April 2, 2020

3501 words 17 mins read

Paper Group ANR 358

Paper Group ANR 358

3DCFS: Fast and Robust Joint 3D Semantic-Instance Segmentation via Coupled Feature Selection. Practical and Bilateral Privacy-preserving Federated Learning. UnOVOST: Unsupervised Offline Video Object Segmentation and Tracking. A Graph-Based Approach for Active Learning in Regression. Supervised Discriminative Sparse PCA with Adaptive Neighbors for …

3DCFS: Fast and Robust Joint 3D Semantic-Instance Segmentation via Coupled Feature Selection

Title 3DCFS: Fast and Robust Joint 3D Semantic-Instance Segmentation via Coupled Feature Selection
Authors Liang Du, Jingang Tan, Xiangyang Xue, Lili Chen, Hongkai Wen, Jianfeng Feng, Jiamao Li, Xiaolin Zhang
Abstract We propose a novel fast and robust 3D point clouds segmentation framework via coupled feature selection, named 3DCFS, that jointly performs semantic and instance segmentation. Inspired by the human scene perception process, we design a novel coupled feature selection module, named CFSM, that adaptively selects and fuses the reciprocal semantic and instance features from two tasks in a coupled manner. To further boost the performance of the instance segmentation task in our 3DCFS, we investigate a loss function that helps the model learn to balance the magnitudes of the output embedding dimensions during training, which makes calculating the Euclidean distance more reliable and enhances the generalizability of the model. Extensive experiments demonstrate that our 3DCFS outperforms state-of-the-art methods on benchmark datasets in terms of accuracy, speed and computational cost.
Tasks 3D Semantic Instance Segmentation, Feature Selection, Instance Segmentation, Semantic Segmentation
Published 2020-03-01
URL https://arxiv.org/abs/2003.00535v1
PDF https://arxiv.org/pdf/2003.00535v1.pdf
PWC https://paperswithcode.com/paper/3dcfs-fast-and-robust-joint-3d-semantic

Practical and Bilateral Privacy-preserving Federated Learning

Title Practical and Bilateral Privacy-preserving Federated Learning
Authors Yan Feng, Xue Yang, Weijun Fang, Shu-Tao Xia, Xiaohu Tang
Abstract Federated learning, as an emerging distributed training model of neural networks without collecting raw data, has attracted widespread attention. However, almost all existing researches of federated learning only consider protecting the privacy of clients, but not preventing model iterates and final model parameters from leaking to untrusted clients and external attackers. In this paper, we present the first bilateral privacy-preserving federated learning scheme, which protects not only the raw training data of clients, but also model iterates during the training phase as well as final model parameters. Specifically, we present an efficient privacy-preserving technique to mask or encrypt the global model, which not only allows clients to train over the noisy global model, but also ensures only the server can obtain the exact updated model. Detailed security analysis shows that clients can access neither model iterates nor the final global model; meanwhile, the server cannot obtain raw training data of clients from additional information used for recovering the exact updated model. Finally, extensive experiments demonstrate the proposed scheme has comparable model accuracy with traditional federated learning without bringing much extra communication overhead.
Published 2020-02-23
URL https://arxiv.org/abs/2002.09843v2
PDF https://arxiv.org/pdf/2002.09843v2.pdf
PWC https://paperswithcode.com/paper/practical-and-bilateral-privacy-preserving

UnOVOST: Unsupervised Offline Video Object Segmentation and Tracking

Title UnOVOST: Unsupervised Offline Video Object Segmentation and Tracking
Authors Jonathon Luiten, Idil Esen Zulfikar, Bastian Leibe
Abstract We address Unsupervised Video Object Segmentation (UVOS), the task of automatically generating accurate pixel masks for salient objects in a video sequence and of tracking these objects consistently through time, without any input about which objects should be tracked. Towards solving this task, we present UnOVOST (Unsupervised Offline Video Object Segmentation and Tracking) as a simple and generic algorithm which is able to track and segment a large variety of objects. This algorithm builds up tracks in a number stages, first grouping segments into short tracklets that are spatio-temporally consistent, before merging these tracklets into long-term consistent object tracks based on their visual similarity. In order to achieve this we introduce a novel tracklet-based Forest Path Cutting data association algorithm which builds up a decision forest of track hypotheses before cutting this forest into paths that form long-term consistent object tracks. When evaluating our approach on the DAVIS 2017 Unsupervised dataset we obtain state-of-the-art performance with a mean J &F score of 67.9% on the val, 58% on the test-dev and 56.4% on the test-challenge benchmarks, obtaining first place in the DAVIS 2019 Unsupervised Video Object Segmentation Challenge. UnOVOST even performs competitively with many semi-supervised video object segmentation algorithms even though it is not given any input as to which objects should be tracked and segmented.
Tasks Semantic Segmentation, Semi-supervised Video Object Segmentation, Unsupervised Video Object Segmentation, Video Object Segmentation, Video Semantic Segmentation
Published 2020-01-15
URL https://arxiv.org/abs/2001.05425v1
PDF https://arxiv.org/pdf/2001.05425v1.pdf
PWC https://paperswithcode.com/paper/unovost-unsupervised-offline-video-object

A Graph-Based Approach for Active Learning in Regression

Title A Graph-Based Approach for Active Learning in Regression
Authors Hongjing Zhang, S. S. Ravi, Ian Davidson
Abstract Active learning aims to reduce labeling efforts by selectively asking humans to annotate the most important data points from an unlabeled pool and is an example of human-machine interaction. Though active learning has been extensively researched for classification and ranking problems, it is relatively understudied for regression problems. Most existing active learning for regression methods use the regression function learned at each active learning iteration to select the next informative point to query. This introduces several challenges such as handling noisy labels, parameter uncertainty and overcoming initially biased training data. Instead, we propose a feature-focused approach that formulates both sequential and batch-mode active regression as a novel bipartite graph optimization problem. We conduct experiments on both noise-free and noisy settings. Our experimental results on benchmark data sets demonstrate the effectiveness of our proposed approach.
Tasks Active Learning
Published 2020-01-30
URL https://arxiv.org/abs/2001.11143v1
PDF https://arxiv.org/pdf/2001.11143v1.pdf
PWC https://paperswithcode.com/paper/a-graph-based-approach-for-active-learning-in

Supervised Discriminative Sparse PCA with Adaptive Neighbors for Dimensionality Reduction

Title Supervised Discriminative Sparse PCA with Adaptive Neighbors for Dimensionality Reduction
Authors Zhenhua Shi, Dongrui Wu, Jian Huang, Yu-Kai Wang, Chin-Teng Lin
Abstract Dimensionality reduction is an important operation in information visualization, feature extraction, clustering, regression, and classification, especially for processing noisy high dimensional data. However, most existing approaches preserve either the global or the local structure of the data, but not both. Approaches that preserve only the global data structure, such as principal component analysis (PCA), are usually sensitive to outliers. Approaches that preserve only the local data structure, such as locality preserving projections, are usually unsupervised (and hence cannot use label information) and uses a fixed similarity graph. We propose a novel linear dimensionality reduction approach, supervised discriminative sparse PCA with adaptive neighbors (SDSPCAAN), to integrate neighborhood-free supervised discriminative sparse PCA and projected clustering with adaptive neighbors. As a result, both global and local data structures, as well as the label information, are used for better dimensionality reduction. Classification experiments on nine high-dimensional datasets validated the effectiveness and robustness of our proposed SDSPCAAN.
Tasks Dimensionality Reduction
Published 2020-01-09
URL https://arxiv.org/abs/2001.03103v2
PDF https://arxiv.org/pdf/2001.03103v2.pdf
PWC https://paperswithcode.com/paper/supervised-discriminative-sparse-pca-with

Semantic Relatedness for Keyword Disambiguation: Exploiting Different Embeddings

Title Semantic Relatedness for Keyword Disambiguation: Exploiting Different Embeddings
Authors María G. Buey, Carlos Bobed, Jorge Gracia, Eduardo Mena
Abstract Understanding the meaning of words is crucial for many tasks that involve human-machine interaction. This has been tackled by research in Word Sense Disambiguation (WSD) in the Natural Language Processing (NLP) field. Recently, WSD and many other NLP tasks have taken advantage of embeddings-based representation of words, sentences, and documents. However, when it comes to WSD, most embeddings models suffer from ambiguity as they do not capture the different possible meanings of the words. Even when they do, the list of possible meanings for a word (sense inventory) has to be known in advance at training time to be included in the embeddings space. Unfortunately, there are situations in which such a sense inventory is not known in advance (e.g., an ontology selected at run-time), or it evolves with time and its status diverges from the one at training time. This hampers the use of embeddings models for WSD. Furthermore, traditional WSD techniques do not perform well in situations in which the available linguistic information is very scarce, such as the case of keyword-based queries. In this paper, we propose an approach to keyword disambiguation which grounds on a semantic relatedness between words and senses provided by an external inventory (ontology) that is not known at training time. Building on previous works, we present a semantic relatedness measure that uses word embeddings, and explore different disambiguation algorithms to also exploit both word and sentence representations. Experimental results show that this approach achieves results comparable with the state of the art when applied for WSD, without training for a particular domain.
Tasks Word Embeddings, Word Sense Disambiguation
Published 2020-02-25
URL https://arxiv.org/abs/2002.11023v1
PDF https://arxiv.org/pdf/2002.11023v1.pdf
PWC https://paperswithcode.com/paper/semantic-relatedness-for-keyword

Camera Model Anonymisation with Augmented cGANs

Title Camera Model Anonymisation with Augmented cGANs
Authors Jerone T. A. Andrews, Yidan Zhang, Lewis D. Griffin
Abstract The model of camera that was used to capture a particular photographic image (model attribution) can be inferred from model-specific artefacts present within the image. Typically these artefacts are found in high-frequency pixel patterns, rather than image content. Model anonymisation is the process of transforming these artefacts such that the apparent capture model is changed. Improved methods for attribution and anonymisation are important for improving digital forensics, and understanding its limits. Through conditional adversarial training, we present an approach for learning these transformations. Significantly, we augment the objective with the losses from pre-trained auxiliary model attribution classifiers that constrain the generator to not only synthesise discriminative high-frequency artefacts, but also salient image-based artefacts lost during image content suppression. Quantitative comparisons against a recent representative approach demonstrate the efficacy of our framework in a non-interactive black-box setting.
Published 2020-02-18
URL https://arxiv.org/abs/2002.07798v1
PDF https://arxiv.org/pdf/2002.07798v1.pdf
PWC https://paperswithcode.com/paper/camera-model-anonymisation-with-augmented

Multi-Fusion Chinese WordNet (MCW) : Compound of Machine Learning and Manual Correction

Title Multi-Fusion Chinese WordNet (MCW) : Compound of Machine Learning and Manual Correction
Authors Mingchen Li, Zili Zhou, Yanna Wang
Abstract Princeton WordNet (PWN) is a lexicon-semantic network based on cognitive linguistics, which promotes the development of natural language processing. Based on PWN, five Chinese wordnets have been developed to solve the problems of syntax and semantics. They include: Northeastern University Chinese WordNet (NEW), Sinica Bilingual Ontological WordNet (BOW), Southeast University Chinese WordNet (SEW), Taiwan University Chinese WordNet (CWN), Chinese Open WordNet (COW). By using them, we found that these word networks have low accuracy and coverage, and cannot completely portray the semantic network of PWN. So we decided to make a new Chinese wordnet called Multi-Fusion Chinese Wordnet (MCW) to make up those shortcomings. The key idea is to extend the SEW with the help of Oxford bilingual dictionary and Xinhua bilingual dictionary, and then correct it. More specifically, we used machine learning and manual adjustment in our corrections. Two standards were formulated to help our work. We conducted experiments on three tasks including relatedness calculation, word similarity and word sense disambiguation for the comparison of lemma’s accuracy, at the same time, coverage also was compared. The results indicate that MCW can benefit from coverage and accuracy via our method. However, it still has room for improvement, especially with lemmas. In the future, we will continue to enhance the accuracy of MCW and expand the concepts in it.
Tasks Word Sense Disambiguation
Published 2020-02-05
URL https://arxiv.org/abs/2002.01761v1
PDF https://arxiv.org/pdf/2002.01761v1.pdf
PWC https://paperswithcode.com/paper/multi-fusion-chinese-wordnet-mcw-compound-of

Discovering Salient Anatomical Landmarks by Predicting Human Gaze

Title Discovering Salient Anatomical Landmarks by Predicting Human Gaze
Authors Richard Droste, Pierre Chatelain, Lior Drukker, Harshita Sharma, Aris T. Papageorghiou, J. Alison Noble
Abstract Anatomical landmarks are a crucial prerequisite for many medical imaging tasks. Usually, the set of landmarks for a given task is predefined by experts. The landmark locations for a given image are then annotated manually or via machine learning methods trained on manual annotations. In this paper, in contrast, we present a method to automatically discover and localize anatomical landmarks in medical images. Specifically, we consider landmarks that attract the visual attention of humans, which we term visually salient landmarks. We illustrate the method for fetal neurosonographic images. First, full-length clinical fetal ultrasound scans are recorded with live sonographer gaze-tracking. Next, a convolutional neural network (CNN) is trained to predict the gaze point distribution (saliency map) of the sonographers on scan video frames. The CNN is then used to predict saliency maps of unseen fetal neurosonographic images, and the landmarks are extracted as the local maxima of these saliency maps. Finally, the landmarks are matched across images by clustering the landmark CNN features. We show that the discovered landmarks can be used within affine image registration, with average landmark alignment errors between 4.1% and 10.9% of the fetal head long axis length.
Tasks Image Registration
Published 2020-01-22
URL https://arxiv.org/abs/2001.08188v1
PDF https://arxiv.org/pdf/2001.08188v1.pdf
PWC https://paperswithcode.com/paper/discovering-salient-anatomical-landmarks-by

A closer look at the approximation capabilities of neural networks

Title A closer look at the approximation capabilities of neural networks
Authors Kai Fong Ernest Chong
Abstract The universal approximation theorem, in one of its most general versions, says that if we consider only continuous activation functions $\sigma$, then a standard feedforward neural network with one hidden layer is able to approximate any continuous multivariate function $f$ to any given approximation threshold $\varepsilon$, if and only if $\sigma$ is non-polynomial. In this paper, we give a direct algebraic proof of the theorem. Furthermore we shall explicitly quantify the number of hidden units required for approximation. Specifically, if $X\subseteq \mathbb{R}^n$ is compact, then a neural network with $n$ input units, $m$ output units, and a single hidden layer with $\binom{n+d}{d}$ hidden units (independent of $m$ and $\varepsilon$), can uniformly approximate any polynomial function $f:X \to \mathbb{R}^m$ whose total degree is at most $d$ for each of its $m$ coordinate functions. In the general case that $f$ is any continuous function, we show there exists some $N\in \mathcal{O}(\varepsilon^{-n})$ (independent of $m$), such that $N$ hidden units would suffice to approximate $f$. We also show that this uniform approximation property (UAP) still holds even under seemingly strong conditions imposed on the weights. We highlight several consequences: (i) For any $\delta > 0$, the UAP still holds if we restrict all non-bias weights $w$ in the last layer to satisfy $w < \delta$. (ii) There exists some $\lambda>0$ (depending only on $f$ and $\sigma$), such that the UAP still holds if we restrict all non-bias weights $w$ in the first layer to satisfy $w>\lambda$. (iii) If the non-bias weights in the first layer are \emph{fixed} and randomly chosen from a suitable range, then the UAP holds with probability $1$.
Published 2020-02-16
URL https://arxiv.org/abs/2002.06505v1
PDF https://arxiv.org/pdf/2002.06505v1.pdf
PWC https://paperswithcode.com/paper/a-closer-look-at-the-approximation-1

Particle Competition and Cooperation for Semi-Supervised Learning with Label Noise

Title Particle Competition and Cooperation for Semi-Supervised Learning with Label Noise
Authors Fabricio Aparecido Breve, Liang Zhao, Marcos Gonçalves Quiles
Abstract Semi-supervised learning methods are usually employed in the classification of data sets where only a small subset of the data items is labeled. In these scenarios, label noise is a crucial issue, since the noise may easily spread to a large portion or even the entire data set, leading to major degradation in classification accuracy. Therefore, the development of new techniques to reduce the nasty effects of label noise in semi-supervised learning is a vital issue. Recently, a graph-based semi-supervised learning approach based on Particle competition and cooperation was developed. In this model, particles walk in the graphs constructed from the data sets. Competition takes place among particles representing different class labels, while the cooperation occurs among particles with the same label. This paper presents a new particle competition and cooperation algorithm, specifically designed to increase the robustness to the presence of label noise, improving its label noise tolerance. Different from other methods, the proposed one does not require a separate technique to deal with label noise. It performs classification of unlabeled nodes and reclassification of the nodes affected by label noise in a unique process. Computer simulations show the classification accuracy of the proposed method when applied to some artificial and real-world data sets, in which we introduce increasing amounts of label noise. The classification accuracy is compared to those achieved by previous particle competition and cooperation algorithms and other representative graph-based semi-supervised learning methods using the same scenarios. Results show the effectiveness of the proposed method.
Published 2020-02-12
URL https://arxiv.org/abs/2002.05198v1
PDF https://arxiv.org/pdf/2002.05198v1.pdf
PWC https://paperswithcode.com/paper/particle-competition-and-cooperation-for-semi

A General Framework for Symmetric Property Estimation

Title A General Framework for Symmetric Property Estimation
Authors Moses Charikar, Kirankumar Shiragur, Aaron Sidford
Abstract In this paper we provide a general framework for estimating symmetric properties of distributions from i.i.d. samples. For a broad class of symmetric properties we identify the easy region where empirical estimation works and the difficult region where more complex estimators are required. We show that by approximately computing the profile maximum likelihood (PML) distribution \cite{ADOS16} in this difficult region we obtain a symmetric property estimation framework that is sample complexity optimal for many properties in a broader parameter regime than previous universal estimation approaches based on PML. The resulting algorithms based on these pseudo PML distributions are also more practical.
Published 2020-03-02
URL https://arxiv.org/abs/2003.00844v1
PDF https://arxiv.org/pdf/2003.00844v1.pdf
PWC https://paperswithcode.com/paper/a-general-framework-for-symmetric-property-1

Firearm Detection and Segmentation Using an Ensemble of Semantic Neural Networks

Title Firearm Detection and Segmentation Using an Ensemble of Semantic Neural Networks
Authors Alexander Egiazarov, Vasileios Mavroeidis, Fabio Massimo Zennaro, Kamer Vishi
Abstract In recent years we have seen an upsurge in terror attacks around the world. Such attacks usually happen in public places with large crowds to cause the most damage possible and get the most attention. Even though surveillance cameras are assumed to be a powerful tool, their effect in preventing crime is far from clear due to either limitation in the ability of humans to vigilantly monitor video surveillance or for the simple reason that they are operating passively. In this paper, we present a weapon detection system based on an ensemble of semantic Convolutional Neural Networks that decomposes the problem of detecting and locating a weapon into a set of smaller problems concerned with the individual component parts of a weapon. This approach has computational and practical advantages: a set of simpler neural networks dedicated to specific tasks requires less computational resources and can be trained in parallel; the overall output of the system given by the aggregation of the outputs of individual networks can be tuned by a user to trade-off false positives and false negatives; finally, according to ensemble theory, the output of the overall system will be robust and reliable even in the presence of weak individual models. We evaluated our system running simulations aimed at assessing the accuracy of individual networks and the whole system. The results on synthetic data and real-world data are promising, and they suggest that our approach may have advantages compared to the monolithic approach based on a single deep convolutional neural network.
Published 2020-02-11
URL https://arxiv.org/abs/2003.00805v1
PDF https://arxiv.org/pdf/2003.00805v1.pdf
PWC https://paperswithcode.com/paper/firearm-detection-and-segmentation-using-an

Towards Brain-Computer Interfaces for Drone Swarm Control

Title Towards Brain-Computer Interfaces for Drone Swarm Control
Authors Ji-Hoon Jeong, Dae-Hyeok Lee, Hyung-Ju Ahn, Seong-Whan Lee
Abstract Noninvasive brain-computer interface (BCI) decodes brain signals to understand user intention. Recent advances have been developed for the BCI-based drone control system as the demand for drone control increases. Especially, drone swarm control based on brain signals could provide various industries such as military service or industry disaster. This paper presents a prototype of a brain swarm interface system for a variety of scenarios using a visual imagery paradigm. We designed the experimental environment that could acquire brain signals under a drone swarm control simulator environment. Through the system, we collected the electroencephalogram (EEG) signals with respect to four different scenarios. Seven subjects participated in our experiment and evaluated classification performances using the basic machine learning algorithm. The grand average classification accuracy is higher than the chance level accuracy. Hence, we could confirm the feasibility of the drone swarm control system based on EEG signals for performing high-level tasks.
Tasks EEG
Published 2020-02-03
URL https://arxiv.org/abs/2002.00519v1
PDF https://arxiv.org/pdf/2002.00519v1.pdf
PWC https://paperswithcode.com/paper/towards-brain-computer-interfaces-for-drone

MA-DST: Multi-Attention Based Scalable Dialog State Tracking

Title MA-DST: Multi-Attention Based Scalable Dialog State Tracking
Authors Adarsh Kumar, Peter Ku, Anuj Kumar Goyal, Angeliki Metallinou, Dilek Hakkani-Tur
Abstract Task oriented dialog agents provide a natural language interface for users to complete their goal. Dialog State Tracking (DST), which is often a core component of these systems, tracks the system’s understanding of the user’s goal throughout the conversation. To enable accurate multi-domain DST, the model needs to encode dependencies between past utterances and slot semantics and understand the dialog context, including long-range cross-domain references. We introduce a novel architecture for this task to encode the conversation history and slot semantics more robustly by using attention mechanisms at multiple granularities. In particular, we use cross-attention to model relationships between the context and slots at different semantic levels and self-attention to resolve cross-domain coreferences. In addition, our proposed architecture does not rely on knowing the domain ontologies beforehand and can also be used in a zero-shot setting for new domains or unseen slot values. Our model improves the joint goal accuracy by 5% (absolute) in the full-data setting and by up to 2% (absolute) in the zero-shot setting over the present state-of-the-art on the MultiWoZ 2.1 dataset.
Published 2020-02-07
URL https://arxiv.org/abs/2002.08898v1
PDF https://arxiv.org/pdf/2002.08898v1.pdf
PWC https://paperswithcode.com/paper/ma-dst-multi-attention-based-scalable-dialog
comments powered by Disqus