Paper Group ANR 353
Pedestrian Models for Autonomous Driving Part I: low level models, from sensing to tracking. Whose Side are Ethics Codes On? Power, Responsibility and the Social Good. Algorithms for Fair Team Formation in Online Labour Marketplaces. Stochastic Optimization of Plain Convolutional Neural Networks with Simple methods. SiTGRU: Single-Tunnelled Gated R …
Pedestrian Models for Autonomous Driving Part I: low level models, from sensing to tracking
| Title | Pedestrian Models for Autonomous Driving Part I: low level models, from sensing to tracking |
| Authors | Fanta Camara, Nicola Bellotto, Serhan Cosar, Dimitris Nathanael, Matthias Althoff, Jingyuan Wu, Johannes Ruenz, André Dietrich, Charles W. Fox |
| Abstract | Autonomous vehicles (AVs) must share space with human pedestrians, both in on-road cases such as cars at pedestrian crossings and off-road cases such as delivery vehicles navigating through crowds on high-streets. Unlike static and kinematic obstacles, pedestrians are active agents with complex, interactive motions. Planning AV actions in the presence of pedestrians thus requires modelling of their probable future behaviour as well as detection and tracking which enable such modelling. This narrative review article is Part I of a pair which together survey the current technology stack involved in this process, organising recent research into a hierarchical taxonomy ranging from low level image detection to high-level psychology models, from the perspective of an AV designer. This self-contained Part I covers the lower levels of this stack, from sensing, through detection and recognition, up to tracking of pedestrians. Technologies at these levels are found to be mature and available as foundations for use in higher level systems such as behaviour modelling, prediction and interaction control. |
| Tasks | Autonomous Driving, Autonomous Vehicles |
| Published | 2020-02-26 |
| URL | https://arxiv.org/abs/2002.11669v1 |
| https://arxiv.org/pdf/2002.11669v1.pdf | |
| PWC | https://paperswithcode.com/paper/pedestrian-models-for-autonomous-driving-part |
| Repo | |
| Framework | |
Whose Side are Ethics Codes On? Power, Responsibility and the Social Good
| Title | Whose Side are Ethics Codes On? Power, Responsibility and the Social Good |
| Authors | Anne L. Washington, Rachel S. Kuo |
| Abstract | The moral authority of ethics codes stems from an assumption that they serve a unified society, yet this ignores the political aspects of any shared resource. The sociologist Howard S. Becker challenged researchers to clarify their power and responsibility in the classic essay: Whose Side Are We On. Building on Becker’s hierarchy of credibility, we report on a critical discourse analysis of data ethics codes and emerging conceptualizations of beneficence, or the “social good”, of data technology. The analysis revealed that ethics codes from corporations and professional associations conflated consumers with society and were largely silent on agency. Interviews with community organizers about social change in the digital era supplement the analysis, surfacing the limits of technical solutions to concerns of marginalized communities. Given evidence that highlights the gulf between the documents and lived experiences, we argue that ethics codes that elevate consumers may simultaneously subordinate the needs of vulnerable populations. Understanding contested digital resources is central to the emerging field of public interest technology. We introduce the concept of digital differential vulnerability to explain disproportionate exposures to harm within data technology and suggest recommendations for future ethics codes. |
| Tasks | |
| Published | 2020-02-04 |
| URL | https://arxiv.org/abs/2002.01559v1 |
| https://arxiv.org/pdf/2002.01559v1.pdf | |
| PWC | https://paperswithcode.com/paper/whose-side-are-ethics-codes-on-power |
| Repo | |
| Framework | |
Algorithms for Fair Team Formation in Online Labour Marketplaces
| Title | Algorithms for Fair Team Formation in Online Labour Marketplaces |
| Authors | Giorgio Barnabò, Adriano Fazzone, Stefano Leonardi, Chris Schwiegelshohn |
| Abstract | As freelancing work keeps on growing almost everywhere due to a sharp decrease in communication costs and to the widespread of Internet-based labour marketplaces (e.g., guru.com, feelancer.com, mturk.com, upwork.com), many researchers and practitioners have started exploring the benefits of outsourcing and crowdsourcing. Since employers often use these platforms to find a group of workers to complete a specific task, researchers have focused their efforts on the study of team formation and matching algorithms and on the design of effective incentive schemes. Nevertheless, just recently, several concerns have been raised on possibly unfair biases introduced through the algorithms used to carry out these selection and matching procedures. For this reason, researchers have started studying the fairness of algorithms related to these online marketplaces, looking for intelligent ways to overcome the algorithmic bias that frequently arises. Broadly speaking, the aim is to guarantee that, for example, the process of hiring workers through the use of machine learning and algorithmic data analysis tools does not discriminate, even unintentionally, on grounds of nationality or gender. In this short paper, we define the Fair Team Formation problem in the following way: given an online labour marketplace where each worker possesses one or more skills, and where all workers are divided into two or more not overlapping classes (for examples, men and women), we want to design an algorithm that is able to find a team with all the skills needed to complete a given task, and that has the same number of people from all classes. We provide inapproximability results for the Fair Team Formation problem together with four algorithms for the problem itself. We also tested the effectiveness of our algorithmic solutions by performing experiments using real data from an online labor marketplace. |
| Tasks | |
| Published | 2020-02-14 |
| URL | https://arxiv.org/abs/2002.11621v1 |
| https://arxiv.org/pdf/2002.11621v1.pdf | |
| PWC | https://paperswithcode.com/paper/algorithms-for-fair-team-formation-in-online |
| Repo | |
| Framework | |
Stochastic Optimization of Plain Convolutional Neural Networks with Simple methods
| Title | Stochastic Optimization of Plain Convolutional Neural Networks with Simple methods |
| Authors | Yahia Assiri |
| Abstract | Convolutional neural networks have been achieving the best possible accuracies in many visual pattern classification problems. However, due to the model capacity required to capture such representations, they are often oversensitive to overfitting and therefore require proper regularization to generalize well. In this paper, we present a combination of regularization techniques which work together to get better performance, we built plain CNNs, and then we used data augmentation, dropout and customized early stopping function, we tested and evaluated these techniques by applying models on five famous datasets, MNIST, CIFAR10, CIFAR100, SVHN, STL10, and we achieved three state-of-the-art-of (MNIST, SVHN, STL10) and very high-Accuracy on the other two datasets. |
| Tasks | Data Augmentation, Image Classification, Stochastic Optimization |
| Published | 2020-01-24 |
| URL | https://arxiv.org/abs/2001.08856v1 |
| https://arxiv.org/pdf/2001.08856v1.pdf | |
| PWC | https://paperswithcode.com/paper/stochastic-optimization-of-plain |
| Repo | |
| Framework | |
SiTGRU: Single-Tunnelled Gated Recurrent Unit for Abnormality Detection
| Title | SiTGRU: Single-Tunnelled Gated Recurrent Unit for Abnormality Detection |
| Authors | Habtamu Fanta, Zhiwen Shao, Lizhuang Ma |
| Abstract | Abnormality detection is a challenging task due to the dependence on a specific context and the unconstrained variability of practical scenarios. In recent years, it has benefited from the powerful features learnt by deep neural networks, and handcrafted features specialized for abnormality detectors. However, these approaches with large complexity still have limitations in handling long term sequential data (e.g., videos), and their learnt features do not thoroughly capture useful information. Recurrent Neural Networks (RNNs) have been shown to be capable of robustly dealing with temporal data in long term sequences. In this paper, we propose a novel version of Gated Recurrent Unit (GRU), called Single Tunnelled GRU for abnormality detection. Particularly, the Single Tunnelled GRU discards the heavy weighted reset gate from GRU cells that overlooks the importance of past content by only favouring current input to obtain an optimized single gated cell model. Moreover, we substitute the hyperbolic tangent activation in standard GRUs with sigmoid activation, as the former suffers from performance loss in deeper networks. Empirical results show that our proposed optimized GRU model outperforms standard GRU and Long Short Term Memory (LSTM) networks on most metrics for detection and generalization tasks on CUHK Avenue and UCSD datasets. The model is also computationally efficient with reduced training and testing time over standard RNNs. |
| Tasks | Anomaly Detection |
| Published | 2020-03-30 |
| URL | https://arxiv.org/abs/2003.13528v1 |
| https://arxiv.org/pdf/2003.13528v1.pdf | |
| PWC | https://paperswithcode.com/paper/sitgru-single-tunnelled-gated-recurrent-unit |
| Repo | |
| Framework | |
Towards Bounding-Box Free Panoptic Segmentation
| Title | Towards Bounding-Box Free Panoptic Segmentation |
| Authors | Ujwal Bonde, Pablo F. Alcantarilla, Stefan Leutenegger |
| Abstract | In this work we introduce a new bounding-box free network (BBFNet) for panoptic segmentation. Panoptic segmentation is an ideal problem for a bounding-box free approach as it already requires per-pixel semantic class labels. We use this observation to exploit class boundaries from an off-the-shelf semantic segmentation network and refine them to predict instance labels. Towards this goal BBFNet predicts coarse watershed levels and use it to detect large instance candidates where boundaries are well defined. For smaller instances, whose boundaries are less reliable, BBFNet also predicts instance centers by means of Hough voting followed by mean-shift to reliably detect small objects. A novel triplet loss network helps merging fragmented instances while refining boundary pixels. Our approach is distinct from previous works in panoptic segmentation that rely on a combination of a semantic segmentation network with a computationally costly instance segmentation network based on bounding boxes, such as Mask R-CNN, to guide the prediction of instance labels using a Mixture-of-Expert (MoE) approach. We benchmark our non-MoE method on Cityscapes and Microsoft COCO datasets and show competitive performance with other MoE based approaches while outperfroming exisiting non-proposal based approaches. We achieve this while been computationally more efficient in terms of number of parameters and FLOPs. Video results are provided here https://blog.slamcore.com/reducing-the-cost-of-understanding. |
| Tasks | Instance Segmentation, Panoptic Segmentation, Semantic Segmentation |
| Published | 2020-02-18 |
| URL | https://arxiv.org/abs/2002.07705v2 |
| https://arxiv.org/pdf/2002.07705v2.pdf | |
| PWC | https://paperswithcode.com/paper/towards-bounding-box-free-panoptic |
| Repo | |
| Framework | |
Learning a Single Neuron with Gradient Methods
| Title | Learning a Single Neuron with Gradient Methods |
| Authors | Gilad Yehudai, Ohad Shamir |
| Abstract | We consider the fundamental problem of learning a single neuron $x \mapsto\sigma(w^\top x)$ using standard gradient methods. As opposed to previous works, which considered specific (and not always realistic) input distributions and activation functions $\sigma(\cdot)$, we ask whether a more general result is attainable, under milder assumptions. On the one hand, we show that some assumptions on the distribution and the activation function are necessary. On the other hand, we prove positive guarantees under mild assumptions, which go beyond those studied in the literature so far. We also point out and study the challenges in further strengthening and generalizing our results. |
| Tasks | |
| Published | 2020-01-15 |
| URL | https://arxiv.org/abs/2001.05205v2 |
| https://arxiv.org/pdf/2001.05205v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-a-single-neuron-with-gradient |
| Repo | |
| Framework | |
Security of Distributed Machine Learning: A Game-Theoretic Approach to Design Secure DSVM
| Title | Security of Distributed Machine Learning: A Game-Theoretic Approach to Design Secure DSVM |
| Authors | Rui Zhang, Quanyan Zhu |
| Abstract | Distributed machine learning algorithms play a significant role in processing massive data sets over large networks. However, the increasing reliance on machine learning on information and communication technologies (ICTs) makes it inherently vulnerable to cyber threats. This work aims to develop secure distributed algorithms to protect the learning from data poisoning and network attacks. We establish a game-theoretic framework to capture the conflicting goals of a learner who uses distributed support vector machines (SVMs) and an attacker who is capable of modifying training data and labels. We develop a fully distributed and iterative algorithm to capture real-time reactions of the learner at each node to adversarial behaviors. The numerical results show that distributed SVM is prone to fail in different types of attacks, and their impact has a strong dependence on the network structure and attack capabilities. |
| Tasks | data poisoning |
| Published | 2020-03-08 |
| URL | https://arxiv.org/abs/2003.04735v1 |
| https://arxiv.org/pdf/2003.04735v1.pdf | |
| PWC | https://paperswithcode.com/paper/security-of-distributed-machine-learning-a |
| Repo | |
| Framework | |
An inexact matching approach for the comparison of plane curves with general elastic metrics
| Title | An inexact matching approach for the comparison of plane curves with general elastic metrics |
| Authors | Yashil Sukurdeep, Martin Bauer, Nicolas Charon |
| Abstract | This paper introduces a new mathematical formulation and numerical approach for the computation of distances and geodesics between immersed planar curves. Our approach combines the general simplifying transform for first-order elastic metrics that was recently introduced by Kurtek and Needham, together with a relaxation of the matching constraint using parametrization-invariant fidelity metrics. The main advantages of this formulation are that it leads to a simple optimization problem for discretized curves, and that it provides a flexible approach to deal with noisy, inconsistent or corrupted data. These benefits are illustrated via a few preliminary numerical results. |
| Tasks | |
| Published | 2020-01-09 |
| URL | https://arxiv.org/abs/2001.02858v1 |
| https://arxiv.org/pdf/2001.02858v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-inexact-matching-approach-for-the |
| Repo | |
| Framework | |
D-GCCA: Decomposition-based Generalized Canonical Correlation Analysis for Multiple High-dimensional Datasets
| Title | D-GCCA: Decomposition-based Generalized Canonical Correlation Analysis for Multiple High-dimensional Datasets |
| Authors | Hai Shu, Zhe Qu, Hongtu Zhu |
| Abstract | Modern biomedical studies often collect multiple types of high-dimensional data on a common set of objects. A popular model for the joint analysis of multi-type datasets decomposes each data matrix into a low-rank common-variation matrix generated by latent factors shared across all datasets, a low-rank distinctive-variation matrix corresponding to each dataset, and an additive noise matrix. We propose decomposition-based generalized canonical correlation analysis (D-GCCA), a novel decomposition method that appropriately defines those matrices on the L2 space of random variables, whereas most existing methods are developed on its approximation, the Euclidean dot product space. Moreover to well calibrate common latent factors, we impose a desirable orthogonality constraint on distinctive latent factors. Existing methods inadequately consider such orthogonality and can thus suffer from substantial loss of undetected common variation. Our D-GCCA takes one step further than GCCA by separating common and distinctive variations among canonical variables, and enjoys an appealing interpretation from the perspective of principal component analysis. Consistent estimators of our common-variation and distinctive-variation matrices are established with good finite-sample numerical performance, and have closed-form expressions leading to efficient computation especially for large-scale datasets. The superiority of D-GCCA over state-of-the-art methods is also corroborated in simulations and real-world data examples. |
| Tasks | |
| Published | 2020-01-09 |
| URL | https://arxiv.org/abs/2001.02856v1 |
| https://arxiv.org/pdf/2001.02856v1.pdf | |
| PWC | https://paperswithcode.com/paper/d-gcca-decomposition-based-generalized |
| Repo | |
| Framework | |
MixPoet: Diverse Poetry Generation via Learning Controllable Mixed Latent Space
| Title | MixPoet: Diverse Poetry Generation via Learning Controllable Mixed Latent Space |
| Authors | Xiaoyuan Yi, Ruoyu Li, Cheng Yang, Wenhao Li, Maosong Sun |
| Abstract | As an essential step towards computer creativity, automatic poetry generation has gained increasing attention these years. Though recent neural models make prominent progress in some criteria of poetry quality, generated poems still suffer from the problem of poor diversity. Related literature researches show that different factors, such as life experience, historical background, etc., would influence composition styles of poets, which considerably contributes to the high diversity of human-authored poetry. Inspired by this, we propose MixPoet, a novel model that absorbs multiple factors to create various styles and promote diversity. Based on a semi-supervised variational autoencoder, our model disentangles the latent space into some subspaces, with each conditioned on one influence factor by adversarial training. In this way, the model learns a controllable latent variable to capture and mix generalized factor-related properties. Different factor mixtures lead to diverse styles and hence further differentiate generated poems from each other. Experiment results on Chinese poetry demonstrate that MixPoet improves both diversity and quality against three state-of-the-art models. |
| Tasks | |
| Published | 2020-03-13 |
| URL | https://arxiv.org/abs/2003.06094v1 |
| https://arxiv.org/pdf/2003.06094v1.pdf | |
| PWC | https://paperswithcode.com/paper/mixpoet-diverse-poetry-generation-via |
| Repo | |
| Framework | |
Hyper-Meta Reinforcement Learning with Sparse Reward
| Title | Hyper-Meta Reinforcement Learning with Sparse Reward |
| Authors | Yun Hua, Xiangfeng Wang, Bo Jin, Wenhao Li, Junchi Yan, Xiaofeng He, Hongyuan Zha |
| Abstract | Despite their success, existing meta reinforcement learning methods still have difficulty in learning a meta policy effectively for RL problems with sparse reward. To this end, we develop a novel meta reinforcement learning framework, Hyper-Meta RL (HMRL), for sparse reward RL problems. It consists of meta state embedding, meta reward shaping and meta policy learning modules: The cross-environment meta state embedding module constructs a common meta state space to adapt to different environments; The meta state based environment-specific meta reward shaping effectively extends the original sparse reward trajectory by cross-environmental knowledge complementarity; As a consequence, the meta policy then achieves better generalization and efficiency with the shaped meta reward. Experiments with sparse reward show the superiority of HMRL on both transferability and policy learning efficiency. |
| Tasks | |
| Published | 2020-02-11 |
| URL | https://arxiv.org/abs/2002.04238v1 |
| https://arxiv.org/pdf/2002.04238v1.pdf | |
| PWC | https://paperswithcode.com/paper/hyper-meta-reinforcement-learning-with-sparse |
| Repo | |
| Framework | |
Heaps’ law and Heaps functions in tagged texts: Evidences of their linguistic relevance
| Title | Heaps’ law and Heaps functions in tagged texts: Evidences of their linguistic relevance |
| Authors | Andrés Chacoma, Damián H. Zanette |
| Abstract | We study the relationship between vocabulary size and text length in a corpus of $75$ literary works in English, authored by six writers, distinguishing between the contributions of three grammatical classes (or ``tags,’’ namely, {\it nouns}, {\it verbs}, and {\it others}), and analyze the progressive appearance of new words of each tag along each individual text. While the power-law relation prescribed by Heaps’ law is satisfactorily fulfilled by total vocabulary sizes and text lengths, the appearance of new words in each text is on the whole well described by the average of random shufflings of the text, which does not obey a power law. Deviations from this average, however, are statistically significant and show a systematic trend across the corpus. Specifically, they reveal that the appearance of new words along each text is predominantly retarded with respect to the average of random shufflings. Moreover, different tags are shown to add systematically distinct contributions to this tendency, with {\it verbs} and {\it others} being respectively more and less retarded than the mean trend, and {\it nouns} following instead this overall mean. These statistical systematicities are likely to point to the existence of linguistically relevant information stored in the different variants of Heaps’ law, a feature that is still in need of extensive assessment. | |
| Tasks | |
| Published | 2020-01-07 |
| URL | https://arxiv.org/abs/2001.02178v1 |
| https://arxiv.org/pdf/2001.02178v1.pdf | |
| PWC | https://paperswithcode.com/paper/heaps-law-and-heaps-functions-in-tagged-texts |
| Repo | |
| Framework | |
Environment-agnostic Multitask Learning for Natural Language Grounded Navigation
| Title | Environment-agnostic Multitask Learning for Natural Language Grounded Navigation |
| Authors | Xin Wang, Vihan Jain, Eugene Ie, William Yang Wang, Zornitsa Kozareva, Sujith Ravi |
| Abstract | Recent research efforts enable study for natural language grounded navigation in photo-realistic environments, e.g., following natural language instructions or dialog. However, existing methods tend to overfit training data in seen environments and fail to generalize well in previously unseen environments. In order to close the gap between seen and unseen environments, we aim at learning a generalized navigation model from two novel perspectives: (1) we introduce a multitask navigation model that can be seamlessly trained on both Vision-Language Navigation (VLN) and Navigation from Dialog History (NDH) tasks, which benefits from richer natural language guidance and effectively transfers knowledge across tasks; (2) we propose to learn environment-agnostic representations for the navigation policy that are invariant among the environments seen during training, thus generalizing better on unseen environments. Extensive experiments show that training with environment-agnostic multitask learning objective significantly reduces the performance gap between seen and unseen environments and the navigation agent so trained outperforms the baselines on unseen environments by 16% (relative measure on success rate) on VLN and 120% (goal progress) on NDH. Our submission to the CVDN leaderboard establishes a new state-of-the-art for the NDH task outperforming the existing best model by more than 66% (goal progress) on the holdout test set. The code for training the navigation model using environment-agnostic multitask learning is available at https://github.com/google-research/valan. |
| Tasks | Vision-Language Navigation |
| Published | 2020-03-01 |
| URL | https://arxiv.org/abs/2003.00443v3 |
| https://arxiv.org/pdf/2003.00443v3.pdf | |
| PWC | https://paperswithcode.com/paper/environment-agnostic-multitask-learning-for |
| Repo | |
| Framework | |
Social-Sensor Composition for Tapestry Scenes
| Title | Social-Sensor Composition for Tapestry Scenes |
| Authors | Tooba Aamir, Hai Dong, Athman Bouguettaya |
| Abstract | The extensive use of social media platforms and overwhelming amounts of imagery data creates unique opportunities for sensing, gathering and sharing information about events. One of its potential applications is to leverage crowdsourced social media images to create a tapestry scene for scene analysis of designated locations and time intervals. The existing attempts however ignore the temporal-semantic relevance and spatio-temporal evolution of the images and direction-oriented scene reconstruction. We propose a novel social-sensor cloud (SocSen) service composition approach to form tapestry scenes for scene analysis. The novelty lies in utilising images and image meta-information to bypass expensive traditional image processing techniques to reconstruct scenes. Metadata, such as geolocation, time and angle of view of an image are modelled as non-functional attributes of a SocSen service. Our major contribution lies on proposing a context and direction-aware spatio-temporal clustering and recommendation approach for selecting a set of temporally and semantically similar services to compose the best available SocSen services. Analytical results based on real datasets are presented to demonstrate the performance of the proposed approach. |
| Tasks | |
| Published | 2020-03-28 |
| URL | https://arxiv.org/abs/2003.13684v1 |
| https://arxiv.org/pdf/2003.13684v1.pdf | |
| PWC | https://paperswithcode.com/paper/social-sensor-composition-for-tapestry-scenes |
| Repo | |
| Framework | |
