Paper Group ANR 790
Look Before You Leap: Bridging Model-Free and Model-Based Reinforcement Learning for Planned-Ahead Vision-and-Language Navigation. A Mixture Model Based Defense for Data Poisoning Attacks Against Naive Bayes Spam Filters. Cascaded CNN-resBiLSTM-CTC: An End-to-End Acoustic Model For Speech Recognition. Learning to Ask Good Questions: Ranking Clarifi …
Look Before You Leap: Bridging Model-Free and Model-Based Reinforcement Learning for Planned-Ahead Vision-and-Language Navigation
| Title | Look Before You Leap: Bridging Model-Free and Model-Based Reinforcement Learning for Planned-Ahead Vision-and-Language Navigation |
| Authors | Xin Wang, Wenhan Xiong, Hongmin Wang, William Yang Wang |
| Abstract | Existing research studies on vision and language grounding for robot navigation focus on improving model-free deep reinforcement learning (DRL) models in synthetic environments. However, model-free DRL models do not consider the dynamics in the real-world environments, and they often fail to generalize to new scenes. In this paper, we take a radical approach to bridge the gap between synthetic studies and real-world practices—We propose a novel, planned-ahead hybrid reinforcement learning model that combines model-free and model-based reinforcement learning to solve a real-world vision-language navigation task. Our look-ahead module tightly integrates a look-ahead policy model with an environment model that predicts the next state and the reward. Experimental results suggest that our proposed method significantly outperforms the baselines and achieves the best on the real-world Room-to-Room dataset. Moreover, our scalable method is more generalizable when transferring to unseen environments. |
| Tasks | Robot Navigation, Vision-Language Navigation |
| Published | 2018-03-21 |
| URL | http://arxiv.org/abs/1803.07729v2 |
| http://arxiv.org/pdf/1803.07729v2.pdf | |
| PWC | https://paperswithcode.com/paper/look-before-you-leap-bridging-model-free-and |
| Repo | |
| Framework | |
A Mixture Model Based Defense for Data Poisoning Attacks Against Naive Bayes Spam Filters
| Title | A Mixture Model Based Defense for Data Poisoning Attacks Against Naive Bayes Spam Filters |
| Authors | David J. Miller, Xinyi Hu, Zhen Xiang, George Kesidis |
| Abstract | Naive Bayes spam filters are highly susceptible to data poisoning attacks. Here, known spam sources/blacklisted IPs exploit the fact that their received emails will be treated as (ground truth) labeled spam examples, and used for classifier training (or re-training). The attacking source thus generates emails that will skew the spam model, potentially resulting in great degradation in classifier accuracy. Such attacks are successful mainly because of the poor representation power of the naive Bayes (NB) model, with only a single (component) density to represent spam (plus a possible attack). We propose a defense based on the use of a mixture of NB models. We demonstrate that the learned mixture almost completely isolates the attack in a second NB component, with the original spam component essentially unchanged by the attack. Our approach addresses both the scenario where the classifier is being re-trained in light of new data and, significantly, the more challenging scenario where the attack is embedded in the original spam training set. Even for weak attack strengths, BIC-based model order selection chooses a two-component solution, which invokes the mixture-based defense. Promising results are presented on the TREC 2005 spam corpus. |
| Tasks | data poisoning |
| Published | 2018-10-31 |
| URL | http://arxiv.org/abs/1811.00121v1 |
| http://arxiv.org/pdf/1811.00121v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-mixture-model-based-defense-for-data |
| Repo | |
| Framework | |
Cascaded CNN-resBiLSTM-CTC: An End-to-End Acoustic Model For Speech Recognition
| Title | Cascaded CNN-resBiLSTM-CTC: An End-to-End Acoustic Model For Speech Recognition |
| Authors | Xinpei Zhou, Jiwei Li, Xi Zhou |
| Abstract | Automatic speech recognition (ASR) tasks are resolved by end-to-end deep learning models, which benefits us by less preparation of raw data, and easier transformation between languages. We propose a novel end-to-end deep learning model architecture namely cascaded CNN-resBiLSTM-CTC. In the proposed model, we add residual blocks in BiLSTM layers to extract sophisticated phoneme and semantic information together, and apply cascaded structure to pay more attention mining information of hard negative samples. By applying both simple Fast Fourier Transform (FFT) technique and n-gram language model (LM) rescoring method, we manage to achieve word error rate (WER) of 3.41% on LibriSpeech test clean corpora. Furthermore, we propose a new batch-varied method to speed up the training process in length-varied tasks, which result in 25% less training time. |
| Tasks | Language Modelling, Speech Recognition |
| Published | 2018-10-29 |
| URL | http://arxiv.org/abs/1810.12001v2 |
| http://arxiv.org/pdf/1810.12001v2.pdf | |
| PWC | https://paperswithcode.com/paper/cascaded-cnn-resbilstm-ctc-an-end-to-end |
| Repo | |
| Framework | |
Learning to Ask Good Questions: Ranking Clarification Questions using Neural Expected Value of Perfect Information
| Title | Learning to Ask Good Questions: Ranking Clarification Questions using Neural Expected Value of Perfect Information |
| Authors | Sudha Rao, Hal Daumé III |
| Abstract | Inquiry is fundamental to communication, and machines cannot effectively collaborate with humans unless they can ask questions. In this work, we build a neural network model for the task of ranking clarification questions. Our model is inspired by the idea of expected value of perfect information: a good question is one whose expected answer will be useful. We study this problem using data from StackExchange, a plentiful online resource in which people routinely ask clarifying questions to posts so that they can better offer assistance to the original poster. We create a dataset of clarification questions consisting of ~77K posts paired with a clarification question (and answer) from three domains of StackExchange: askubuntu, unix and superuser. We evaluate our model on 500 samples of this dataset against expert human judgments and demonstrate significant improvements over controlled baselines. |
| Tasks | |
| Published | 2018-05-12 |
| URL | http://arxiv.org/abs/1805.04655v2 |
| http://arxiv.org/pdf/1805.04655v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-ask-good-questions-ranking |
| Repo | |
| Framework | |
A probabilistic framework for multi-view feature learning with many-to-many associations via neural networks
| Title | A probabilistic framework for multi-view feature learning with many-to-many associations via neural networks |
| Authors | Akifumi Okuno, Tetsuya Hada, Hidetoshi Shimodaira |
| Abstract | A simple framework Probabilistic Multi-view Graph Embedding (PMvGE) is proposed for multi-view feature learning with many-to-many associations so that it generalizes various existing multi-view methods. PMvGE is a probabilistic model for predicting new associations via graph embedding of the nodes of data vectors with links of their associations. Multi-view data vectors with many-to-many associations are transformed by neural networks to feature vectors in a shared space, and the probability of new association between two data vectors is modeled by the inner product of their feature vectors. While existing multi-view feature learning techniques can treat only either of many-to-many association or non-linear transformation, PMvGE can treat both simultaneously. By combining Mercer’s theorem and the universal approximation theorem, we prove that PMvGE learns a wide class of similarity measures across views. Our likelihood-based estimator enables efficient computation of non-linear transformations of data vectors in large-scale datasets by minibatch SGD, and numerical experiments illustrate that PMvGE outperforms existing multi-view methods. |
| Tasks | Graph Embedding |
| Published | 2018-02-13 |
| URL | http://arxiv.org/abs/1802.04630v2 |
| http://arxiv.org/pdf/1802.04630v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-probabilistic-framework-for-multi-view |
| Repo | |
| Framework | |
MIS-SLAM: Real-time Large Scale Dense Deformable SLAM System in Minimal Invasive Surgery Based on Heterogeneous Computing
| Title | MIS-SLAM: Real-time Large Scale Dense Deformable SLAM System in Minimal Invasive Surgery Based on Heterogeneous Computing |
| Authors | Jingwei Song, Jun Wang, Liang Zhao, Shoudong Huang, Gamini Dissanayake |
| Abstract | Real-time simultaneously localization and dense mapping is very helpful for providing Virtual Reality and Augmented Reality for surgeons or even surgical robots. In this paper, we propose MIS-SLAM: a complete real-time large scale dense deformable SLAM system with stereoscope in Minimal Invasive Surgery based on heterogeneous computing by making full use of CPU and GPU. Idled CPU is used to perform ORB- SLAM for providing robust global pose. Strategies are taken to integrate modules from CPU and GPU. We solved the key problem raised in previous work, that is, fast movement of scope and blurry images make the scope tracking fail. Benefiting from improved localization, MIS-SLAM can achieve large scale scope localizing and dense mapping in real-time. It transforms and deforms current model and incrementally fuses new observation while keeping vivid texture. In-vivo experiments conducted on publicly available datasets presented in the form of videos demonstrate the feasibility and practicality of MIS-SLAM for potential clinical purpose. |
| Tasks | |
| Published | 2018-03-06 |
| URL | http://arxiv.org/abs/1803.02009v2 |
| http://arxiv.org/pdf/1803.02009v2.pdf | |
| PWC | https://paperswithcode.com/paper/mis-slam-real-time-large-scale-dense |
| Repo | |
| Framework | |
Saliency deep embedding for aurora image search
| Title | Saliency deep embedding for aurora image search |
| Authors | Xi Yang, Xinbo Gao, Bin Song, Nannan Wang, Dong Yang |
| Abstract | Deep neural networks have achieved remarkable success in the field of image search. However, the state-of-the-art algorithms are trained and tested for natural images captured with ordinary cameras. In this paper, we aim to explore a new search method for images captured with circular fisheye lens, especially the aurora images. To reduce the interference from uninformative regions and focus on the most interested regions, we propose a saliency proposal network (SPN) to replace the region proposal network (RPN) in the recent Mask R-CNN. In our SPN, the centers of the anchors are not distributed in a rectangular meshing manner, but exhibit spherical distortion. Additionally, the directions of the anchors are along the deformation lines perpendicular to the magnetic meridian, which perfectly accords with the imaging principle of circular fisheye lens. Extensive experiments are performed on the big aurora data, demonstrating the superiority of our method in both search accuracy and efficiency. |
| Tasks | Image Retrieval |
| Published | 2018-05-23 |
| URL | http://arxiv.org/abs/1805.09033v1 |
| http://arxiv.org/pdf/1805.09033v1.pdf | |
| PWC | https://paperswithcode.com/paper/saliency-deep-embedding-for-aurora-image |
| Repo | |
| Framework | |
Minimum weight norm models do not always generalize well for over-parameterized problems
| Title | Minimum weight norm models do not always generalize well for over-parameterized problems |
| Authors | Vatsal Shah, Anastasios Kyrillidis, Sujay Sanghavi |
| Abstract | Stochastic gradient descent is the de facto algorithm for training deep neural networks (DNNs). Despite its popularity, it still requires fine tuning in order to achieve its best performance. This has led to the development of adaptive methods, that claim automatic hyper-parameter optimization. Recently, researchers have studied both algorithmic classes via toy examples: e.g., for over-parameterized linear regression, Wilson et. al. (2017) shows that, while SGD always converges to the minimum-norm solution, adaptive methods show no such inclination, leading to worse generalization capabilities. Our aim is to study this conjecture further. We empirically show that the minimum weight norm is not necessarily the proper gauge of good generalization in simplified scenaria, and different models found by adaptive methods could outperform plain gradient methods. In practical DNN settings, we observe that adaptive methods can outperform SGD, with larger weight norm output models, but without necessarily reducing the amount of tuning required. |
| Tasks | |
| Published | 2018-11-16 |
| URL | http://arxiv.org/abs/1811.07055v2 |
| http://arxiv.org/pdf/1811.07055v2.pdf | |
| PWC | https://paperswithcode.com/paper/minimum-weight-norm-models-do-not-always |
| Repo | |
| Framework | |
When Gaussian Process Meets Big Data: A Review of Scalable GPs
| Title | When Gaussian Process Meets Big Data: A Review of Scalable GPs |
| Authors | Haitao Liu, Yew-Soon Ong, Xiaobo Shen, Jianfei Cai |
| Abstract | The vast quantity of information brought by big data as well as the evolving computer hardware encourages success stories in the machine learning community. In the meanwhile, it poses challenges for the Gaussian process (GP) regression, a well-known non-parametric and interpretable Bayesian model, which suffers from cubic complexity to data size. To improve the scalability while retaining desirable prediction quality, a variety of scalable GPs have been presented. But they have not yet been comprehensively reviewed and analyzed in order to be well understood by both academia and industry. The review of scalable GPs in the GP community is timely and important due to the explosion of data size. To this end, this paper is devoted to the review on state-of-the-art scalable GPs involving two main categories: global approximations which distillate the entire data and local approximations which divide the data for subspace learning. Particularly, for global approximations, we mainly focus on sparse approximations comprising prior approximations which modify the prior but perform exact inference, posterior approximations which retain exact prior but perform approximate inference, and structured sparse approximations which exploit specific structures in kernel matrix; for local approximations, we highlight the mixture/product of experts that conducts model averaging from multiple local experts to boost predictions. To present a complete review, recent advances for improving the scalability and capability of scalable GPs are reviewed. Finally, the extensions and open issues regarding the implementation of scalable GPs in various scenarios are reviewed and discussed to inspire novel ideas for future research avenues. |
| Tasks | |
| Published | 2018-07-03 |
| URL | http://arxiv.org/abs/1807.01065v2 |
| http://arxiv.org/pdf/1807.01065v2.pdf | |
| PWC | https://paperswithcode.com/paper/when-gaussian-process-meets-big-data-a-review |
| Repo | |
| Framework | |
Extracting Fairness Policies from Legal Documents
| Title | Extracting Fairness Policies from Legal Documents |
| Authors | Rashmi Nagpal, Chetna Wadhwa, Mallika Gupta, Samiulla Shaikh, Sameep Mehta, Vikram Goyal |
| Abstract | Machine Learning community is recently exploring the implications of bias and fairness with respect to the AI applications. The definition of fairness for such applications varies based on their domain of application. The policies governing the use of such machine learning system in a given context are defined by the constitutional laws of nations and regulatory policies enforced by the organizations that are involved in the usage. Fairness related laws and policies are often spread across the large documents like constitution, agreements, and organizational regulations. These legal documents have long complex sentences in order to achieve rigorousness and robustness. Automatic extraction of fairness policies, or in general, any specific kind of policies from large legal corpus can be very useful for the study of bias and fairness in the context of AI applications. We attempted to automatically extract fairness policies from publicly available law documents using two approaches based on semantic relatedness. The experiments reveal how classical Wordnet-based similarity and vector-based similarity differ in addressing this task. We have shown that similarity based on word vectors beats the classical approach with a large margin, whereas other vector representations of senses and sentences fail to even match the classical baseline. Further, we have presented thorough error analysis and reasoning to explain the results with appropriate examples from the dataset for deeper insights. |
| Tasks | |
| Published | 2018-09-12 |
| URL | http://arxiv.org/abs/1809.04262v1 |
| http://arxiv.org/pdf/1809.04262v1.pdf | |
| PWC | https://paperswithcode.com/paper/extracting-fairness-policies-from-legal |
| Repo | |
| Framework | |
Detecting Outliers in Data with Correlated Measures
| Title | Detecting Outliers in Data with Correlated Measures |
| Authors | Yu-Hsuan Kuo, Zhenhui Li, Daniel Kifer |
| Abstract | Advances in sensor technology have enabled the collection of large-scale datasets. Such datasets can be extremely noisy and often contain a significant amount of outliers that result from sensor malfunction or human operation faults. In order to utilize such data for real-world applications, it is critical to detect outliers so that models built from these datasets will not be skewed by outliers. In this paper, we propose a new outlier detection method that utilizes the correlations in the data (e.g., taxi trip distance vs. trip time). Different from existing outlier detection methods, we build a robust regression model that explicitly models the outliers and detects outliers simultaneously with the model fitting. We validate our approach on real-world datasets against methods specifically designed for each dataset as well as the state of the art outlier detectors. Our outlier detection method achieves better performances, demonstrating the robustness and generality of our method. Last, we report interesting case studies on some outliers that result from atypical events. |
| Tasks | Outlier Detection |
| Published | 2018-08-26 |
| URL | http://arxiv.org/abs/1808.08640v1 |
| http://arxiv.org/pdf/1808.08640v1.pdf | |
| PWC | https://paperswithcode.com/paper/detecting-outliers-in-data-with-correlated |
| Repo | |
| Framework | |
Learning to Segment Medical Images with Scribble-Supervision Alone
| Title | Learning to Segment Medical Images with Scribble-Supervision Alone |
| Authors | Yigit B. Can, Krishna Chaitanya, Basil Mustafa, Lisa M. Koch, Ender Konukoglu, Christian F. Baumgartner |
| Abstract | Semantic segmentation of medical images is a crucial step for the quantification of healthy anatomy and diseases alike. The majority of the current state-of-the-art segmentation algorithms are based on deep neural networks and rely on large datasets with full pixel-wise annotations. Producing such annotations can often only be done by medical professionals and requires large amounts of valuable time. Training a medical image segmentation network with weak annotations remains a relatively unexplored topic. In this work we investigate training strategies to learn the parameters of a pixel-wise segmentation network from scribble annotations alone. We evaluate the techniques on public cardiac (ACDC) and prostate (NCI-ISBI) segmentation datasets. We find that the networks trained on scribbles suffer from a remarkably small degradation in Dice of only 2.9% (cardiac) and 4.5% (prostate) with respect to a network trained on full annotations. |
| Tasks | Medical Image Segmentation, Semantic Segmentation |
| Published | 2018-07-12 |
| URL | http://arxiv.org/abs/1807.04668v1 |
| http://arxiv.org/pdf/1807.04668v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-segment-medical-images-with |
| Repo | |
| Framework | |
Outlier detection on network flow analysis
| Title | Outlier detection on network flow analysis |
| Authors | Quang-Vinh Dang |
| Abstract | It is important to be able to detect and classify malicious network traffic flows such as DDoS attacks from benign flows. Normally the task is performed by using supervised classification algorithms. In this paper we analyze the usage of outlier detection algorithms for the network traffic classification problem. |
| Tasks | Outlier Detection |
| Published | 2018-08-06 |
| URL | http://arxiv.org/abs/1808.02024v1 |
| http://arxiv.org/pdf/1808.02024v1.pdf | |
| PWC | https://paperswithcode.com/paper/outlier-detection-on-network-flow-analysis |
| Repo | |
| Framework | |
Testing Halfspaces over Rotation-Invariant Distributions
| Title | Testing Halfspaces over Rotation-Invariant Distributions |
| Authors | Nathaniel Harms |
| Abstract | We present an algorithm for testing halfspaces over arbitrary, unknown rotation-invariant distributions. Using $\tilde O(\sqrt{n}\epsilon^{-7})$ random examples of an unknown function $f$, the algorithm determines with high probability whether $f$ is of the form $f(x) = sign(\sum_i w_ix_i-t)$ or is $\epsilon$-far from all such functions. This sample size is significantly smaller than the well-known requirement of $\Omega(n)$ samples for learning halfspaces, and known lower bounds imply that our sample size is optimal (in its dependence on $n$) up to logarithmic factors. The algorithm is distribution-free in the sense that it requires no knowledge of the distribution aside from the promise of rotation invariance. To prove the correctness of this algorithm we present a theorem relating the distance between a function and a halfspace to the distance between their centers of mass, that applies to arbitrary distributions. |
| Tasks | |
| Published | 2018-10-31 |
| URL | http://arxiv.org/abs/1811.00139v1 |
| http://arxiv.org/pdf/1811.00139v1.pdf | |
| PWC | https://paperswithcode.com/paper/testing-halfspaces-over-rotation-invariant |
| Repo | |
| Framework | |
Path Planning in Support of Smart Mobility Applications using Generative Adversarial Networks
| Title | Path Planning in Support of Smart Mobility Applications using Generative Adversarial Networks |
| Authors | Mehdi Mohammadi, Ala Al-Fuqaha, Jun-Seok Oh |
| Abstract | This paper describes and evaluates the use of Generative Adversarial Networks (GANs) for path planning in support of smart mobility applications such as indoor and outdoor navigation applications, individualized wayfinding for people with disabilities (e.g., vision impairments, physical disabilities, etc.), path planning for evacuations, robotic navigations, and path planning for autonomous vehicles. We propose an architecture based on GANs to recommend accurate and reliable paths for navigation applications. The proposed system can use crowd-sourced data to learn the trajectories and infer new ones. The system provides users with generated paths that help them navigate from their local environment to reach a desired location. As a use case, we experimented with the proposed method in support of a wayfinding application in an indoor environment. Our experiments assert that the generated paths are correct and reliable. The accuracy of the classification task for the generated paths is up to 99% and the quality of the generated paths has a mean opinion score of 89%. |
| Tasks | Autonomous Vehicles |
| Published | 2018-04-23 |
| URL | http://arxiv.org/abs/1804.08396v1 |
| http://arxiv.org/pdf/1804.08396v1.pdf | |
| PWC | https://paperswithcode.com/paper/path-planning-in-support-of-smart-mobility |
| Repo | |
| Framework | |
