April 1, 2020

3157 words 15 mins read

Paper Group ANR 497

Target Detection, Tracking and Avoidance System for Low-cost UAVs using AI-Based Approaches. Hybrid calibration procedure for fringe projection profilometry based on stereo-vision and polynomial fitting. Introducing Aspects of Creativity in Automatic Poetry Generation. Does label smoothing mitigate label noise?. Bypassing the Monster: A Faster and …

Target Detection, Tracking and Avoidance System for Low-cost UAVs using AI-Based Approaches


Title	Target Detection, Tracking and Avoidance System for Low-cost UAVs using AI-Based Approaches
Authors	Vinorth Varatharasan, Alice Shuang Shuang Rao, Eric Toutounji, Ju-Hyeon Hong, Hyo-Sang Shin
Abstract	An onboard target detection, tracking and avoidance system has been developed in this paper, for low-cost UAV flight controllers using AI-Based approaches. The aim of the proposed system is that an ally UAV can either avoid or track an unexpected enemy UAV with a net to protect itself. In this point of view, a simple and robust target detection, tracking and avoidance system is designed. Two open-source tools were used for the aim: a state-of-the-art object detection technique called SSD and an API for MAVLink compatible systems called MAVSDK. The MAVSDK performs velocity control when a UAV is detected so that the manoeuvre is done simply and efficiently. The proposed system was verified with Software in the loop (SITL) and Hardware in the loop (HITL) simulators. The simplicity of this algorithm makes it innovative, and therefore it should be used in future applications needing robust performances with low-cost hardware such as delivery drone applications.
Tasks	Object Detection
Published	2020-02-27
URL	https://arxiv.org/abs/2002.12461v1
PDF	https://arxiv.org/pdf/2002.12461v1.pdf
PWC	https://paperswithcode.com/paper/target-detection-tracking-and-avoidance
Repo
Framework

Hybrid calibration procedure for fringe projection profilometry based on stereo-vision and polynomial fitting


Title	Hybrid calibration procedure for fringe projection profilometry based on stereo-vision and polynomial fitting
Authors	Raul Vargas, Andres G. Marrugo, Song Zhang, Lenny A. Romero
Abstract	The key to accurate 3D shape measurement in Fringe Projection Profilometry (FPP) is the proper calibration of the measurement system. Current calibration techniques rely on phase-coordinate mapping (PCM) or back-projection stereo-vision (SV) methods. PCM methods are cumbersome to implement as they require precise positioning of the calibration target relative to the FPP system but produce highly accurate measurements within the calibration volume. SV methods generally do not achieve the same accuracy level. However, the calibration is more flexible in that the calibration target can be arbitrarily positioned. In this work, we propose a hybrid calibration method that leverages the SV calibration approach using a PCM method to achieve higher accuracy. The method has the flexibility of SV methods, is robust to lens distortions, and has a simple relation between the recovered phase and the metric coordinates. Experimental results show that the proposed Hybrid method outperforms the SV method in terms of accuracy and reconstruction time due to its low computational complexity.
Tasks	Calibration
Published	2020-03-09
URL	https://arxiv.org/abs/2003.04168v1
PDF	https://arxiv.org/pdf/2003.04168v1.pdf
PWC	https://paperswithcode.com/paper/hybrid-calibration-procedure-for-fringe
Repo
Framework

Introducing Aspects of Creativity in Automatic Poetry Generation


Title	Introducing Aspects of Creativity in Automatic Poetry Generation
Authors	Brendan Bena, Jugal Kalita
Abstract	Poetry Generation involves teaching systems to automatically generate text that resembles poetic work. A deep learning system can learn to generate poetry on its own by training on a corpus of poems and modeling the particular style of language. In this paper, we propose taking an approach that fine-tunes GPT-2, a pre-trained language model, to our downstream task of poetry generation. We extend prior work on poetry generation by introducing creative elements. Specifically, we generate poems that express emotion and elicit the same in readers, and poems that use the language of dreams—called dream poetry. We are able to produce poems that correctly elicit the emotions of sadness and joy 87.5 and 85 percent, respectively, of the time. We produce dreamlike poetry by training on a corpus of texts that describe dreams. Poems from this model are shown to capture elements of dream poetry with scores of no less than 3.2 on the Likert scale. We perform crowdsourced human-evaluation for all our poems. We also make use of the Coh-Metrix tool, outlining metrics we use to gauge the quality of text generated.
Tasks	Language Modelling
Published	2020-02-06
URL	https://arxiv.org/abs/2002.02511v1
PDF	https://arxiv.org/pdf/2002.02511v1.pdf
PWC	https://paperswithcode.com/paper/introducing-aspects-of-creativity-in
Repo
Framework

Does label smoothing mitigate label noise?


Title	Does label smoothing mitigate label noise?
Authors	Michal Lukasik, Srinadh Bhojanapalli, Aditya Krishna Menon, Sanjiv Kumar
Abstract	Label smoothing is commonly used in training deep learning models, wherein one-hot training labels are mixed with uniform label vectors. Empirically, smoothing has been shown to improve both predictive performance and model calibration. In this paper, we study whether label smoothing is also effective as a means of coping with label noise. While label smoothing apparently amplifies this problem — being equivalent to injecting symmetric noise to the labels — we show how it relates to a general family of loss-correction techniques from the label noise literature. Building on this connection, we show that label smoothing is competitive with loss-correction under label noise. Further, we show that when distilling models from noisy data, label smoothing of the teacher is beneficial; this is in contrast to recent findings for noise-free problems, and sheds further light on settings where label smoothing is beneficial.
Tasks	Calibration
Published	2020-03-05
URL	https://arxiv.org/abs/2003.02819v1
PDF	https://arxiv.org/pdf/2003.02819v1.pdf
PWC	https://paperswithcode.com/paper/does-label-smoothing-mitigate-label-noise
Repo
Framework

Bypassing the Monster: A Faster and Simpler Optimal Algorithm for Contextual Bandits under Realizability


Title	Bypassing the Monster: A Faster and Simpler Optimal Algorithm for Contextual Bandits under Realizability
Authors	David Simchi-Levi, Yunzong Xu
Abstract	We consider the general (stochastic) contextual bandit problem under the realizability assumption, i.e., the expected reward, as a function of contexts and actions, belongs to a general function class $\mathcal{F}$. We design a fast and simple algorithm that achieves the statistically optimal regret with only ${O}(\log T)$ calls to an offline least-squares regression oracle across all $T$ rounds (the number of oracle calls can be further reduced to $O(\log\log T)$ if $T$ is known in advance). Our algorithm provides the first universal and optimal reduction from contextual bandits to offline regression, solving an important open problem for the realizable setting of contextual bandits. Our algorithm is also the first provably optimal contextual bandit algorithm with a logarithmic number of oracle calls.
Tasks	Multi-Armed Bandits
Published	2020-03-28
URL	https://arxiv.org/abs/2003.12699v1
PDF	https://arxiv.org/pdf/2003.12699v1.pdf
PWC	https://paperswithcode.com/paper/bypassing-the-monster-a-faster-and-simpler
Repo
Framework

Learning to Smooth and Fold Real Fabric Using Dense Object Descriptors Trained on Synthetic Color Images


Title	Learning to Smooth and Fold Real Fabric Using Dense Object Descriptors Trained on Synthetic Color Images
Authors	Aditya Ganapathi, Priya Sundaresan, Brijen Thananjeyan, Ashwin Balakrishna, Daniel Seita, Jennifer Grannen, Minho Hwang, Ryan Hoque, Joseph E. Gonzalez, Nawid Jamali, Katsu Yamane, Soshi Iba, Ken Goldberg
Abstract	Robotic fabric manipulation is challenging due to the infinite dimensional configuration space and complex dynamics. In this paper, we learn visual representations of deformable fabric by training dense object descriptors that capture correspondences across images of fabric in various configurations. The learned descriptors capture higher level geometric structure, facilitating design of explainable policies. We demonstrate that the learned representation facilitates multistep fabric smoothing and folding tasks on two real physical systems, the da Vinci surgical robot and the ABB YuMi given high level demonstrations from a supervisor. The system achieves a 78.8% average task success rate across six fabric manipulation tasks. See https://tinyurl.com/fabric-descriptors for supplementary material and videos.
Tasks
Published	2020-03-28
URL	https://arxiv.org/abs/2003.12698v1
PDF	https://arxiv.org/pdf/2003.12698v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-smooth-and-fold-real-fabric-using
Repo
Framework

Character-Aware Attention-Based End-to-End Speech Recognition


Title	Character-Aware Attention-Based End-to-End Speech Recognition
Authors	Zhong Meng, Yashesh Gaur, Jinyu Li, Yifan Gong
Abstract	Predicting words and subword units (WSUs) as the output has shown to be effective for the attention-based encoder-decoder (AED) model in end-to-end speech recognition. However, as one input to the decoder recurrent neural network (RNN), each WSU embedding is learned independently through context and acoustic information in a purely data-driven fashion. Little effort has been made to explicitly model the morphological relationships among WSUs. In this work, we propose a novel character-aware (CA) AED model in which each WSU embedding is computed by summarizing the embeddings of its constituent characters using a CA-RNN. This WSU-independent CA-RNN is jointly trained with the encoder, the decoder and the attention network of a conventional AED to predict WSUs. With CA-AED, the embeddings of morphologically similar WSUs are naturally and directly correlated through the CA-RNN in addition to the semantic and acoustic relations modeled by a traditional AED. Moreover, CA-AED significantly reduces the model parameters in a traditional AED by replacing the large pool of WSU embeddings with a much smaller set of character embeddings. On a 3400 hours Microsoft Cortana dataset, CA-AED achieves up to 11.9% relative WER improvement over a strong AED baseline with 27.1% fewer model parameters.
Tasks	End-To-End Speech Recognition, Speech Recognition
Published	2020-01-06
URL	https://arxiv.org/abs/2001.01795v1
PDF	https://arxiv.org/pdf/2001.01795v1.pdf
PWC	https://paperswithcode.com/paper/character-aware-attention-based-end-to-end
Repo
Framework

A Newton Frank-Wolfe Method for Constrained Self-Concordant Minimization


Title	A Newton Frank-Wolfe Method for Constrained Self-Concordant Minimization
Authors	Deyi Liu, Volkan Cevher, Quoc Tran-Dinh
Abstract	We demonstrate how to scalably solve a class of constrained self-concordant minimization problems using linear minimization oracles (LMO) over the constraint set. We prove that the number of LMO calls of our method is nearly the same as that of the Frank-Wolfe method in the L-smooth case. Specifically, our Newton Frank-Wolfe method uses $\mathcal{O}(\epsilon^{-\nu})$ LMO’s, where $\epsilon$ is the desired accuracy and $\nu:= 1 + o(1)$. In addition, we demonstrate how our algorithm can exploit the improved variants of the LMO-based schemes, including away-steps, to attain linear convergence rates. We also provide numerical evidence with portfolio design with the competitive ratio, D-optimal experimental design, and logistic regression with the elastic net where Newton Frank-Wolfe outperforms the state-of-the-art.
Tasks
Published	2020-02-17
URL	https://arxiv.org/abs/2002.07003v1
PDF	https://arxiv.org/pdf/2002.07003v1.pdf
PWC	https://paperswithcode.com/paper/a-newton-frank-wolfe-method-for-constrained
Repo
Framework

Model Assertions for Monitoring and Improving ML Models


Title	Model Assertions for Monitoring and Improving ML Models
Authors	Daniel Kang, Deepti Raghavan, Peter Bailis, Matei Zaharia
Abstract	ML models are increasingly deployed in settings with real world interactions such as vehicles, but unfortunately, these models can fail in systematic ways. To prevent errors, ML engineering teams monitor and continuously improve these models. We propose a new abstraction, model assertions, that adapts the classical use of program assertions as a way to monitor and improve ML models. Model assertions are arbitrary functions over a model’s input and output that indicate when errors may be occurring, e.g., a function that triggers if an object rapidly changes its class in a video. We propose methods of using model assertions at all stages of ML system deployment, including runtime monitoring, validating labels, and continuously improving ML models. For runtime monitoring, we show that model assertions can find high confidence errors, where a model returns the wrong output with high confidence, which uncertainty-based monitoring techniques would not detect. For training, we propose two methods of using model assertions. First, we propose a bandit-based active learning algorithm that can sample from data flagged by assertions and show that it can reduce labeling costs by up to 40% over traditional uncertainty-based methods. Second, we propose an API for generating “consistency assertions” (e.g., the class change example) and weak labels for inputs where the consistency assertions fail, and show that these weak labels can improve relative model quality by up to 46%. We evaluate model assertions on four real-world tasks with video, LIDAR, and ECG data.
Tasks	Active Learning
Published	2020-03-03
URL	https://arxiv.org/abs/2003.01668v3
PDF	https://arxiv.org/pdf/2003.01668v3.pdf
PWC	https://paperswithcode.com/paper/model-assertions-for-monitoring-and-improving
Repo
Framework

Time Series Forecasting Using LSTM Networks: A Symbolic Approach


Title	Time Series Forecasting Using LSTM Networks: A Symbolic Approach
Authors	Steven Elsworth, Stefan Güttel
Abstract	Machine learning methods trained on raw numerical time series data exhibit fundamental limitations such as a high sensitivity to the hyper parameters and even to the initialization of random weights. A combination of a recurrent neural network with a dimension-reducing symbolic representation is proposed and applied for the purpose of time series forecasting. It is shown that the symbolic representation can help to alleviate some of the aforementioned problems and, in addition, might allow for faster training without sacrificing the forecast performance.
Tasks	Time Series, Time Series Forecasting
Published	2020-03-12
URL	https://arxiv.org/abs/2003.05672v1
PDF	https://arxiv.org/pdf/2003.05672v1.pdf
PWC	https://paperswithcode.com/paper/time-series-forecasting-using-lstm-networks-a
Repo
Framework

Learning to Augment Expressions for Few-shot Fine-grained Facial Expression Recognition


Title	Learning to Augment Expressions for Few-shot Fine-grained Facial Expression Recognition
Authors	Wenxuan Wang, Yanwei Fu, Qiang Sun, Tao Chen, Chenjie Cao, Ziqi Zheng, Guoqiang Xu, Han Qiu, Yu-Gang Jiang, Xiangyang Xue
Abstract	Affective computing and cognitive theory are widely used in modern human-computer interaction scenarios. Human faces, as the most prominent and easily accessible features, have attracted great attention from researchers. Since humans have rich emotions and developed musculature, there exist a lot of fine-grained expressions in real-world applications. However, it is extremely time-consuming to collect and annotate a large number of facial images, of which may even require psychologists to correctly categorize them. To the best of our knowledge, the existing expression datasets are only limited to several basic facial expressions, which are not sufficient to support our ambitions in developing successful human-computer interaction systems. To this end, a novel Fine-grained Facial Expression Database - F2ED is contributed in this paper, and it includes more than 200k images with 54 facial expressions from 119 persons. Considering the phenomenon of uneven data distribution and lack of samples is common in real-world scenarios, we further evaluate several tasks of few-shot expression learning by virtue of our F2ED, which are to recognize the facial expressions given only few training instances. These tasks mimic human performance to learn robust and general representation from few examples. To address such few-shot tasks, we propose a unified task-driven framework - Compositional Generative Adversarial Network (Comp-GAN) learning to synthesize facial images and thus augmenting the instances of few-shot expression classes. Extensive experiments are conducted on F2ED and existing facial expression datasets, i.e., JAFFE and FER2013, to validate the efficacy of our F2ED in pre-training facial expression recognition network and the effectiveness of our proposed approach Comp-GAN to improve the performance of few-shot recognition tasks.
Tasks	Facial Expression Recognition
Published	2020-01-17
URL	https://arxiv.org/abs/2001.06144v1
PDF	https://arxiv.org/pdf/2001.06144v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-augment-expressions-for-few-shot
Repo
Framework

Designing Color Filters that Make Cameras MoreColorimetric


Title	Designing Color Filters that Make Cameras MoreColorimetric
Authors	Graham D. Finlayson, Yuteng Zhu
Abstract	When we place a colored filter in front of a camera the effective camera response functions are equal to the given camera spectral sensitivities multiplied by the filter spectral transmittance. In this paper, we solve for the filter which returns the modified sensitivities as close to being a linear transformation from the color matching functions of human visual system as possible. When this linearity condition - sometimes called the Luther condition - is approximately met, the `camera+filter’ system can be used for accurate color measurement. Then, we reformulate our filter design optimisation for making the sensor responses as close to the CIEXYZ tristimulus values as possible given the knowledge of real measured surfaces and illuminants spectra data. This data-driven method in turn is extended to incorporate constraints on the filter (smoothness and bounded transmission). Also, because how the optimisation is initialised is shown to impact on the performance of the solved-for filters, a multi-initialisation optimisation is developed. Experiments demonstrate that, by taking pictures through our optimised color filters we can make cameras significantly more colorimetric. \|
Tasks
Published	2020-03-27
URL	https://arxiv.org/abs/2003.12645v1
PDF	https://arxiv.org/pdf/2003.12645v1.pdf
PWC	https://paperswithcode.com/paper/designing-color-filters-that-make-cameras
Repo
Framework

A Collective Learning Framework to Boost GNN Expressiveness


Title	A Collective Learning Framework to Boost GNN Expressiveness
Authors	Mengyue Hang, Jennifer Neville, Bruno Ribeiro
Abstract	Graph Neural Networks (GNNs) have recently been used for node and graph classification tasks with great success, but GNNs model dependencies among the attributes of nearby neighboring nodes rather than dependencies among observed node labels. In this work, we consider the task of inductive node classification using GNNs in supervised and semi-supervised settings, with the goal of incorporating label dependencies. Because current GNNs are not universal (i.e., most-expressive) graph representations, we propose a general collective learning approach to increase the representation power of any existing GNN. Our framework combines ideas from collective classification with self-supervised learning, and uses a Monte Carlo approach to sampling embeddings for inductive learning across graphs. We evaluate performance on five real-world network datasets and demonstrate consistent, significant improvement in node classification accuracy, for a variety of state-of-the-art GNNs.
Tasks	Graph Classification, Node Classification
Published	2020-03-26
URL	https://arxiv.org/abs/2003.12169v1
PDF	https://arxiv.org/pdf/2003.12169v1.pdf
PWC	https://paperswithcode.com/paper/a-collective-learning-framework-to-boost-gnn
Repo
Framework

Dividing Deep Learning Model for Continuous Anomaly Detection of Inconsistent ICT Systems


Title	Dividing Deep Learning Model for Continuous Anomaly Detection of Inconsistent ICT Systems
Authors	Kengo Tajiri, Yasuhiro Ikeda, Yuusuke Nakano, Keishiro Watanabe
Abstract	Health monitoring is important for maintaining reliable information and communications technology (ICT) systems. Anomaly detection methods based on machine learning, which train a model for describing “normality” are promising for monitoring the state of ICT systems. However, these methods cannot be used when the type of monitored log data changes from that of training data due to the replacement of certain equipment. Therefore, such methods may dismiss an anomaly that appears when log data changes. To solve this problem, we propose an ICT-systems-monitoring method with deep learning models divided based on the correlation of log data. We also propose an algorithm for extracting the correlations of log data from a deep learning model and separating log data based on the correlation. When some of the log data changes, our method can continue health monitoring with the divided models which are not affected by changes in the log data. We present the results from experiments involving benchmark data and real log data, which indicate that our method using divided models does not decrease anomaly detection accuracy and a model for anomaly detection can be divided to continue monitoring a network state even if some the log data change.
Tasks	Anomaly Detection
Published	2020-03-24
URL	https://arxiv.org/abs/2003.10783v1
PDF	https://arxiv.org/pdf/2003.10783v1.pdf
PWC	https://paperswithcode.com/paper/dividing-deep-learning-model-for-continuous
Repo
Framework

Ego-based Entropy Measures for Structural Representations


Title	Ego-based Entropy Measures for Structural Representations
Authors	George Dasoulas, Giannis Nikolentzos, Kevin Scaman, Aladin Virmaux, Michalis Vazirgiannis
Abstract	In complex networks, nodes that share similar structural characteristics often exhibit similar roles (e.g type of users in a social network or the hierarchical position of employees in a company). In order to leverage this relationship, a growing literature proposed latent representations that identify structurally equivalent nodes. However, most of the existing methods require high time and space complexity. In this paper, we propose VNEstruct, a simple approach for generating low-dimensional structural node embeddings, that is both time efficient and robust to perturbations of the graph structure. The proposed approach focuses on the local neighborhood of each node and employs the Von Neumann entropy, an information-theoretic tool, to extract features that capture the neighborhood’s topology. Moreover, on graph classification tasks, we suggest the utilization of the generated structural embeddings for the transformation of an attributed graph structure into a set of augmented node attributes. Empirically, we observe that the proposed approach exhibits robustness on structural role identification tasks and state-of-the-art performance on graph classification tasks, while maintaining very high computational speed.
Tasks	Graph Classification
Published	2020-03-01
URL	https://arxiv.org/abs/2003.00553v1
PDF	https://arxiv.org/pdf/2003.00553v1.pdf
PWC	https://paperswithcode.com/paper/ego-based-entropy-measures-for-structural
Repo
Framework