Paper Group ANR 7
Relative Geometry-Aware Siamese Neural Network for 6DOF Camera Relocalization. Random Fourier Features via Fast Surrogate Leverage Weighted Sampling. Sparse optimal control of networks with multiplicative noise via policy gradient. Aggregation of pairwise comparisons with reduction of biases. From Language to Goals: Inverse Reinforcement Learning f …
Relative Geometry-Aware Siamese Neural Network for 6DOF Camera Relocalization
| Title | Relative Geometry-Aware Siamese Neural Network for 6DOF Camera Relocalization |
| Authors | Qing Li, Jiasong Zhu, Rui Cao, Ke Sun, Jonathan M. Garibaldi, Qingquan Li, Bozhi Liu, Guoping Qiu |
| Abstract | 6DOF camera relocalization is an important component of autonomous driving and navigation. Deep learning has recently emerged as a promising technique to tackle this problem. In this paper, we present a novel relative geometry-aware Siamese neural network to enhance the performance of deep learning-based methods through explicitly exploiting the relative geometry constraints between images. We perform multi-task learning and predict the absolute and relative poses simultaneously. We regularize the shared-weight twin networks in both the pose and feature domains to ensure that the estimated poses are globally as well as locally correct. We employ metric learning and design a novel adaptive metric distance loss to learn a feature that is capable of distinguishing poses of visually similar images from different locations. We evaluate the proposed method on public indoor and outdoor benchmarks and the experimental results demonstrate that our method can significantly improve localization performance. Furthermore, extensive ablation evaluations are conducted to demonstrate the effectiveness of different terms of the loss function. |
| Tasks | Autonomous Driving, Camera Relocalization, Metric Learning, Multi-Task Learning |
| Published | 2019-01-04 |
| URL | http://arxiv.org/abs/1901.01049v2 |
| http://arxiv.org/pdf/1901.01049v2.pdf | |
| PWC | https://paperswithcode.com/paper/relative-geometry-aware-siamese-neural |
| Repo | |
| Framework | |
Random Fourier Features via Fast Surrogate Leverage Weighted Sampling
| Title | Random Fourier Features via Fast Surrogate Leverage Weighted Sampling |
| Authors | Fanghui Liu, Xiaolin Huang, Yudong Chen, Jie Yang, Johan A. K. Suykens |
| Abstract | In this paper, we propose a fast surrogate leverage weighted sampling strategy to generate refined random Fourier features for kernel approximation. Compared to the current state-of-the-art method that uses the leverage weighted scheme [Li-ICML2019], our new strategy is simpler and more effective. It uses kernel alignment to guide the sampling process and it can avoid the matrix inversion operator when we compute the leverage function. Given n observations and s random features, our strategy can reduce the time complexity from O(ns^2+s^3) to O(ns^2), while achieving comparable (or even slightly better) prediction performance when applied to kernel ridge regression (KRR). In addition, we provide theoretical guarantees on the generalization performance of our approach, and in particular characterize the number of random features required to achieve statistical guarantees in KRR. Experiments on several benchmark datasets demonstrate that our algorithm achieves comparable prediction performance and takes less time cost when compared to [Li-ICML2019]. |
| Tasks | |
| Published | 2019-11-20 |
| URL | https://arxiv.org/abs/1911.09158v1 |
| https://arxiv.org/pdf/1911.09158v1.pdf | |
| PWC | https://paperswithcode.com/paper/random-fourier-features-via-fast-surrogate |
| Repo | |
| Framework | |
Sparse optimal control of networks with multiplicative noise via policy gradient
| Title | Sparse optimal control of networks with multiplicative noise via policy gradient |
| Authors | Benjamin Gravell, Yi Guo, Tyler Summers |
| Abstract | We give algorithms for designing near-optimal sparse controllers using policy gradient with applications to control of systems corrupted by multiplicative noise, which is increasingly important in emerging complex dynamical networks. Various regularization schemes are examined and incorporated into the optimization by the use of gradient, subgradient, and proximal gradient methods. Numerical experiments on a large networked system show that the algorithms converge to performant sparse mean-square stabilizing controllers. |
| Tasks | |
| Published | 2019-05-28 |
| URL | https://arxiv.org/abs/1905.13548v1 |
| https://arxiv.org/pdf/1905.13548v1.pdf | |
| PWC | https://paperswithcode.com/paper/190513548 |
| Repo | |
| Framework | |
Aggregation of pairwise comparisons with reduction of biases
| Title | Aggregation of pairwise comparisons with reduction of biases |
| Authors | Nadezhda Bugakova, Valentina Fedorova, Gleb Gusev, Alexey Drutsa |
| Abstract | We study the problem of ranking from crowdsourced pairwise comparisons. Answers to pairwise tasks are known to be affected by the position of items on the screen, however, previous models for aggregation of pairwise comparisons do not focus on modeling such kind of biases. We introduce a new aggregation model factorBT for pairwise comparisons, which accounts for certain factors of pairwise tasks that are known to be irrelevant to the result of comparisons but may affect workers’ answers due to perceptual reasons. By modeling biases that influence workers, factorBT is able to reduce the effect of biased pairwise comparisons on the resulted ranking. Our empirical studies on real-world data sets showed that factorBT produces more accurate ranking from crowdsourced pairwise comparisons than previously established models. |
| Tasks | |
| Published | 2019-06-09 |
| URL | https://arxiv.org/abs/1906.03711v1 |
| https://arxiv.org/pdf/1906.03711v1.pdf | |
| PWC | https://paperswithcode.com/paper/aggregation-of-pairwise-comparisons-with |
| Repo | |
| Framework | |
From Language to Goals: Inverse Reinforcement Learning for Vision-Based Instruction Following
| Title | From Language to Goals: Inverse Reinforcement Learning for Vision-Based Instruction Following |
| Authors | Justin Fu, Anoop Korattikara, Sergey Levine, Sergio Guadarrama |
| Abstract | Reinforcement learning is a promising framework for solving control problems, but its use in practical situations is hampered by the fact that reward functions are often difficult to engineer. Specifying goals and tasks for autonomous machines, such as robots, is a significant challenge: conventionally, reward functions and goal states have been used to communicate objectives. But people can communicate objectives to each other simply by describing or demonstrating them. How can we build learning algorithms that will allow us to tell machines what we want them to do? In this work, we investigate the problem of grounding language commands as reward functions using inverse reinforcement learning, and argue that language-conditioned rewards are more transferable than language-conditioned policies to new environments. We propose language-conditioned reward learning (LC-RL), which grounds language commands as a reward function represented by a deep neural network. We demonstrate that our model learns rewards that transfer to novel tasks and environments on realistic, high-dimensional visual environments with natural language commands, whereas directly learning a language-conditioned policy leads to poor performance. |
| Tasks | |
| Published | 2019-02-20 |
| URL | http://arxiv.org/abs/1902.07742v1 |
| http://arxiv.org/pdf/1902.07742v1.pdf | |
| PWC | https://paperswithcode.com/paper/from-language-to-goals-inverse-reinforcement |
| Repo | |
| Framework | |
EQSA: Earthquake Situational Analytics from Social Media
| Title | EQSA: Earthquake Situational Analytics from Social Media |
| Authors | Huyen Nguyen, Tommy Dang |
| Abstract | This paper introduces EQSA, an interactive exploratory tool for earthquake situational analytics using social media. EQSA is designed to support users to characterize the condition across the area around the earthquake zone, regarding related events, resources to be allocated, and responses from the community. On the general level, changes in the volume of messages from chosen categories are presented, assisting users in conveying a general idea of the condition. More in-depth analysis is provided with topic evolution, community visualization, and location representation. EQSA is developed with intuitive, interactive features and multiple linked views, visualizing social media data, and supporting users to gain a comprehensive insight into the situation. In this paper, we present the application of EQSA with the VAST Challenge 2019: Mini-Challenge 3 (MC3) dataset. |
| Tasks | |
| Published | 2019-10-20 |
| URL | https://arxiv.org/abs/1910.08881v1 |
| https://arxiv.org/pdf/1910.08881v1.pdf | |
| PWC | https://paperswithcode.com/paper/eqsa-earthquake-situational-analytics-from |
| Repo | |
| Framework | |
Fast Local Planning and Mapping in Unknown Off-Road Terrain
| Title | Fast Local Planning and Mapping in Unknown Off-Road Terrain |
| Authors | Timothy Overbye, Srikanth Saripalli |
| Abstract | In this paper, we present a fast, on-line mapping and planning solution for operation in unknown, off-road, environments. We combine obstacle detection along with a terrain gradient map to make simple and adaptable cost map. This map can be created and updated at 10 Hz. An A* planner finds optimal paths over the map. Finally, we take multiple samples over the control input space and do a kinematic forward simulation to generated feasible trajectories. Then the most optimal trajectory, as determined by the cost map and proximity to A* path, is chosen and sent to the controller. Our method allows real time operation at rates of 30 Hz. We demonstrate the efficiency of our method in various off-road terrain at high speed. |
| Tasks | |
| Published | 2019-10-18 |
| URL | https://arxiv.org/abs/1910.08521v1 |
| https://arxiv.org/pdf/1910.08521v1.pdf | |
| PWC | https://paperswithcode.com/paper/fast-local-planning-and-mapping-in-unknown |
| Repo | |
| Framework | |
Dynamic Modeling and Equilibria in Fair Decision Making
| Title | Dynamic Modeling and Equilibria in Fair Decision Making |
| Authors | Joshua Williams, J. Zico Kolter |
| Abstract | Recent studies on fairness in automated decision making systems have both investigated the potential future impact of these decisions on the population at large, and emphasized that imposing ‘‘typical’’ fairness constraints such as demographic parity or equality of opportunity does not guarantee a benefit to disadvantaged groups. However, these previous studies have focused on either simple one-step cost/benefit criteria, or on discrete underlying state spaces. In this work, we first propose a natural continuous representation of population state, governed by the Beta distribution, using a loan granting setting as a running example. Next, we apply a model of population dynamics under lending decisions, and show that when conditional payback probabilities are estimated correctly 1) ``optimal’’ behavior by lenders can lead to ‘‘Matthew Effect’’ bifurcations (i.e., ‘‘the rich get richer and the poor get poorer’'), but that 2) many common fairness constraints on the allowable policies cause groups to converge to the same equilibrium point. Last, we contrast our results in the case of misspecified conditional probability estimates with prior work, and show that for this model, different levels of group misestimation guarantees that even fair policies lead to bifurcations. We illustrate some of the modeling conclusions on real data from credit scoring. | |
| Tasks | Decision Making |
| Published | 2019-11-15 |
| URL | https://arxiv.org/abs/1911.06837v1 |
| https://arxiv.org/pdf/1911.06837v1.pdf | |
| PWC | https://paperswithcode.com/paper/dynamic-modeling-and-equilibria-in-fair |
| Repo | |
| Framework | |
Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification
| Title | Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification |
| Authors | Tzu-Ming Harry Hsu, Hang Qi, Matthew Brown |
| Abstract | Federated Learning enables visual models to be trained in a privacy-preserving way using real-world data from mobile devices. Given their distributed nature, the statistics of the data across these devices is likely to differ significantly. In this work, we look at the effect such non-identical data distributions has on visual classification via Federated Learning. We propose a way to synthesize datasets with a continuous range of identicalness and provide performance measures for the Federated Averaging algorithm. We show that performance degrades as distributions differ more, and propose a mitigation strategy via server momentum. Experiments on CIFAR-10 demonstrate improved classification performance over a range of non-identicalness, with classification accuracy improved from 30.1% to 76.9% in the most skewed settings. |
| Tasks | |
| Published | 2019-09-13 |
| URL | https://arxiv.org/abs/1909.06335v1 |
| https://arxiv.org/pdf/1909.06335v1.pdf | |
| PWC | https://paperswithcode.com/paper/measuring-the-effects-of-non-identical-data |
| Repo | |
| Framework | |
Attribute-Guided Deep Polarimetric Thermal-to-visible Face Recognition
| Title | Attribute-Guided Deep Polarimetric Thermal-to-visible Face Recognition |
| Authors | Seyed Mehdi Iranmanesh, Nasser M. Nasrabadi |
| Abstract | In this paper, we present an attribute-guided deep coupled learning framework to address the problem of matching polarimetric thermal face photos against a gallery of visible faces. The coupled framework contains two sub-networks, one dedicated to the visible spectrum and the second sub-network dedicated to the polarimetric thermal spectrum. Each sub-network is made of a generative adversarial network (GAN) architecture. We propose a novel Attribute-Guided Coupled Generative Adversarial Network (AGC-GAN) architecture which utilizes facial attributes to improve the thermal-to-visible face recognition performance. The proposed AGC-GAN exploits the facial attributes and leverages multiple loss functions in order to learn rich discriminative features in a common embedding subspace. To achieve a realistic photo reconstruction while preserving the discriminative information, we also add a perceptual loss term to the coupling loss function. An ablation study is performed to show the effectiveness of different loss functions for optimizing the proposed method. Moreover, the superiority of the model compared to the state-of-the-art models is demonstrated using polarimetric dataset. |
| Tasks | Face Recognition |
| Published | 2019-07-27 |
| URL | https://arxiv.org/abs/1907.11980v1 |
| https://arxiv.org/pdf/1907.11980v1.pdf | |
| PWC | https://paperswithcode.com/paper/attribute-guided-deep-polarimetric-thermal-to |
| Repo | |
| Framework | |
Stretching the Effectiveness of MLE from Accuracy to Bias for Pairwise Comparisons
| Title | Stretching the Effectiveness of MLE from Accuracy to Bias for Pairwise Comparisons |
| Authors | Jingyan Wang, Nihar B. Shah, R. Ravi |
| Abstract | A number of applications (e.g., AI bot tournaments, sports, peer grading, crowdsourcing) use pairwise comparison data and the Bradley-Terry-Luce (BTL) model to evaluate a given collection of items (e.g., bots, teams, students, search results). Past work has shown that under the BTL model, the widely-used maximum-likelihood estimator (MLE) is minimax-optimal in estimating the item parameters, in terms of the mean squared error. However, another important desideratum for designing estimators is fairness. In this work, we consider fairness modeled by the notion of bias in statistics. We show that the MLE incurs a suboptimal rate in terms of bias. We then propose a simple modification to the MLE, which “stretches” the bounding box of the maximum-likelihood optimizer by a small constant factor from the underlying ground truth domain. We show that this simple modification leads to an improved rate in bias, while maintaining minimax-optimality in the mean squared error. In this manner, our proposed class of estimators provably improves fairness represented by bias without loss in accuracy. |
| Tasks | |
| Published | 2019-06-10 |
| URL | https://arxiv.org/abs/1906.04066v1 |
| https://arxiv.org/pdf/1906.04066v1.pdf | |
| PWC | https://paperswithcode.com/paper/stretching-the-effectiveness-of-mle-from |
| Repo | |
| Framework | |
Privacy-Preserving Detection of IoT Devices Connected Behind a NAT in a Smart Home Setup
| Title | Privacy-Preserving Detection of IoT Devices Connected Behind a NAT in a Smart Home Setup |
| Authors | Yair Meidan, Vinay Sachidananda, Yuval Elovici, Asaf Shabtai |
| Abstract | Today, telecommunication service providers (telcos) are exposed to cyber-attacks executed by compromised IoT devices connected to their customers’ networks. Such attacks might have severe effects not only on the target of attacks but also on the telcos themselves. To mitigate those risks we propose a machine learning based method that can detect devices of specific vulnerable IoT models connected behind a domestic NAT, thereby identifying home networks that pose a risk to the telco’s infrastructure and availability of services. As part of the effort to preserve the domestic customers’ privacy, our method relies on NetFlow data solely, refraining from inspecting the payload. To promote future research in this domain we share our novel dataset, collected in our lab from numerous and various commercial IoT devices. |
| Tasks | |
| Published | 2019-05-31 |
| URL | https://arxiv.org/abs/1905.13430v1 |
| https://arxiv.org/pdf/1905.13430v1.pdf | |
| PWC | https://paperswithcode.com/paper/privacy-preserving-detection-of-iot-devices |
| Repo | |
| Framework | |
DDLSTM: Dual-Domain LSTM for Cross-Dataset Action Recognition
| Title | DDLSTM: Dual-Domain LSTM for Cross-Dataset Action Recognition |
| Authors | Toby Perrett, Dima Damen |
| Abstract | Domain alignment in convolutional networks aims to learn the degree of layer-specific feature alignment beneficial to the joint learning of source and target datasets. While increasingly popular in convolutional networks, there have been no previous attempts to achieve domain alignment in recurrent networks. Similar to spatial features, both source and target domains are likely to exhibit temporal dependencies that can be jointly learnt and aligned. In this paper we introduce Dual-Domain LSTM (DDLSTM), an architecture that is able to learn temporal dependencies from two domains concurrently. It performs cross-contaminated batch normalisation on both input-to-hidden and hidden-to-hidden weights, and learns the parameters for cross-contamination, for both single-layer and multi-layer LSTM architectures. We evaluate DDLSTM on frame-level action recognition using three datasets, taking a pair at a time, and report an average increase in accuracy of 3.5%. The proposed DDLSTM architecture outperforms standard, fine-tuned, and batch-normalised LSTMs. |
| Tasks | Temporal Action Localization |
| Published | 2019-04-18 |
| URL | http://arxiv.org/abs/1904.08634v1 |
| http://arxiv.org/pdf/1904.08634v1.pdf | |
| PWC | https://paperswithcode.com/paper/ddlstm-dual-domain-lstm-for-cross-dataset |
| Repo | |
| Framework | |
A Higher-Order Kolmogorov-Smirnov Test
| Title | A Higher-Order Kolmogorov-Smirnov Test |
| Authors | Veeranjaneyulu Sadhanala, Yu-Xiang Wang, Aaditya Ramdas, Ryan J. Tibshirani |
| Abstract | We present an extension of the Kolmogorov-Smirnov (KS) two-sample test, which can be more sensitive to differences in the tails. Our test statistic is an integral probability metric (IPM) defined over a higher-order total variation ball, recovering the original KS test as its simplest case. We give an exact representer result for our IPM, which generalizes the fact that the original KS test statistic can be expressed in equivalent variational and CDF forms. For small enough orders ($k \leq 5$), we develop a linear-time algorithm for computing our higher-order KS test statistic; for all others ($k \geq 6$), we give a nearly linear-time approximation. We derive the asymptotic null distribution for our test, and show that our nearly linear-time approximation shares the same asymptotic null. Lastly, we complement our theory with numerical studies. |
| Tasks | |
| Published | 2019-03-24 |
| URL | http://arxiv.org/abs/1903.10083v1 |
| http://arxiv.org/pdf/1903.10083v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-higher-order-kolmogorov-smirnov-test |
| Repo | |
| Framework | |
Bayesian inverse regression for dimension reduction with small datasets
| Title | Bayesian inverse regression for dimension reduction with small datasets |
| Authors | Xin Cai, Guang Lin, Jinglai Li |
| Abstract | We consider supervised dimension reduction problems, namely to identify a low dimensional projection of the predictors $-x$ which can retain the statistical relationship between $-x$ and the response variable $y$. We follow the idea of the sliced inverse regression (SIR) and the sliced average variance estimation (SAVE) type of methods, which is to use the statistical information of the conditional distribution $\pi(-xy)$ to identify the dimension reduction (DR) space. In particular we focus on the task of computing this conditional distribution without slicing the data. We propose a Bayesian framework to compute the conditional distribution where the likelihood function is obtained using the Gaussian process regression model. The conditional distribution $\pi(-xy)$ can then be computed directly via Monte Carlo sampling. We then can perform DR by considering certain moment functions (e.g. the first or the second moment) of the samples of the posterior distribution. With numerical examples, we demonstrate that the proposed method is especially effective for small data problems. |
| Tasks | Dimensionality Reduction |
| Published | 2019-06-19 |
| URL | https://arxiv.org/abs/1906.08018v3 |
| https://arxiv.org/pdf/1906.08018v3.pdf | |
| PWC | https://paperswithcode.com/paper/bayesian-inverse-regression-for-supervised |
| Repo | |
| Framework | |
