Paper Group ANR 908
Instance Embedding Transfer to Unsupervised Video Object Segmentation. Blaming humans in autonomous vehicle accidents: Shared responsibility across levels of automation. Scalable Bilinear $π$ Learning Using State and Action Features. Towards Clinical Diagnosis: Automated Stroke Lesion Segmentation on Multimodal MR Image Using Convolutional Neural N …
Instance Embedding Transfer to Unsupervised Video Object Segmentation
| Title | Instance Embedding Transfer to Unsupervised Video Object Segmentation |
| Authors | Siyang Li, Bryan Seybold, Alexey Vorobyov, Alireza Fathi, Qin Huang, C. -C. Jay Kuo |
| Abstract | We propose a method for unsupervised video object segmentation by transferring the knowledge encapsulated in image-based instance embedding networks. The instance embedding network produces an embedding vector for each pixel that enables identifying all pixels belonging to the same object. Though trained on static images, the instance embeddings are stable over consecutive video frames, which allows us to link objects together over time. Thus, we adapt the instance networks trained on static images to video object segmentation and incorporate the embeddings with objectness and optical flow features, without model retraining or online fine-tuning. The proposed method outperforms state-of-the-art unsupervised segmentation methods in the DAVIS dataset and the FBMS dataset. |
| Tasks | Optical Flow Estimation, Semantic Segmentation, Unsupervised Video Object Segmentation, Video Object Segmentation, Video Semantic Segmentation |
| Published | 2018-01-03 |
| URL | http://arxiv.org/abs/1801.00908v2 |
| http://arxiv.org/pdf/1801.00908v2.pdf | |
| PWC | https://paperswithcode.com/paper/instance-embedding-transfer-to-unsupervised |
| Repo | |
| Framework | |
Blaming humans in autonomous vehicle accidents: Shared responsibility across levels of automation
| Title | Blaming humans in autonomous vehicle accidents: Shared responsibility across levels of automation |
| Authors | Edmond Awad, Sydney Levine, Max Kleiman-Weiner, Sohan Dsouza, Joshua B. Tenenbaum, Azim Shariff, Jean-François Bonnefon, Iyad Rahwan |
| Abstract | When a semi-autonomous car crashes and harms someone, how are blame and causal responsibility distributed across the human and machine drivers? In this article, we consider cases in which a pedestrian was hit and killed by a car being operated under shared control of a primary and a secondary driver. We find that when only one driver makes an error, that driver receives the blame and is considered causally responsible for the harm, regardless of whether that driver is a machine or a human. However, when both drivers make errors in cases of shared control between a human and a machine, the blame and responsibility attributed to the machine is reduced. This finding portends a public under-reaction to the malfunctioning AI components of semi-autonomous cars and therefore has a direct policy implication: a bottom-up regulatory scheme (which operates through tort law that is adjudicated through the jury system) could fail to properly regulate the safety of shared-control vehicles; instead, a top-down scheme (enacted through federal laws) may be called for. |
| Tasks | |
| Published | 2018-03-19 |
| URL | http://arxiv.org/abs/1803.07170v2 |
| http://arxiv.org/pdf/1803.07170v2.pdf | |
| PWC | https://paperswithcode.com/paper/blaming-humans-in-autonomous-vehicle |
| Repo | |
| Framework | |
Scalable Bilinear $π$ Learning Using State and Action Features
| Title | Scalable Bilinear $π$ Learning Using State and Action Features |
| Authors | Yichen Chen, Lihong Li, Mengdi Wang |
| Abstract | Approximate linear programming (ALP) represents one of the major algorithmic families to solve large-scale Markov decision processes (MDP). In this work, we study a primal-dual formulation of the ALP, and develop a scalable, model-free algorithm called bilinear $\pi$ learning for reinforcement learning when a sampling oracle is provided. This algorithm enjoys a number of advantages. First, it adopts (bi)linear models to represent the high-dimensional value function and state-action distributions, using given state and action features. Its run-time complexity depends on the number of features, not the size of the underlying MDPs. Second, it operates in a fully online fashion without having to store any sample, thus having minimal memory footprint. Third, we prove that it is sample-efficient, solving for the optimal policy to high precision with a sample complexity linear in the dimension of the parameter space. |
| Tasks | |
| Published | 2018-04-27 |
| URL | http://arxiv.org/abs/1804.10328v1 |
| http://arxiv.org/pdf/1804.10328v1.pdf | |
| PWC | https://paperswithcode.com/paper/scalable-bilinear-learning-using-state-and |
| Repo | |
| Framework | |
Towards Clinical Diagnosis: Automated Stroke Lesion Segmentation on Multimodal MR Image Using Convolutional Neural Network
| Title | Towards Clinical Diagnosis: Automated Stroke Lesion Segmentation on Multimodal MR Image Using Convolutional Neural Network |
| Authors | Zhiyang Liu, Chen Cao, Shuxue Ding, Tong Han, Hong Wu, Sheng Liu |
| Abstract | The patient with ischemic stroke can benefit most from the earliest possible definitive diagnosis. While the high quality medical resources are quite scarce across the globe, an automated diagnostic tool is expected in analyzing the magnetic resonance (MR) images to provide reference in clinical diagnosis. In this paper, we propose a deep learning method to automatically segment ischemic stroke lesions from multi-modal MR images. By using atrous convolution and global convolution network, our proposed residual-structured fully convolutional network (Res-FCN) is able to capture features from large receptive fields. The network architecture is validated on a large dataset of 212 clinically acquired multi-modal MR images, which is shown to achieve a mean dice coefficient of 0.645 with a mean number of false negative lesions of 1.515. The false negatives can reach a value that close to a common medical image doctor, making it exceptive for a real clinical application. |
| Tasks | Lesion Segmentation |
| Published | 2018-03-05 |
| URL | http://arxiv.org/abs/1803.05848v1 |
| http://arxiv.org/pdf/1803.05848v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-clinical-diagnosis-automated-stroke |
| Repo | |
| Framework | |
Trade Selection with Supervised Learning and OCA
| Title | Trade Selection with Supervised Learning and OCA |
| Authors | David Saltiel, Eric Benhamou |
| Abstract | In recent years, state-of-the-art methods for supervised learning have exploited increasingly gradient boosting techniques, with mainstream efficient implementations such as xgboost or lightgbm. One of the key points in generating proficient methods is Feature Selection (FS). It consists in selecting the right valuable effective features. When facing hundreds of these features, it becomes critical to select best features. While filter and wrappers methods have come to some maturity, embedded methods are truly necessary to find the best features set as they are hybrid methods combining features filtering and wrapping. In this work, we tackle the problem of finding through machine learning best a priori trades from an algorithmic strategy. We derive this new method using coordinate ascent optimization and using block variables. We compare our method to Recursive Feature Elimination (RFE) and Binary Coordinate Ascent (BCA). We show on a real life example the capacity of this method to select good trades a priori. Not only this method outperforms the initial trading strategy as it avoids taking loosing trades, it also surpasses other method, having the smallest feature set and the highest score at the same time. The interest of this method goes beyond this simple trade classification problem as it is a very general method to determine the optimal feature set using some information about features relationship as well as using coordinate ascent optimization. |
| Tasks | Feature Selection |
| Published | 2018-12-09 |
| URL | http://arxiv.org/abs/1812.04486v1 |
| http://arxiv.org/pdf/1812.04486v1.pdf | |
| PWC | https://paperswithcode.com/paper/trade-selection-with-supervised-learning-and |
| Repo | |
| Framework | |
Concealing the identity of faces in oblique images with adaptive hopping Gaussian mixtures
| Title | Concealing the identity of faces in oblique images with adaptive hopping Gaussian mixtures |
| Authors | Omair Sarwar, Bernhard Rinner, Andrea Cavallaro |
| Abstract | Cameras mounted on Micro Aerial Vehicles (MAVs) are increasingly used for recreational photography. However, aerial photographs of public places often contain faces of bystanders thus leading to a perceived or actual violation of privacy. To address this issue, we propose to pseudo-randomly modify the appearance of face regions in the images using a privacy filter that prevents a human or a face recogniser from inferring the identities of people. The filter, which is applied only when the resolution is high enough for a face to be recognisable, adaptively distorts the face appearance as a function of its resolution. Moreover, the proposed filter locally changes its parameters to discourage attacks that use parameter estimation. The filter exploits both global adaptiveness to reduce distortion and local hopping of the parameters to make their estimation difficult for an attacker. In order to evaluate the efficiency of the proposed approach, we use a state-of-the-art face recognition algorithm and synthetically generated face data with 3D geometric image transformations that mimic faces captured from an MAV at different heights and pitch angles. Experimental results show that the proposed filter protects privacy while reducing distortion and exhibits resilience against attacks. |
| Tasks | Face Recognition |
| Published | 2018-10-29 |
| URL | http://arxiv.org/abs/1810.12435v1 |
| http://arxiv.org/pdf/1810.12435v1.pdf | |
| PWC | https://paperswithcode.com/paper/concealing-the-identity-of-faces-in-oblique |
| Repo | |
| Framework | |
The fifth ‘CHiME’ Speech Separation and Recognition Challenge: Dataset, task and baselines
| Title | The fifth ‘CHiME’ Speech Separation and Recognition Challenge: Dataset, task and baselines |
| Authors | Jon Barker, Shinji Watanabe, Emmanuel Vincent, Jan Trmal |
| Abstract | The CHiME challenge series aims to advance robust automatic speech recognition (ASR) technology by promoting research at the interface of speech and language processing, signal processing , and machine learning. This paper introduces the 5th CHiME Challenge, which considers the task of distant multi-microphone conversational ASR in real home environments. Speech material was elicited using a dinner party scenario with efforts taken to capture data that is representative of natural conversational speech and recorded by 6 Kinect microphone arrays and 4 binaural microphone pairs. The challenge features a single-array track and a multiple-array track and, for each track, distinct rankings will be produced for systems focusing on robustness with respect to distant-microphone capture vs. systems attempting to address all aspects of the task including conversational language modeling. We discuss the rationale for the challenge and provide a detailed description of the data collection procedure, the task, and the baseline systems for array synchronization, speech enhancement, and conventional and end-to-end ASR. |
| Tasks | End-To-End Speech Recognition, Language Modelling, Speech Enhancement, Speech Recognition, Speech Separation |
| Published | 2018-03-28 |
| URL | http://arxiv.org/abs/1803.10609v1 |
| http://arxiv.org/pdf/1803.10609v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-fifth-chime-speech-separation-and |
| Repo | |
| Framework | |
Contextual and Position-Aware Factorization Machines for Sentiment Classification
| Title | Contextual and Position-Aware Factorization Machines for Sentiment Classification |
| Authors | Shuai Wang, Mianwei Zhou, Geli Fei, Yi Chang, Bing Liu |
| Abstract | While existing machine learning models have achieved great success for sentiment classification, they typically do not explicitly capture sentiment-oriented word interaction, which can lead to poor results for fine-grained analysis at the snippet level (a phrase or sentence). Factorization Machine provides a possible approach to learning element-wise interaction for recommender systems, but they are not directly applicable to our task due to the inability to model contexts and word sequences. In this work, we develop two Position-aware Factorization Machines which consider word interaction, context and position information. Such information is jointly encoded in a set of sentiment-oriented word interaction vectors. Compared to traditional word embeddings, SWI vectors explicitly capture sentiment-oriented word interaction and simplify the parameter learning. Experimental results show that while they have comparable performance with state-of-the-art methods for document-level classification, they benefit the snippet/sentence-level sentiment analysis. |
| Tasks | Recommendation Systems, Sentiment Analysis, Word Embeddings |
| Published | 2018-01-18 |
| URL | http://arxiv.org/abs/1801.06172v1 |
| http://arxiv.org/pdf/1801.06172v1.pdf | |
| PWC | https://paperswithcode.com/paper/contextual-and-position-aware-factorization |
| Repo | |
| Framework | |
A Temporally Sensitive Submodularity Framework for Timeline Summarization
| Title | A Temporally Sensitive Submodularity Framework for Timeline Summarization |
| Authors | Sebastian Martschat, Katja Markert |
| Abstract | Timeline summarization (TLS) creates an overview of long-running events via dated daily summaries for the most important dates. TLS differs from standard multi-document summarization (MDS) in the importance of date selection, interdependencies between summaries of different dates and by having very short summaries compared to the number of corpus documents. However, we show that MDS optimization models using submodular functions can be adapted to yield well-performing TLS models by designing objective functions and constraints that model the temporal dimension inherent in TLS. Importantly, these adaptations retain the elegance and advantages of the original MDS models (clear separation of features and inference, performance guarantees and scalability, little need for supervision) that current TLS-specific models lack. An open-source implementation of the framework and all models described in this paper is available online. |
| Tasks | Document Summarization, Multi-Document Summarization, Timeline Summarization |
| Published | 2018-10-18 |
| URL | http://arxiv.org/abs/1810.07949v1 |
| http://arxiv.org/pdf/1810.07949v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-temporally-sensitive-submodularity |
| Repo | |
| Framework | |
Where Do You Think You’re Going?: Inferring Beliefs about Dynamics from Behavior
| Title | Where Do You Think You’re Going?: Inferring Beliefs about Dynamics from Behavior |
| Authors | Siddharth Reddy, Anca D. Dragan, Sergey Levine |
| Abstract | Inferring intent from observed behavior has been studied extensively within the frameworks of Bayesian inverse planning and inverse reinforcement learning. These methods infer a goal or reward function that best explains the actions of the observed agent, typically a human demonstrator. Another agent can use this inferred intent to predict, imitate, or assist the human user. However, a central assumption in inverse reinforcement learning is that the demonstrator is close to optimal. While models of suboptimal behavior exist, they typically assume that suboptimal actions are the result of some type of random noise or a known cognitive bias, like temporal inconsistency. In this paper, we take an alternative approach, and model suboptimal behavior as the result of internal model misspecification: the reason that user actions might deviate from near-optimal actions is that the user has an incorrect set of beliefs about the rules – the dynamics – governing how actions affect the environment. Our insight is that while demonstrated actions may be suboptimal in the real world, they may actually be near-optimal with respect to the user’s internal model of the dynamics. By estimating these internal beliefs from observed behavior, we arrive at a new method for inferring intent. We demonstrate in simulation and in a user study with 12 participants that this approach enables us to more accurately model human intent, and can be used in a variety of applications, including offering assistance in a shared autonomy framework and inferring human preferences. |
| Tasks | |
| Published | 2018-05-21 |
| URL | http://arxiv.org/abs/1805.08010v4 |
| http://arxiv.org/pdf/1805.08010v4.pdf | |
| PWC | https://paperswithcode.com/paper/where-do-you-think-youre-going-inferring |
| Repo | |
| Framework | |
Hierarchy of GANs for learning embodied self-awareness model
| Title | Hierarchy of GANs for learning embodied self-awareness model |
| Authors | Mahdyar Ravanbakhsh, Mohamad Baydoun, Damian Campo, Pablo Marin, David Martin, Lucio Marcenaro, Carlo S. Regazzoni |
| Abstract | In recent years several architectures have been proposed to learn embodied agents complex self-awareness models. In this paper, dynamic incremental self-awareness (SA) models are proposed that allow experiences done by an agent to be modeled in a hierarchical fashion, starting from more simple situations to more structured ones. Each situation is learned from subsets of private agent perception data as a model capable to predict normal behaviors and detect abnormalities. Hierarchical SA models have been already proposed using low dimensional sensorial inputs. In this work, a hierarchical model is introduced by means of a cross-modal Generative Adversarial Networks (GANs) processing high dimensional visual data. Different levels of the GANs are detected in a self-supervised manner using GANs discriminators decision boundaries. Real experiments on semi-autonomous ground vehicles are presented. |
| Tasks | |
| Published | 2018-06-08 |
| URL | http://arxiv.org/abs/1806.04012v1 |
| http://arxiv.org/pdf/1806.04012v1.pdf | |
| PWC | https://paperswithcode.com/paper/hierarchy-of-gans-for-learning-embodied-self |
| Repo | |
| Framework | |
LSICC: A Large Scale Informal Chinese Corpus
| Title | LSICC: A Large Scale Informal Chinese Corpus |
| Authors | Jianyu Zhao, Zhuoran Ji |
| Abstract | Deep learning based natural language processing model is proven powerful, but need large-scale dataset. Due to the significant gap between the real-world tasks and existing Chinese corpus, in this paper, we introduce a large-scale corpus of informal Chinese. This corpus contains around 37 million book reviews and 50 thousand netizen’s comments to the news. We explore the informal words frequencies of the corpus and show the difference between our corpus and the existing ones. The corpus can be further used to train deep learning based natural language processing tasks such as Chinese word segmentation, sentiment analysis. |
| Tasks | Chinese Word Segmentation, Sentiment Analysis |
| Published | 2018-11-26 |
| URL | http://arxiv.org/abs/1811.10167v1 |
| http://arxiv.org/pdf/1811.10167v1.pdf | |
| PWC | https://paperswithcode.com/paper/lsicc-a-large-scale-informal-chinese-corpus |
| Repo | |
| Framework | |
Locally Private Gaussian Estimation
| Title | Locally Private Gaussian Estimation |
| Authors | Matthew Joseph, Janardhan Kulkarni, Jieming Mao, Zhiwei Steven Wu |
| Abstract | We study a basic private estimation problem: each of $n$ users draws a single i.i.d. sample from an unknown Gaussian distribution, and the goal is to estimate the mean of this Gaussian distribution while satisfying local differential privacy for each user. Informally, local differential privacy requires that each data point is individually and independently privatized before it is passed to a learning algorithm. Locally private Gaussian estimation is therefore difficult because the data domain is unbounded: users may draw arbitrarily different inputs, but local differential privacy nonetheless mandates that different users have (worst-case) similar privatized output distributions. We provide both adaptive two-round solutions and nonadaptive one-round solutions for locally private Gaussian estimation. We then partially match these upper bounds with an information-theoretic lower bound. This lower bound shows that our accuracy guarantees are tight up to logarithmic factors for all sequentially interactive $(\varepsilon,\delta)$-locally private protocols. |
| Tasks | |
| Published | 2018-11-20 |
| URL | https://arxiv.org/abs/1811.08382v2 |
| https://arxiv.org/pdf/1811.08382v2.pdf | |
| PWC | https://paperswithcode.com/paper/locally-private-gaussian-estimation |
| Repo | |
| Framework | |
Generative Neural Machine Translation
| Title | Generative Neural Machine Translation |
| Authors | Harshil Shah, David Barber |
| Abstract | We introduce Generative Neural Machine Translation (GNMT), a latent variable architecture which is designed to model the semantics of the source and target sentences. We modify an encoder-decoder translation model by adding a latent variable as a language agnostic representation which is encouraged to learn the meaning of the sentence. GNMT achieves competitive BLEU scores on pure translation tasks, and is superior when there are missing words in the source sentence. We augment the model to facilitate multilingual translation and semi-supervised learning without adding parameters. This framework significantly reduces overfitting when there is limited paired data available, and is effective for translating between pairs of languages not seen during training. |
| Tasks | Machine Translation |
| Published | 2018-06-13 |
| URL | http://arxiv.org/abs/1806.05138v1 |
| http://arxiv.org/pdf/1806.05138v1.pdf | |
| PWC | https://paperswithcode.com/paper/generative-neural-machine-translation |
| Repo | |
| Framework | |
Mapping Text to Knowledge Graph Entities using Multi-Sense LSTMs
| Title | Mapping Text to Knowledge Graph Entities using Multi-Sense LSTMs |
| Authors | Dimitri Kartsaklis, Mohammad Taher Pilehvar, Nigel Collier |
| Abstract | This paper addresses the problem of mapping natural language text to knowledge base entities. The mapping process is approached as a composition of a phrase or a sentence into a point in a multi-dimensional entity space obtained from a knowledge graph. The compositional model is an LSTM equipped with a dynamic disambiguation mechanism on the input word embeddings (a Multi-Sense LSTM), addressing polysemy issues. Further, the knowledge base space is prepared by collecting random walks from a graph enhanced with textual features, which act as a set of semantic bridges between text and knowledge base entities. The ideas of this work are demonstrated on large-scale text-to-entity mapping and entity classification tasks, with state of the art results. |
| Tasks | Word Embeddings |
| Published | 2018-08-23 |
| URL | http://arxiv.org/abs/1808.07724v1 |
| http://arxiv.org/pdf/1808.07724v1.pdf | |
| PWC | https://paperswithcode.com/paper/mapping-text-to-knowledge-graph-entities |
| Repo | |
| Framework | |
