Paper Group AWR 75
EMI: Exploration with Mutual Information. Hierarchical Methods of Moments. Classification from Pairwise Similarity and Unlabeled Data. A tutorial on Particle Swarm Optimization Clustering. Exploiting Unintended Feature Leakage in Collaborative Learning. Road Damage Detection And Classification In Smartphone Captured Images Using Mask R-CNN. Multimo …
EMI: Exploration with Mutual Information
| Title | EMI: Exploration with Mutual Information |
| Authors | Hyoungseok Kim, Jaekyeom Kim, Yeonwoo Jeong, Sergey Levine, Hyun Oh Song |
| Abstract | Reinforcement learning algorithms struggle when the reward signal is very sparse. In these cases, naive random exploration methods essentially rely on a random walk to stumble onto a rewarding state. Recent works utilize intrinsic motivation to guide the exploration via generative models, predictive forward models, or discriminative modeling of novelty. We propose EMI, which is an exploration method that constructs embedding representation of states and actions that does not rely on generative decoding of the full observation but extracts predictive signals that can be used to guide exploration based on forward prediction in the representation space. Our experiments show competitive results on challenging locomotion tasks with continuous control and on image-based exploration tasks with discrete actions on Atari. The source code is available at https://github.com/snu-mllab/EMI . |
| Tasks | Continuous Control |
| Published | 2018-10-02 |
| URL | https://arxiv.org/abs/1810.01176v6 |
| https://arxiv.org/pdf/1810.01176v6.pdf | |
| PWC | https://paperswithcode.com/paper/emi-exploration-with-mutual-information |
| Repo | https://github.com/snu-mllab/EMI |
| Framework | none |
Hierarchical Methods of Moments
| Title | Hierarchical Methods of Moments |
| Authors | Matteo Ruffini, Guillaume Rabusseau, Borja Balle |
| Abstract | Spectral methods of moments provide a powerful tool for learning the parameters of latent variable models. Despite their theoretical appeal, the applicability of these methods to real data is still limited due to a lack of robustness to model misspecification. In this paper we present a hierarchical approach to methods of moments to circumvent such limitations. Our method is based on replacing the tensor decomposition step used in previous algorithms with approximate joint diagonalization. Experiments on topic modeling show that our method outperforms previous tensor decomposition methods in terms of speed and model quality. |
| Tasks | Latent Variable Models |
| Published | 2018-10-17 |
| URL | http://arxiv.org/abs/1810.07468v1 |
| http://arxiv.org/pdf/1810.07468v1.pdf | |
| PWC | https://paperswithcode.com/paper/hierarchical-methods-of-moments |
| Repo | https://github.com/mruffini/Hierarchical-Methods-of-Moments |
| Framework | none |
Classification from Pairwise Similarity and Unlabeled Data
| Title | Classification from Pairwise Similarity and Unlabeled Data |
| Authors | Han Bao, Gang Niu, Masashi Sugiyama |
| Abstract | Supervised learning needs a huge amount of labeled data, which can be a big bottleneck under the situation where there is a privacy concern or labeling cost is high. To overcome this problem, we propose a new weakly-supervised learning setting where only similar (S) data pairs (two examples belong to the same class) and unlabeled (U) data points are needed instead of fully labeled data, which is called SU classification. We show that an unbiased estimator of the classification risk can be obtained only from SU data, and the estimation error of its empirical risk minimizer achieves the optimal parametric convergence rate. Finally, we demonstrate the effectiveness of the proposed method through experiments. |
| Tasks | |
| Published | 2018-02-12 |
| URL | http://arxiv.org/abs/1802.04381v3 |
| http://arxiv.org/pdf/1802.04381v3.pdf | |
| PWC | https://paperswithcode.com/paper/classification-from-pairwise-similarity-and |
| Repo | https://github.com/srishtis/SU_classification_study |
| Framework | none |
A tutorial on Particle Swarm Optimization Clustering
| Title | A tutorial on Particle Swarm Optimization Clustering |
| Authors | Augusto Luis Ballardini |
| Abstract | This paper proposes a tutorial on the Data Clustering technique using the Particle Swarm Optimization approach. Following the work proposed by Merwe et al. here we present an in-deep analysis of the algorithm together with a Matlab implementation and a short tutorial that explains how to modify the proposed implementation and the effect of the parameters of the original algorithm. Moreover, we provide a comparison against the results obtained using the well known K-Means approach. All the source code presented in this paper is publicly available under the GPL-v2 license. |
| Tasks | |
| Published | 2018-09-06 |
| URL | http://arxiv.org/abs/1809.01942v1 |
| http://arxiv.org/pdf/1809.01942v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-tutorial-on-particle-swarm-optimization |
| Repo | https://github.com/iralabdisco/pso-clustering |
| Framework | none |
Exploiting Unintended Feature Leakage in Collaborative Learning
| Title | Exploiting Unintended Feature Leakage in Collaborative Learning |
| Authors | Luca Melis, Congzheng Song, Emiliano De Cristofaro, Vitaly Shmatikov |
| Abstract | Collaborative machine learning and related techniques such as federated learning allow multiple participants, each with his own training dataset, to build a joint model by training locally and periodically exchanging model updates. We demonstrate that these updates leak unintended information about participants’ training data and develop passive and active inference attacks to exploit this leakage. First, we show that an adversarial participant can infer the presence of exact data points – for example, specific locations – in others’ training data (i.e., membership inference). Then, we show how this adversary can infer properties that hold only for a subset of the training data and are independent of the properties that the joint model aims to capture. For example, he can infer when a specific person first appears in the photos used to train a binary gender classifier. We evaluate our attacks on a variety of tasks, datasets, and learning configurations, analyze their limitations, and discuss possible defenses. |
| Tasks | |
| Published | 2018-05-10 |
| URL | http://arxiv.org/abs/1805.04049v3 |
| http://arxiv.org/pdf/1805.04049v3.pdf | |
| PWC | https://paperswithcode.com/paper/exploiting-unintended-feature-leakage-in |
| Repo | https://github.com/csong27/property-inference-collaborative-ml |
| Framework | none |
Road Damage Detection And Classification In Smartphone Captured Images Using Mask R-CNN
| Title | Road Damage Detection And Classification In Smartphone Captured Images Using Mask R-CNN |
| Authors | Janpreet Singh, Shashank Shekhar |
| Abstract | This paper summarizes the design, experiments and results of our solution to the Road Damage Detection and Classification Challenge held as part of the 2018 IEEE International Conference On Big Data Cup. Automatic detection and classification of damage in roads is an essential problem for multiple applications like maintenance and autonomous driving. We demonstrate that convolutional neural net based instance detection and classfication approaches can be used to solve this problem. In particular we show that Mask-RCNN, one of the state-of-the-art algorithms for object detection, localization and instance segmentation of natural images, can be used to perform this task in a fast manner with effective results. We achieve a mean F1 score of 0.528 at an IoU of 50% on the task of detection and classification of different types of damages in real-world road images acquired using a smartphone camera and our average inference time for each image is 0.105 seconds on an NVIDIA GeForce 1080Ti graphic card. The code and saved models for our approach can be found here : https://github.com/sshkhr/BigDataCup18 Submission |
| Tasks | Autonomous Driving, Instance Segmentation, Object Detection, Road Damage Detection, Semantic Segmentation |
| Published | 2018-11-12 |
| URL | http://arxiv.org/abs/1811.04535v1 |
| http://arxiv.org/pdf/1811.04535v1.pdf | |
| PWC | https://paperswithcode.com/paper/road-damage-detection-and-classification-in |
| Repo | https://github.com/sshkhr/BigDataCup18_Submission |
| Framework | none |
Multimodal Sentiment Analysis with Word-Level Fusion and Reinforcement Learning
| Title | Multimodal Sentiment Analysis with Word-Level Fusion and Reinforcement Learning |
| Authors | Minghai Chen, Sen Wang, Paul Pu Liang, Tadas Baltrušaitis, Amir Zadeh, Louis-Philippe Morency |
| Abstract | With the increasing popularity of video sharing websites such as YouTube and Facebook, multimodal sentiment analysis has received increasing attention from the scientific community. Contrary to previous works in multimodal sentiment analysis which focus on holistic information in speech segments such as bag of words representations and average facial expression intensity, we develop a novel deep architecture for multimodal sentiment analysis that performs modality fusion at the word level. In this paper, we propose the Gated Multimodal Embedding LSTM with Temporal Attention (GME-LSTM(A)) model that is composed of 2 modules. The Gated Multimodal Embedding alleviates the difficulties of fusion when there are noisy modalities. The LSTM with Temporal Attention performs word level fusion at a finer fusion resolution between input modalities and attends to the most important time steps. As a result, the GME-LSTM(A) is able to better model the multimodal structure of speech through time and perform better sentiment comprehension. We demonstrate the effectiveness of this approach on the publicly-available Multimodal Corpus of Sentiment Intensity and Subjectivity Analysis (CMU-MOSI) dataset by achieving state-of-the-art sentiment classification and regression results. Qualitative analysis on our model emphasizes the importance of the Temporal Attention Layer in sentiment prediction because the additional acoustic and visual modalities are noisy. We also demonstrate the effectiveness of the Gated Multimodal Embedding in selectively filtering these noisy modalities out. Our results and analysis open new areas in the study of sentiment analysis in human communication and provide new models for multimodal fusion. |
| Tasks | Multimodal Sentiment Analysis, Sentiment Analysis, Subjectivity Analysis |
| Published | 2018-02-03 |
| URL | http://arxiv.org/abs/1802.00924v1 |
| http://arxiv.org/pdf/1802.00924v1.pdf | |
| PWC | https://paperswithcode.com/paper/multimodal-sentiment-analysis-with-word-level |
| Repo | https://github.com/pliang279/MFN |
| Framework | pytorch |
Comprehensive Supersense Disambiguation of English Prepositions and Possessives
| Title | Comprehensive Supersense Disambiguation of English Prepositions and Possessives |
| Authors | Nathan Schneider, Jena D. Hwang, Vivek Srikumar, Jakob Prange, Austin Blodgett, Sarah R. Moeller, Aviram Stern, Adi Bitan, Omri Abend |
| Abstract | Semantic relations are often signaled with prepositional or possessive marking–but extreme polysemy bedevils their analysis and automatic interpretation. We introduce a new annotation scheme, corpus, and task for the disambiguation of prepositions and possessives in English. Unlike previous approaches, our annotations are comprehensive with respect to types and tokens of these markers; use broadly applicable supersense classes rather than fine-grained dictionary definitions; unite prepositions and possessives under the same class inventory; and distinguish between a marker’s lexical contribution and the role it marks in the context of a predicate or scene. Strong interannotator agreement rates, as well as encouraging disambiguation results with established supervised methods, speak to the viability of the scheme and task. |
| Tasks | |
| Published | 2018-05-13 |
| URL | http://arxiv.org/abs/1805.04905v1 |
| http://arxiv.org/pdf/1805.04905v1.pdf | |
| PWC | https://paperswithcode.com/paper/comprehensive-supersense-disambiguation-of |
| Repo | https://github.com/nert-gu/streusle |
| Framework | none |
Hyperspectral Image Dataset for Benchmarking on Salient Object Detection
| Title | Hyperspectral Image Dataset for Benchmarking on Salient Object Detection |
| Authors | Nevrez Imamoglu, Yu Oishi, Xiaoqiang Zhang, Guanqun Ding, Yuming Fang, Toru Kouyama, Ryosuke Nakamura |
| Abstract | Many works have been done on salient object detection using supervised or unsupervised approaches on colour images. Recently, a few studies demonstrated that efficient salient object detection can also be implemented by using spectral features in visible spectrum of hyperspectral images from natural scenes. However, these models on hyperspectral salient object detection were tested with a very few number of data selected from various online public dataset, which are not specifically created for object detection purposes. Therefore, here, we aim to contribute to the field by releasing a hyperspectral salient object detection dataset with a collection of 60 hyperspectral images with their respective ground-truth binary images and representative rendered colour images (sRGB). We took several aspects in consideration during the data collection such as variation in object size, number of objects, foreground-background contrast, object position on the image, and etc. Then, we prepared ground truth binary images for each hyperspectral data, where salient objects are labelled on the images. Finally, we did performance evaluation using Area Under Curve (AUC) metric on some existing hyperspectral saliency detection models in literature. |
| Tasks | Object Detection, Saliency Detection, Salient Object Detection |
| Published | 2018-06-29 |
| URL | http://arxiv.org/abs/1806.11314v2 |
| http://arxiv.org/pdf/1806.11314v2.pdf | |
| PWC | https://paperswithcode.com/paper/hyperspectral-image-dataset-for-benchmarking |
| Repo | https://github.com/gistairc/HS-SOD |
| Framework | none |
Nonparametric Quantile-Based Causal Discovery
| Title | Nonparametric Quantile-Based Causal Discovery |
| Authors | Natasa Tagasovska, Thibault Vatter, Valérie Chavez-Demoulin |
| Abstract | Distinguishing cause from effect using observational data is a challenging problem, especially in the bivariate case. Contemporary methods often assume an independence between the cause and the generating mechanism of the effect given the cause. From this postulate, they derive asymmetries to uncover causal relationships. Leveraging the same postulate, in this work, we propose a novel approach based on the link between Kolmogorov complexity and quantile scoring. We use a nonparametric conditional quantile estimator based on copulas to implement our procedure, thus avoiding restrictive assumptions about the joint distribution between cause and effect. In an extensive study on real and synthetic data, we show that quantile copula causal discovery (QCCD) compares favorably to state-of-the-art methods. |
| Tasks | Causal Discovery |
| Published | 2018-01-31 |
| URL | http://arxiv.org/abs/1801.10579v2 |
| http://arxiv.org/pdf/1801.10579v2.pdf | |
| PWC | https://paperswithcode.com/paper/nonparametric-quantile-based-causal-discovery |
| Repo | https://github.com/tagas/qccd |
| Framework | none |
Multi-Modal Emotion recognition on IEMOCAP Dataset using Deep Learning
| Title | Multi-Modal Emotion recognition on IEMOCAP Dataset using Deep Learning |
| Authors | Samarth Tripathi, Sarthak Tripathi, Homayoon Beigi |
| Abstract | Emotion recognition has become an important field of research in Human Computer Interactions as we improve upon the techniques for modelling the various aspects of behaviour. With the advancement of technology our understanding of emotions are advancing, there is a growing need for automatic emotion recognition systems. One of the directions the research is heading is the use of Neural Networks which are adept at estimating complex functions that depend on a large number and diverse source of input data. In this paper we attempt to exploit this effectiveness of Neural networks to enable us to perform multimodal Emotion recognition on IEMOCAP dataset using data from Speech, Text, and Motion capture data from face expressions, rotation and hand movements. Prior research has concentrated on Emotion detection from Speech on the IEMOCAP dataset, but our approach is the first that uses the multiple modes of data offered by IEMOCAP for a more robust and accurate emotion detection. |
| Tasks | Emotion Recognition, Motion Capture, Multimodal Emotion Recognition |
| Published | 2018-04-16 |
| URL | https://arxiv.org/abs/1804.05788v3 |
| https://arxiv.org/pdf/1804.05788v3.pdf | |
| PWC | https://paperswithcode.com/paper/multi-modal-emotion-recognition-on-iemocap |
| Repo | https://github.com/Samarth-Tripathi/IEMOCAP-Emotion-Detection |
| Framework | none |
Matchable Image Retrieval by Learning from Surface Reconstruction
| Title | Matchable Image Retrieval by Learning from Surface Reconstruction |
| Authors | Tianwei Shen, Zixin Luo, Lei Zhou, Runze Zhang, Siyu Zhu, Tian Fang, Long Quan |
| Abstract | Convolutional Neural Networks (CNNs) have achieved superior performance on object image retrieval, while Bag-of-Words (BoW) models with handcrafted local features still dominate the retrieval of overlapping images in 3D reconstruction. In this paper, we narrow down this gap by presenting an efficient CNN-based method to retrieve images with overlaps, which we refer to as the matchable image retrieval problem. Different from previous methods that generates training data based on sparse reconstruction, we create a large-scale image database with rich 3D geometrics and exploit information from surface reconstruction to obtain fine-grained training data. We propose a batched triplet-based loss function combined with mesh re-projection to effectively learn the CNN representation. The proposed method significantly accelerates the image retrieval process in 3D reconstruction and outperforms the state-of-the-art CNN-based and BoW methods for matchable image retrieval. The code and data are available at https://github.com/hlzz/mirror. |
| Tasks | 3D Reconstruction, Image Retrieval |
| Published | 2018-11-26 |
| URL | http://arxiv.org/abs/1811.10343v2 |
| http://arxiv.org/pdf/1811.10343v2.pdf | |
| PWC | https://paperswithcode.com/paper/matchable-image-retrieval-by-learning-from |
| Repo | https://github.com/hlzz/mirror |
| Framework | tf |
Improving Shape Deformation in Unsupervised Image-to-Image Translation
| Title | Improving Shape Deformation in Unsupervised Image-to-Image Translation |
| Authors | Aaron Gokaslan, Vivek Ramanujan, Daniel Ritchie, Kwang In Kim, James Tompkin |
| Abstract | Unsupervised image-to-image translation techniques are able to map local texture between two domains, but they are typically unsuccessful when the domains require larger shape change. Inspired by semantic segmentation, we introduce a discriminator with dilated convolutions that is able to use information from across the entire image to train a more context-aware generator. This is coupled with a multi-scale perceptual loss that is better able to represent error in the underlying shape of objects. We demonstrate that this design is more capable of representing shape deformation in a challenging toy dataset, plus in complex mappings with significant dataset variation between humans, dolls, and anime faces, and between cats and dogs. |
| Tasks | Image-to-Image Translation, Semantic Segmentation, Unsupervised Image-To-Image Translation |
| Published | 2018-08-13 |
| URL | http://arxiv.org/abs/1808.04325v2 |
| http://arxiv.org/pdf/1808.04325v2.pdf | |
| PWC | https://paperswithcode.com/paper/improving-shape-deformation-in-unsupervised |
| Repo | https://github.com/Funaizhang/dics |
| Framework | none |
Elastic Neural Networks for Classification
| Title | Elastic Neural Networks for Classification |
| Authors | Yi Zhou, Yue Bai, Shuvra S. Bhattacharyya, Heikki Huttunen |
| Abstract | In this work we propose a framework for improving the performance of any deep neural network that may suffer from vanishing gradients. To address the vanishing gradient issue, we study a framework, where we insert an intermediate output branch after each layer in the computational graph and use the corresponding prediction loss for feeding the gradient to the early layers. The framework - which we name Elastic network - is tested with several well-known networks on CIFAR10 and CIFAR100 datasets, and the experimental results show that the proposed framework improves the accuracy on both shallow networks (e.g., MobileNet) and deep convolutional neural networks (e.g., DenseNet). We also identify the types of networks where the framework does not improve the performance and discuss the reasons. Finally, as a side product, the computational complexity of the resulting networks can be adjusted in an elastic manner by selecting the output branch according to current computational budget. |
| Tasks | |
| Published | 2018-10-01 |
| URL | https://arxiv.org/abs/1810.00589v4 |
| https://arxiv.org/pdf/1810.00589v4.pdf | |
| PWC | https://paperswithcode.com/paper/elastic-neural-networks-for-classification |
| Repo | https://github.com/yipersevere/elastic-neural-networks-for-classification |
| Framework | pytorch |
Multiscale Fisher’s Independence Test for Multivariate Dependence
| Title | Multiscale Fisher’s Independence Test for Multivariate Dependence |
| Authors | Shai Gorsky, Li Ma |
| Abstract | Identifying dependency in multivariate data is a common inference task that arises in numerous applications. However, existing nonparametric independence tests typically require computation that scales at least quadratically with the sample size, making it difficult to apply them to massive data. Moreover, resampling is usually necessary to evaluate the statistical significance of the resulting test statistics at finite sample sizes, further worsening the computational burden. We introduce a scalable, resampling-free approach to testing the independence between two random vectors by breaking down the task into simple univariate tests of independence on a collection of 2x2 contingency tables constructed through sequential coarse-to-fine discretization of the sample space, transforming the inference task into a multiple testing problem that can be completed with almost linear complexity with respect to the sample size. To address increasing dimensionality, we introduce a coarse-to-fine sequential adaptive procedure that exploits the spatial features of dependency structures to more effectively examine the sample space. We derive a finite-sample theory that guarantees the inferential validity of our adaptive procedure at any given sample size. In particular, we show that our approach can achieve strong control of the family-wise error rate without resampling or large-sample approximation. We demonstrate the substantial computational advantage of the procedure in comparison to existing approaches as well as its decent statistical power under various dependency scenarios through an extensive simulation study, and illustrate how the divide-and-conquer nature of the procedure can be exploited to not just test independence but to learn the nature of the underlying dependency. Finally, we demonstrate the use of our method through analyzing a large data set from a flow cytometry experiment. |
| Tasks | |
| Published | 2018-06-18 |
| URL | https://arxiv.org/abs/1806.06777v6 |
| https://arxiv.org/pdf/1806.06777v6.pdf | |
| PWC | https://paperswithcode.com/paper/multifit-a-multivariate-multiscale-framework |
| Repo | https://github.com/MaStatLab/multiFit |
| Framework | none |
