January 27, 2020

2712 words 13 mins read

Paper Group ANR 1265

Action2Vec: A Crossmodal Embedding Approach to Action Learning. 3D Robot Pose Estimation from 2D Images. Pivot-based Transfer Learning for Neural Machine Translation between Non-English Languages. A kernel log-rank test of independence for right-censored data. Survival and Neural Models for Private Equity Exit Prediction. A Framework to Explore Wor …

Action2Vec: A Crossmodal Embedding Approach to Action Learning


Title	Action2Vec: A Crossmodal Embedding Approach to Action Learning
Authors	Meera Hahn, Andrew Silva, James M. Rehg
Abstract	We describe a novel cross-modal embedding space for actions, named Action2Vec, which combines linguistic cues from class labels with spatio-temporal features derived from video clips. Our approach uses a hierarchical recurrent network to capture the temporal structure of video features. We train our embedding using a joint loss that combines classification accuracy with similarity to Word2Vec semantics. We evaluate Action2Vec by performing zero shot action recognition and obtain state of the art results on three standard datasets. In addition, we present two novel analogy tests which quantify the extent to which our joint embedding captures distributional semantics. This is the first joint embedding space to combine verbs and action videos, and the first to be thoroughly evaluated with respect to its distributional semantics.
Tasks	Temporal Action Localization
Published	2019-01-02
URL	http://arxiv.org/abs/1901.00484v1
PDF	http://arxiv.org/pdf/1901.00484v1.pdf
PWC	https://paperswithcode.com/paper/action2vec-a-crossmodal-embedding-approach-to
Repo
Framework

3D Robot Pose Estimation from 2D Images


Title	3D Robot Pose Estimation from 2D Images
Authors	Christoph Heindl, Sebastian Zambal, Thomas Ponitz, Andreas Pichler, Josef Scharinger
Abstract	This paper considers the task of locating articulated poses of multiple robots in images. Our approach simultaneously infers the number of robots in a scene, identifies joint locations and estimates sparse depth maps around joint locations. The proposed method applies staged convolutional feature detectors to 2D image inputs and computes robot instance masks using a recurrent network architecture. In addition, regression maps of most likely joint locations in pixel coordinates together with depth information are computed. Compositing 3D robot joint kinematics is accomplished by applying masks to joint readout maps. Our end-to-end formulation is in contrast to previous work in which the composition of robot joints into kinematics is performed in a separate post-processing step. Despite the fact that our models are trained on artificial data, we demonstrate generalizability to real world images.
Tasks	Pose Estimation
Published	2019-02-13
URL	http://arxiv.org/abs/1902.04987v1
PDF	http://arxiv.org/pdf/1902.04987v1.pdf
PWC	https://paperswithcode.com/paper/3d-robot-pose-estimation-from-2d-images
Repo
Framework

Pivot-based Transfer Learning for Neural Machine Translation between Non-English Languages


Title	Pivot-based Transfer Learning for Neural Machine Translation between Non-English Languages
Authors	Yunsu Kim, Petre Petrov, Pavel Petrushkov, Shahram Khadivi, Hermann Ney
Abstract	We present effective pre-training strategies for neural machine translation (NMT) using parallel corpora involving a pivot language, i.e., source-pivot and pivot-target, leading to a significant improvement in source-target translation. We propose three methods to increase the relation among source, pivot, and target languages in the pre-training: 1) step-wise training of a single model for different language pairs, 2) additional adapter component to smoothly connect pre-trained encoder and decoder, and 3) cross-lingual encoder training via autoencoding of the pivot language. Our methods greatly outperform multilingual models up to +2.6% BLEU in WMT 2019 French-German and German-Czech tasks. We show that our improvements are valid also in zero-shot/zero-resource scenarios.
Tasks	Machine Translation, Transfer Learning
Published	2019-09-20
URL	https://arxiv.org/abs/1909.09524v1
PDF	https://arxiv.org/pdf/1909.09524v1.pdf
PWC	https://paperswithcode.com/paper/pivot-based-transfer-learning-for-neural
Repo
Framework

A kernel log-rank test of independence for right-censored data


Title	A kernel log-rank test of independence for right-censored data
Authors	Tamara Fernandez, Arthur Gretton, David Rindt, Dino Sejdinovic
Abstract	With the incorporation of new data gathering methods in clinical research, it becomes fundamental for survival analysis techniques to deal with high-dimensional or/and non-standard covariates. In this paper we introduce a general non-parametric independence test between right-censored survival times and covariates taking values on a general (not necessarily Euclidean) space $\mathcal{X}$. We show that our test statistic has a dual interpretation, first in terms of the supremum of a potentially infinite collection of weight-indexed log-rank tests, with weight functions belonging to a reproducing kernel Hilbert space (RKHS) of functions; and second, as the norm of the difference of embeddings of certain finite measures into the RKHS, similar to the Hilbert-Schmidt Independence Criterion (HSIC) test-statistic. We study the asymptotic properties of the test, finding sufficient conditions to ensure that our test is omnibus. The test statistic can be computed straightforwardly, and the rejection threshold is obtained via an asymptotically consistent Wild-Bootstrap procedure. We perform extensive simulations demonstrating that our testing procedure generally performs better than competing approaches in detecting complex nonlinear dependence.
Tasks	Survival Analysis
Published	2019-12-08
URL	https://arxiv.org/abs/1912.03784v1
PDF	https://arxiv.org/pdf/1912.03784v1.pdf
PWC	https://paperswithcode.com/paper/a-kernel-log-rank-test-of-independence-for
Repo
Framework

Survival and Neural Models for Private Equity Exit Prediction


Title	Survival and Neural Models for Private Equity Exit Prediction
Authors	Giuseppe C. Calafiore, Marisa H. Morales, Vittorio Tiozzo, Giulia Fracastoro, Serge Marquie
Abstract	Within the Private Equity (PE) market, the event of a private company undertaking an Initial Public Offering (IPO) is usually a very high-return one for the investors in the company. For this reason, an effective predictive model for the IPO event is considered as a valuable tool in the PE market, an endeavor in which publicly available quantitative information is generally scarce. In this paper, we describe a data-analytic procedure for predicting the probability with which a company will go public in a given forward period of time. The proposed method is based on the interplay of a neural network (NN) model for estimating the overall event probability, and Survival Analysis (SA) for further modeling the probability of the IPO event in any given interval of time. The proposed neuro-survival model is tuned and tested across nine industrial sectors using real data from the Thomson Reuters Eikon PE database.
Tasks	Survival Analysis
Published	2019-11-19
URL	https://arxiv.org/abs/1911.08201v4
PDF	https://arxiv.org/pdf/1911.08201v4.pdf
PWC	https://paperswithcode.com/paper/survival-and-neural-models-for-private-equity
Repo
Framework

A Framework to Explore Workload-Specific Performance and Lifetime Trade-offs in Neuromorphic Computing


Title	A Framework to Explore Workload-Specific Performance and Lifetime Trade-offs in Neuromorphic Computing
Authors	Adarsha Balaji, Shihao Song, Anup Das, Nikil Dutt, Jeff Krichmar, Nagarajan Kandasamy, Francky Catthoor
Abstract	Neuromorphic hardware with non-volatile memory (NVM) can implement machine learning workload in an energy-efficient manner. Unfortunately, certain NVMs such as phase change memory (PCM) require high voltages for correct operation. These voltages are supplied from an on-chip charge pump. If the charge pump is activated too frequently, its internal CMOS devices do not recover from stress, accelerating their aging and leading to negative bias temperature instability (NBTI) generated defects. Forcefully discharging the stressed charge pump can lower the aging rate of its CMOS devices, but makes the neuromorphic hardware unavailable to perform computations while its charge pump is being discharged. This negatively impacts performance such as latency and accuracy of the machine learning workload being executed. In this paper, we propose a novel framework to exploit workload-specific performance and lifetime trade-offs in neuromorphic computing. Our framework first extracts the precise times at which a charge pump in the hardware is activated to support neural computations within a workload. This timing information is then used with a characterized NBTI reliability model to estimate the charge pump’s aging during the workload execution. We use our framework to evaluate workload-specific performance and reliability impacts of using 1) different SNN mapping strategies and 2) different charge pump discharge strategies. We show that our framework can be used by system designers to explore performance and reliability trade-offs early in the design of neuromorphic hardware such that appropriate reliability-oriented design margins can be set.
Tasks
Published	2019-11-01
URL	https://arxiv.org/abs/1911.00548v1
PDF	https://arxiv.org/pdf/1911.00548v1.pdf
PWC	https://paperswithcode.com/paper/a-framework-to-explore-workload-specific
Repo
Framework

Big Data Analytics for Large Scale Wireless Networks: Challenges and Opportunities


Title	Big Data Analytics for Large Scale Wireless Networks: Challenges and Opportunities
Authors	Hong-Ning Dai, Raymond Chi-Wing Wong, Hao Wang, Zibin Zheng, Athanasios V. Vasilakos
Abstract	The wide proliferation of various wireless communication systems and wireless devices has led to the arrival of big data era in large scale wireless networks. Big data of large scale wireless networks has the key features of wide variety, high volume, real-time velocity and huge value leading to the unique research challenges that are different from existing computing systems. In this paper, we present a survey of the state-of-art big data analytics (BDA) approaches for large scale wireless networks. In particular, we categorize the life cycle of BDA into four consecutive stages: Data Acquisition, Data Preprocessing, Data Storage and Data Analytics. We then present a detailed survey of the technical solutions to the challenges in BDA for large scale wireless networks according to each stage in the life cycle of BDA. Moreover, we discuss the open research issues and outline the future directions in this promising area.
Tasks
Published	2019-09-02
URL	https://arxiv.org/abs/1909.08069v1
PDF	https://arxiv.org/pdf/1909.08069v1.pdf
PWC	https://paperswithcode.com/paper/big-data-analytics-for-large-scale-wireless
Repo
Framework

Fast Pedestrian Detection based on T-CENTRIST


Title	Fast Pedestrian Detection based on T-CENTRIST
Authors	Hongyin Ni, Bin Lia
Abstract	Pedestrian detection is a research hotspot and a difficult issue in the computer vision such as the Intelligent Surveillance System (ISS), the Intelligent Transport System (ITS), robotics, and automotive safety. However, the human body’s position, angle, and dress in a video scene are complicated and changeable, which have a great influence on the detection accuracy. In this paper, through the analysis on the pros and cons of Census Transform Histogram (CENTRIST), a novel feature is presented for human detection-Ternary CENTRIST (T-CENTRIST). The T-CENTRIST feature takes the relationship between each pixel and its neighborhood pixels into account. Meanwhile, it also considers the relevancy among these neighborhood pixels. Therefore, the proposed feature description method can reflect the silhouette of pedestrian more adequately and accurately than that of CENTRIST. Second, we propose a fast pedestrian detection framework based on T-CENTRIST, which introduces the idea of extended blocks and the integral image. Finally, experimental results verify the effectiveness of the proposed pedestrian detection method.
Tasks	Human Detection, Pedestrian Detection
Published	2019-02-17
URL	http://arxiv.org/abs/1902.06218v1
PDF	http://arxiv.org/pdf/1902.06218v1.pdf
PWC	https://paperswithcode.com/paper/fast-pedestrian-detection-based-on-t-centrist
Repo
Framework

Near Optimal Stratified Sampling


Title	Near Optimal Stratified Sampling
Authors	Tiancheng Yu, Xiyu Zhai, Suvrit Sra
Abstract	The performance of a machine learning system is usually evaluated by using i.i.d.\ observations with true labels. However, acquiring ground truth labels is expensive, while obtaining unlabeled samples may be cheaper. Stratified sampling can be beneficial in such settings and can reduce the number of true labels required without compromising the evaluation accuracy. Stratified sampling exploits statistical properties (e.g., variance) across strata of the unlabeled population, though usually under the unrealistic assumption that these properties are known. We propose two new algorithms that simultaneously estimate these properties and optimize the evaluation accuracy. We construct a lower bound to show the proposed algorithms (to log-factors) are rate optimal. Experiments on synthetic and real data show the reduction in label complexity that is enabled by our algorithms.
Tasks
Published	2019-06-26
URL	https://arxiv.org/abs/1906.11289v2
PDF	https://arxiv.org/pdf/1906.11289v2.pdf
PWC	https://paperswithcode.com/paper/near-optimal-stratified-sampling
Repo
Framework

Reinforcement Learning with Probabilistic Guarantees for Autonomous Driving


Title	Reinforcement Learning with Probabilistic Guarantees for Autonomous Driving
Authors	Maxime Bouton, Jesper Karlsson, Alireza Nakhaei, Kikuo Fujimura, Mykel J. Kochenderfer, Jana Tumova
Abstract	Designing reliable decision strategies for autonomous urban driving is challenging. Reinforcement learning (RL) has been used to automatically derive suitable behavior in uncertain environments, but it does not provide any guarantee on the performance of the resulting policy. We propose a generic approach to enforce probabilistic guarantees on an RL agent. An exploration strategy is derived prior to training that constrains the agent to choose among actions that satisfy a desired probabilistic specification expressed with linear temporal logic (LTL). Reducing the search space to policies satisfying the LTL formula helps training and simplifies reward design. This paper outlines a case study of an intersection scenario involving multiple traffic participants. The resulting policy outperforms a rule-based heuristic approach in terms of efficiency while exhibiting strong guarantees on safety.
Tasks	Autonomous Driving
Published	2019-04-15
URL	https://arxiv.org/abs/1904.07189v2
PDF	https://arxiv.org/pdf/1904.07189v2.pdf
PWC	https://paperswithcode.com/paper/reinforcement-learning-with-probabilistic
Repo
Framework

Semi-Supervised Self-Taught Deep Learning for Finger Bones Segmentation


Title	Semi-Supervised Self-Taught Deep Learning for Finger Bones Segmentation
Authors	Ziyuan Zhao, Xiaoman Zhang, Cen Chen, Wei Li, Songyou Peng, Jie Wang, Xulei Yang, Le Zhang, Zeng Zeng
Abstract	Segmentation stands at the forefront of many high-level vision tasks. In this study, we focus on segmenting finger bones within a newly introduced semi-supervised self-taught deep learning framework which consists of a student network and a stand-alone teacher module. The whole system is boosted in a life-long learning manner wherein each step the teacher module provides a refinement for the student network to learn with newly unlabeled data. Experimental results demonstrate the superiority of the proposed method over conventional supervised deep learning methods.
Tasks
Published	2019-03-12
URL	http://arxiv.org/abs/1903.04778v1
PDF	http://arxiv.org/pdf/1903.04778v1.pdf
PWC	https://paperswithcode.com/paper/semi-supervised-self-taught-deep-learning-for
Repo
Framework

Transformer to CNN: Label-scarce distillation for efficient text classification


Title	Transformer to CNN: Label-scarce distillation for efficient text classification
Authors	Yew Ken Chia, Sam Witteveen, Martin Andrews
Abstract	Significant advances have been made in Natural Language Processing (NLP) modelling since the beginning of 2018. The new approaches allow for accurate results, even when there is little labelled data, because these NLP models can benefit from training on both task-agnostic and task-specific unlabelled data. However, these advantages come with significant size and computational costs. This workshop paper outlines how our proposed convolutional student architecture, having been trained by a distillation process from a large-scale model, can achieve 300x inference speedup and 39x reduction in parameter count. In some cases, the student model performance surpasses its teacher on the studied tasks.
Tasks	Text Classification
Published	2019-09-08
URL	https://arxiv.org/abs/1909.03508v1
PDF	https://arxiv.org/pdf/1909.03508v1.pdf
PWC	https://paperswithcode.com/paper/transformer-to-cnn-label-scarce-distillation
Repo
Framework

To Trust, or Not to Trust? A Study of Human Bias in Automated Video Interview Assessments


Title	To Trust, or Not to Trust? A Study of Human Bias in Automated Video Interview Assessments
Authors	Chee Wee Leong, Katrina Roohr, Vikram Ramanarayanan, Michelle P. Martin-Raugh, Harrison Kell, Rutuja Ubale, Yao Qian, Zydrune Mladineo, Laura McCulla
Abstract	Supervised systems require human labels for training. But, are humans themselves always impartial during the annotation process? We examine this question in the context of automated assessment of human behavioral tasks. Specifically, we investigate whether human ratings themselves can be trusted at their face value when scoring video-based structured interviews, and whether such ratings can impact machine learning models that use them as training data. We present preliminary empirical evidence that indicates there might be biases in such annotations, most of which are visual in nature.
Tasks
Published	2019-11-27
URL	https://arxiv.org/abs/1911.13248v1
PDF	https://arxiv.org/pdf/1911.13248v1.pdf
PWC	https://paperswithcode.com/paper/to-trust-or-not-to-trust-a-study-of-human
Repo
Framework

Improved Adversarial Learning for Fair Classification


Title	Improved Adversarial Learning for Fair Classification
Authors	L. Elisa Celis, Vijay Keswani
Abstract	Motivated by concerns that machine learning algorithms may introduce significant bias in classification models, developing fair classifiers has become an important problem in machine learning research. One important paradigm towards this has been providing algorithms for adversarially learning fair classifiers (Zhang et al., 2018; Madras et al., 2018). We formulate the adversarial learning problem as a multi-objective optimization problem and find the fair model using gradient descent-ascent algorithm with a modified gradient update step, inspired by the approach of Zhang et al., 2018. We provide theoretical insight and guarantees that formalize the heuristic arguments presented previously towards taking such an approach. We test our approach empirically on the Adult dataset and synthetic datasets and compare against state of the art algorithms (Celis et al., 2018; Zhang et al., 2018; Zafar et al., 2017). The results show that our models and algorithms have comparable or better accuracy than other algorithms while performing better in terms of fairness, as measured using statistical rate or false discovery rate.
Tasks
Published	2019-01-29
URL	http://arxiv.org/abs/1901.10443v1
PDF	http://arxiv.org/pdf/1901.10443v1.pdf
PWC	https://paperswithcode.com/paper/improved-adversarial-learning-for-fair
Repo
Framework

Enriching Neural Models with Targeted Features for Dementia Detection


Title	Enriching Neural Models with Targeted Features for Dementia Detection
Authors	Flavio Di Palo, Natalie Parde
Abstract	Alzheimer’s disease (AD) is an irreversible brain disease that can dramatically reduce quality of life, most commonly manifesting in older adults and eventually leading to the need for full-time care. Early detection is fundamental to slowing its progression; however, diagnosis can be expensive, time-consuming, and invasive. In this work we develop a neural model based on a CNN-LSTM architecture that learns to detect AD and related dementias using targeted and implicitly-learned features from conversational transcripts. Our approach establishes the new state of the art on the DementiaBank dataset, achieving an F1 score of 0.929 when classifying participants into AD and control groups.
Tasks
Published	2019-06-13
URL	https://arxiv.org/abs/1906.05483v1
PDF	https://arxiv.org/pdf/1906.05483v1.pdf
PWC	https://paperswithcode.com/paper/enriching-neural-models-with-targeted
Repo
Framework