianzhu Zhang, Baopu Li, Qi Chu, Nenghai Yu
Abstract Cross-modality person re-identification (cm-ReID) is a challenging but key technology for intelligent video analysis. Existing works mainly focus on learning common representation by embedding different modalities into a same feature space. However, only learning the common characteristics means great information loss, lowering the upper bound of feature distinctiveness. In this paper, we tackle the above limitation by proposing a novel cross-modality shared-specific feature transfer algorithm (termed cm-SSFT) to explore the potential of both the modality-shared information and the modality-specific characteristics to boost the re-identification performance. We model the affinities of different modality samples according to the shared features and then transfer both shared and specific features among and across modalities. We also propose a complementary feature learning strategy including modality adaption, project adversarial learning and reconstruction enhancement to learn discriminative and complementary shared and specific features of each modality, respectively. The entire cm-SSFT algorithm can be trained in an end-to-end manner. We conducted comprehensive experiments to validate the superiority of the overall algorithm and the effectiveness of each component. The proposed algorithm significantly outperforms state-of-the-arts by 22.5% and 19.3% mAP on the two mainstream benchmark datasets SYSU-MM01 and RegDB, respectively.
Tasks Person Re-Identification
Published 2020-02-28
URL https://arxiv.org/abs/2002.12489v3
PDF https://arxiv.org/pdf/2002.12489v3.pdf
PWC https://paperswithcode.com/paper/cross-modality-person-re-identification-with

Importance of using appropriate baselines for evaluation of data-efficiency in deep reinforcement learning for Atari

Title Importance of using appropriate baselines for evaluation of data-efficiency in deep reinforcement learning for Atari
Authors Kacper Kielak
Abstract Reinforcement learning (RL) has seen great advancements in the past few years. Nevertheless, the consensus among the RL community is that currently used methods, despite all their benefits, suffer from extreme data inefficiency, especially in the rich visual domains like Atari. To circumvent this problem, novel approaches were introduced that often claim to be much more efficient than popular variations of the state-of-the-art DQN algorithm. In this paper, however, we demonstrate that the newly proposed techniques simply used unfair baselines in their experiments. Namely, we show that the actual improvement in the efficiency came from allowing the algorithm for more training updates for each data sample, and not from employing the new methods. By allowing DQN to execute network updates more frequently we manage to reach similar or better results than the recently proposed advancement, often at a fraction of complexity and computational costs. Furthermore, based on the outcomes of the study, we argue that the agent similar to the modified DQN that is presented in this paper should be used as a baseline for any future work aimed at improving sample efficiency of deep reinforcement learning.
Published 2020-03-23
URL https://arxiv.org/abs/2003.10181v2
PDF https://arxiv.org/pdf/2003.10181v2.pdf
PWC https://paperswithcode.com/paper/do-recent-advancements-in-model-based-deep-1

Stan: Small tumor-aware network for breast ultrasound image segmentation

Title Stan: Small tumor-aware network for breast ultrasound image segmentation
Authors Bryar Shareef, Min Xian, Aleksandar Vakanski
Abstract Breast tumor segmentation provides accurate tumor boundary, and serves as a key step toward further cancer quantification. Although deep learning-based approaches have been proposed and achieved promising results, existing approaches have difficulty in detecting small breast tumors. The capacity to detecting small tumors is particularly important in finding early stage cancers using computer-aided diagnosis (CAD) systems. In this paper, we propose a novel deep learning architecture called Small Tumor-Aware Network (STAN), to improve the performance of segmenting tumors with different size. The new architecture integrates both rich context information and high-resolution image features. We validate the proposed approach using seven quantitative metrics on two public breast ultrasound datasets. The proposed approach outperformed the state-of-the-art approaches in segmenting small breast tumors. Index
Tasks Semantic Segmentation
Published 2020-02-03
URL https://arxiv.org/abs/2002.01034v1
PDF https://arxiv.org/pdf/2002.01034v1.pdf
PWC https://paperswithcode.com/paper/stan-small-tumor-aware-network-for-breast
comments powered by Disqus