Paper Group ANR 385
Linear Regression with Shuffled Labels. “I know it when I see it”. Visualization and Intuitive Interpretability. Sliced Wasserstein Kernel for Persistence Diagrams. Normalized Total Gradient: A New Measure for Multispectral Image Registration. Employing Weak Annotations for Medical Image Analysis Problems. Disentangling group and link persistence i …
Linear Regression with Shuffled Labels
| Title | Linear Regression with Shuffled Labels |
| Authors | Abubakar Abid, Ada Poon, James Zou |
| Abstract | Is it possible to perform linear regression on datasets whose labels are shuffled with respect to the inputs? We explore this question by proposing several estimators that recover the weights of a noisy linear model from labels that are shuffled by an unknown permutation. We show that the analog of the classical least-squares estimator produces inconsistent estimates in this setting, and introduce an estimator based on the self-moments of the input features and labels. We study the regimes in which each estimator excels, and generalize the estimators to the setting where partial ordering information is available in the form of experiments replicated independently. The result is a framework that enables robust inference, as we demonstrate by experiments on both synthetic and standard datasets, where we are able to recover approximate weights using only shuffled labels. Our work demonstrates that linear regression in the absence of complete ordering information is possible and can be of practical interest, particularly in experiments that characterize populations of particles, such as flow cytometry. |
| Tasks | |
| Published | 2017-05-03 |
| URL | http://arxiv.org/abs/1705.01342v2 |
| http://arxiv.org/pdf/1705.01342v2.pdf | |
| PWC | https://paperswithcode.com/paper/linear-regression-with-shuffled-labels |
| Repo | |
| Framework | |
“I know it when I see it”. Visualization and Intuitive Interpretability
| Title | “I know it when I see it”. Visualization and Intuitive Interpretability |
| Authors | Fabian Offert |
| Abstract | Most research on the interpretability of machine learning systems focuses on the development of a more rigorous notion of interpretability. I suggest that a better understanding of the deficiencies of the intuitive notion of interpretability is needed as well. I show that visualization enables but also impedes intuitive interpretability, as it presupposes two levels of technical pre-interpretation: dimensionality reduction and regularization. Furthermore, I argue that the use of positive concepts to emulate the distributed semantic structure of machine learning models introduces a significant human bias into the model. As a consequence, I suggest that, if intuitive interpretability is needed, singular representations of internal model states should be avoided. |
| Tasks | Dimensionality Reduction |
| Published | 2017-11-20 |
| URL | http://arxiv.org/abs/1711.08042v2 |
| http://arxiv.org/pdf/1711.08042v2.pdf | |
| PWC | https://paperswithcode.com/paper/i-know-it-when-i-see-it-visualization-and |
| Repo | |
| Framework | |
Sliced Wasserstein Kernel for Persistence Diagrams
| Title | Sliced Wasserstein Kernel for Persistence Diagrams |
| Authors | Mathieu Carrière, Marco Cuturi, Steve Oudot |
| Abstract | Persistence diagrams (PDs) play a key role in topological data analysis (TDA), in which they are routinely used to describe topological properties of complicated shapes. PDs enjoy strong stability properties and have proven their utility in various learning contexts. They do not, however, live in a space naturally endowed with a Hilbert structure and are usually compared with specific distances, such as the bottleneck distance. To incorporate PDs in a learning pipeline, several kernels have been proposed for PDs with a strong emphasis on the stability of the RKHS distance w.r.t. perturbations of the PDs. In this article, we use the Sliced Wasserstein approximation SW of the Wasserstein distance to define a new kernel for PDs, which is not only provably stable but also provably discriminative (depending on the number of points in the PDs) w.r.t. the Wasserstein distance $d_1$ between PDs. We also demonstrate its practicality, by developing an approximation technique to reduce kernel computation time, and show that our proposal compares favorably to existing kernels for PDs on several benchmarks. |
| Tasks | Graph Classification, Topological Data Analysis |
| Published | 2017-06-11 |
| URL | http://arxiv.org/abs/1706.03358v3 |
| http://arxiv.org/pdf/1706.03358v3.pdf | |
| PWC | https://paperswithcode.com/paper/sliced-wasserstein-kernel-for-persistence |
| Repo | |
| Framework | |
Normalized Total Gradient: A New Measure for Multispectral Image Registration
| Title | Normalized Total Gradient: A New Measure for Multispectral Image Registration |
| Authors | Shu-Jie Chen, Hui-Liang Shen |
| Abstract | Image registration is a fundamental issue in multispectral image processing. In filter wheel based multispectral imaging systems, the non-coplanar placement of the filters always causes the misalignment of multiple channel images. The selective characteristic of spectral response in multispectral imaging raises two challenges to image registration. First, the intensity levels of a local region may be different in individual channel images. Second, the local intensity may vary rapidly in some channel images while keeps stationary in others. Conventional multimodal measures, such as mutual information, correlation coefficient, and correlation ratio, can register images with different regional intensity levels, but will fail in the circumstance of severe local intensity variation. In this paper, a new measure, namely normalized total gradient (NTG), is proposed for multispectral image registration. The NTG is applied on the difference between two channel images. This measure is based on the key assumption (observation) that the gradient of difference image between two aligned channel images is sparser than that between two misaligned ones. A registration framework, which incorporates image pyramid and global/local optimization, is further introduced for rigid transform. Experimental results validate that the proposed method is effective for multispectral image registration and performs better than conventional methods. |
| Tasks | Image Registration |
| Published | 2017-02-15 |
| URL | http://arxiv.org/abs/1702.04562v1 |
| http://arxiv.org/pdf/1702.04562v1.pdf | |
| PWC | https://paperswithcode.com/paper/normalized-total-gradient-a-new-measure-for |
| Repo | |
| Framework | |
Employing Weak Annotations for Medical Image Analysis Problems
| Title | Employing Weak Annotations for Medical Image Analysis Problems |
| Authors | Martin Rajchl, Lisa M. Koch, Christian Ledig, Jonathan Passerat-Palmbach, Kazunari Misawa, Kensaku Mori, Daniel Rueckert |
| Abstract | To efficiently establish training databases for machine learning methods, collaborative and crowdsourcing platforms have been investigated to collectively tackle the annotation effort. However, when this concept is ported to the medical imaging domain, reading expertise will have a direct impact on the annotation accuracy. In this study, we examine the impact of expertise and the amount of available annotations on the accuracy outcome of a liver segmentation problem in an abdominal computed tomography (CT) image database. In controlled experiments, we study this impact for different types of weak annotations. To address the decrease in accuracy associated with lower expertise, we propose a method for outlier correction making use of a weakly labelled atlas. Using this approach, we demonstrate that weak annotations subject to high error rates can achieve a similarly high accuracy as state-of-the-art multi-atlas segmentation approaches relying on a large amount of expert manual segmentations. Annotations of this nature can realistically be obtained from a non-expert crowd and can potentially enable crowdsourcing of weak annotation tasks for medical image analysis. |
| Tasks | Computed Tomography (CT), Liver Segmentation |
| Published | 2017-08-21 |
| URL | http://arxiv.org/abs/1708.06297v1 |
| http://arxiv.org/pdf/1708.06297v1.pdf | |
| PWC | https://paperswithcode.com/paper/employing-weak-annotations-for-medical-image |
| Repo | |
| Framework | |
Disentangling group and link persistence in Dynamic Stochastic Block models
| Title | Disentangling group and link persistence in Dynamic Stochastic Block models |
| Authors | Paolo Barucca, Fabrizio Lillo, Piero Mazzarisi, Daniele Tantari |
| Abstract | We study the inference of a model of dynamic networks in which both communities and links keep memory of previous network states. By considering maximum likelihood inference from single snapshot observations of the network, we show that link persistence makes the inference of communities harder, decreasing the detectability threshold, while community persistence tends to make it easier. We analytically show that communities inferred from single network snapshot can share a maximum overlap with the underlying communities of a specific previous instant in time. This leads to time-lagged inference: the identification of past communities rather than present ones. Finally we compute the time lag and propose a corrected algorithm, the Lagged Snapshot Dynamic (LSD) algorithm, for community detection in dynamic networks. We analytically and numerically characterize the detectability transitions of such algorithm as a function of the memory parameters of the model and we make a comparison with a full dynamic inference. |
| Tasks | Community Detection |
| Published | 2017-01-20 |
| URL | http://arxiv.org/abs/1701.05804v4 |
| http://arxiv.org/pdf/1701.05804v4.pdf | |
| PWC | https://paperswithcode.com/paper/disentangling-group-and-link-persistence-in |
| Repo | |
| Framework | |
Heavy-Tailed Analogues of the Covariance Matrix for ICA
| Title | Heavy-Tailed Analogues of the Covariance Matrix for ICA |
| Authors | Joseph Anderson, Navin Goyal, Anupama Nandi, Luis Rademacher |
| Abstract | Independent Component Analysis (ICA) is the problem of learning a square matrix $A$, given samples of $X=AS$, where $S$ is a random vector with independent coordinates. Most existing algorithms are provably efficient only when each $S_i$ has finite and moderately valued fourth moment. However, there are practical applications where this assumption need not be true, such as speech and finance. Algorithms have been proposed for heavy-tailed ICA, but they are not practical, using random walks and the full power of the ellipsoid algorithm multiple times. The main contributions of this paper are: (1) A practical algorithm for heavy-tailed ICA that we call HTICA. We provide theoretical guarantees and show that it outperforms other algorithms in some heavy-tailed regimes, both on real and synthetic data. Like the current state-of-the-art, the new algorithm is based on the centroid body (a first moment analogue of the covariance matrix). Unlike the state-of-the-art, our algorithm is practically efficient. To achieve this, we use explicit analytic representations of the centroid body, which bypasses the use of the ellipsoid method and random walks. (2) We study how heavy tails affect different ICA algorithms, including HTICA. Somewhat surprisingly, we show that some algorithms that use the covariance matrix or higher moments can successfully solve a range of ICA instances with infinite second moment. We study this theoretically and experimentally, with both synthetic and real-world heavy-tailed data. |
| Tasks | |
| Published | 2017-02-22 |
| URL | http://arxiv.org/abs/1702.06976v1 |
| http://arxiv.org/pdf/1702.06976v1.pdf | |
| PWC | https://paperswithcode.com/paper/heavy-tailed-analogues-of-the-covariance |
| Repo | |
| Framework | |
Sparse Autoencoder for Unsupervised Nucleus Detection and Representation in Histopathology Images
| Title | Sparse Autoencoder for Unsupervised Nucleus Detection and Representation in Histopathology Images |
| Authors | Le Hou, Vu Nguyen, Dimitris Samaras, Tahsin M. Kurc, Yi Gao, Tianhao Zhao, Joel H. Saltz |
| Abstract | Histopathology images are crucial to the study of complex diseases such as cancer. The histologic characteristics of nuclei play a key role in disease diagnosis, prognosis and analysis. In this work, we propose a sparse Convolutional Autoencoder (CAE) for fully unsupervised, simultaneous nucleus detection and feature extraction in histopathology tissue images. Our CAE detects and encodes nuclei in image patches in tissue images into sparse feature maps that encode both the location and appearance of nuclei. Our CAE is the first unsupervised detection network for computer vision applications. The pretrained nucleus detection and feature extraction modules in our CAE can be fine-tuned for supervised learning in an end-to-end fashion. We evaluate our method on four datasets and reduce the errors of state-of-the-art methods up to 42%. We are able to achieve comparable performance with only 5% of the fully-supervised annotation cost. |
| Tasks | |
| Published | 2017-04-03 |
| URL | http://arxiv.org/abs/1704.00406v2 |
| http://arxiv.org/pdf/1704.00406v2.pdf | |
| PWC | https://paperswithcode.com/paper/sparse-autoencoder-for-unsupervised-nucleus |
| Repo | |
| Framework | |
Multiview Deep Learning for Predicting Twitter Users’ Location
| Title | Multiview Deep Learning for Predicting Twitter Users’ Location |
| Authors | Tien Huu Do, Duc Minh Nguyen, Evaggelia Tsiligianni, Bruno Cornelis, Nikos Deligiannis |
| Abstract | The problem of predicting the location of users on large social networks like Twitter has emerged from real-life applications such as social unrest detection and online marketing. Twitter user geolocation is a difficult and active research topic with a vast literature. Most of the proposed methods follow either a content-based or a network-based approach. The former exploits user-generated content while the latter utilizes the connection or interaction between Twitter users. In this paper, we introduce a novel method combining the strength of both approaches. Concretely, we propose a multi-entry neural network architecture named MENET leveraging the advances in deep learning and multiview learning. The generalizability of MENET enables the integration of multiple data representations. In the context of Twitter user geolocation, we realize MENET with textual, network, and metadata features. Considering the natural distribution of Twitter users across the concerned geographical area, we subdivide the surface of the earth into multi-scale cells and train MENET with the labels of the cells. We show that our method outperforms the state of the art by a large margin on three benchmark datasets. |
| Tasks | Multiview Learning |
| Published | 2017-12-21 |
| URL | http://arxiv.org/abs/1712.08091v1 |
| http://arxiv.org/pdf/1712.08091v1.pdf | |
| PWC | https://paperswithcode.com/paper/multiview-deep-learning-for-predicting |
| Repo | |
| Framework | |
Dropping Convexity for More Efficient and Scalable Online Multiview Learning
| Title | Dropping Convexity for More Efficient and Scalable Online Multiview Learning |
| Authors | Zhehui Chen, Lin F. Yang, Chris J. Li, Tuo Zhao |
| Abstract | Multiview representation learning is very popular for latent factor analysis. It naturally arises in many data analysis, machine learning, and information retrieval applications to model dependent structures among multiple data sources. For computational convenience, existing approaches usually formulate the multiview representation learning as convex optimization problems, where global optima can be obtained by certain algorithms in polynomial time. However, many pieces of evidence have corroborated that heuristic nonconvex approaches also have good empirical computational performance and convergence to the global optima, although there is a lack of theoretical justification. Such a gap between theory and practice motivates us to study a nonconvex formulation for multiview representation learning, which can be efficiently solved by a simple stochastic gradient descent (SGD) algorithm. We first illustrate the geometry of the nonconvex formulation; Then, we establish asymptotic global rates of convergence to the global optima by diffusion approximations. Numerical experiments are provided to support our theory. |
| Tasks | Information Retrieval, Multiview Learning, Representation Learning |
| Published | 2017-02-27 |
| URL | http://arxiv.org/abs/1702.08134v9 |
| http://arxiv.org/pdf/1702.08134v9.pdf | |
| PWC | https://paperswithcode.com/paper/dropping-convexity-for-more-efficient-and |
| Repo | |
| Framework | |
A second order primal-dual method for nonsmooth convex composite optimization
| Title | A second order primal-dual method for nonsmooth convex composite optimization |
| Authors | Neil K. Dhingra, Sei Zhen Khong, Mihailo R. Jovanović |
| Abstract | We develop a second order primal-dual method for optimization problems in which the objective function is given by the sum of a strongly convex twice differentiable term and a possibly nondifferentiable convex regularizer. After introducing an auxiliary variable, we utilize the proximal operator of the nonsmooth regularizer to transform the associated augmented Lagrangian into a function that is once, but not twice, continuously differentiable. The saddle point of this function corresponds to the solution of the original optimization problem. We employ a generalization of the Hessian to define second order updates on this function and prove global exponential stability of the corresponding differential inclusion. Furthermore, we develop a globally convergent customized algorithm that utilizes the primal-dual augmented Lagrangian as a merit function. We show that the search direction can be computed efficiently and prove quadratic/superlinear asymptotic convergence. We use the $\ell_1$-regularized least squares problem and the problem of designing a distributed controller for a spatially-invariant system to demonstrate the merits and the effectiveness of our method. |
| Tasks | |
| Published | 2017-09-05 |
| URL | http://arxiv.org/abs/1709.01610v1 |
| http://arxiv.org/pdf/1709.01610v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-second-order-primal-dual-method-for |
| Repo | |
| Framework | |
A Bayesian Hyperprior Approach for Joint Image Denoising and Interpolation, with an Application to HDR Imaging
| Title | A Bayesian Hyperprior Approach for Joint Image Denoising and Interpolation, with an Application to HDR Imaging |
| Authors | Cecilia Aguerrebere, Andrés Almansa, Julie Delon, Yann Gousseau, Pablo Musé |
| Abstract | Recently, impressive denoising results have been achieved by Bayesian approaches which assume Gaussian models for the image patches. This improvement in performance can be attributed to the use of per-patch models. Unfortunately such an approach is particularly unstable for most inverse problems beyond denoising. In this work, we propose the use of a hyperprior to model image patches, in order to stabilize the estimation procedure. There are two main advantages to the proposed restoration scheme: Firstly it is adapted to diagonal degradation matrices, and in particular to missing data problems (e.g. inpainting of missing pixels or zooming). Secondly it can deal with signal dependent noise models, particularly suited to digital cameras. As such, the scheme is especially adapted to computational photography. In order to illustrate this point, we provide an application to high dynamic range imaging from a single image taken with a modified sensor, which shows the effectiveness of the proposed scheme. |
| Tasks | Denoising, Image Denoising |
| Published | 2017-06-10 |
| URL | http://arxiv.org/abs/1706.03261v1 |
| http://arxiv.org/pdf/1706.03261v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-bayesian-hyperprior-approach-for-joint |
| Repo | |
| Framework | |
Robust Intrinsic and Extrinsic Calibration of RGB-D Cameras
| Title | Robust Intrinsic and Extrinsic Calibration of RGB-D Cameras |
| Authors | Filippo Basso, Emanuele Menegatti, Alberto Pretto |
| Abstract | Color-depth cameras (RGB-D cameras) have become the primary sensors in most robotics systems, from service robotics to industrial robotics applications. Typical consumer-grade RGB-D cameras are provided with a coarse intrinsic and extrinsic calibration that generally does not meet the accuracy requirements needed by many robotics applications (e.g., highly accurate 3D environment reconstruction and mapping, high precision object recognition and localization, …). In this paper, we propose a human-friendly, reliable and accurate calibration framework that enables to easily estimate both the intrinsic and extrinsic parameters of a general color-depth sensor couple. Our approach is based on a novel two components error model. This model unifies the error sources of RGB-D pairs based on different technologies, such as structured-light 3D cameras and time-of-flight cameras. Our method provides some important advantages compared to other state-of-the-art systems: it is general (i.e., well suited for different types of sensors), based on an easy and stable calibration protocol, provides a greater calibration accuracy, and has been implemented within the ROS robotics framework. We report detailed experimental validations and performance comparisons to support our statements. |
| Tasks | Calibration, Object Recognition |
| Published | 2017-01-20 |
| URL | http://arxiv.org/abs/1701.05748v2 |
| http://arxiv.org/pdf/1701.05748v2.pdf | |
| PWC | https://paperswithcode.com/paper/robust-intrinsic-and-extrinsic-calibration-of |
| Repo | |
| Framework | |
Optimal Sub-sampling with Influence Functions
| Title | Optimal Sub-sampling with Influence Functions |
| Authors | Daniel Ting, Eric Brochu |
| Abstract | Sub-sampling is a common and often effective method to deal with the computational challenges of large datasets. However, for most statistical models, there is no well-motivated approach for drawing a non-uniform subsample. We show that the concept of an asymptotically linear estimator and the associated influence function leads to optimal sampling procedures for a wide class of popular models. Furthermore, for linear regression models which have well-studied procedures for non-uniform sub-sampling, we show our optimal influence function based method outperforms previous approaches. We empirically show the improved performance of our method on real datasets. |
| Tasks | |
| Published | 2017-09-06 |
| URL | http://arxiv.org/abs/1709.01716v1 |
| http://arxiv.org/pdf/1709.01716v1.pdf | |
| PWC | https://paperswithcode.com/paper/optimal-sub-sampling-with-influence-functions |
| Repo | |
| Framework | |
Visual and Textual Sentiment Analysis Using Deep Fusion Convolutional Neural Networks
| Title | Visual and Textual Sentiment Analysis Using Deep Fusion Convolutional Neural Networks |
| Authors | Xingyue Chen, Yunhong Wang, Qingjie Liu |
| Abstract | Sentiment analysis is attracting more and more attentions and has become a very hot research topic due to its potential applications in personalized recommendation, opinion mining, etc. Most of the existing methods are based on either textual or visual data and can not achieve satisfactory results, as it is very hard to extract sufficient information from only one single modality data. Inspired by the observation that there exists strong semantic correlation between visual and textual data in social medias, we propose an end-to-end deep fusion convolutional neural network to jointly learn textual and visual sentiment representations from training examples. The two modality information are fused together in a pooling layer and fed into fully-connected layers to predict the sentiment polarity. We evaluate the proposed approach on two widely used data sets. Results show that our method achieves promising result compared with the state-of-the-art methods which clearly demonstrate its competency. |
| Tasks | Opinion Mining, Sentiment Analysis |
| Published | 2017-11-21 |
| URL | http://arxiv.org/abs/1711.07798v1 |
| http://arxiv.org/pdf/1711.07798v1.pdf | |
| PWC | https://paperswithcode.com/paper/visual-and-textual-sentiment-analysis-using |
| Repo | |
| Framework | |
