Search Results for author:
Found 65 papers, 31 papers with code
SEN: A Novel Feature Normalization Dissimilarity Measure for Prototypical Few-Shot Learning Networks
In this paper, we equip Prototypical Networks (PNs) with a novel dissimilarity measure to enable discriminative feature normalization for few-shot learning.
Explaining time series models using frequency masking
Time series data is fundamentally important for describing many critical domains such as healthcare, finance, and climate, where explainable models are necessary for safe automated decision-making.
Generalized Cauchy-Schwarz Divergence and Its Deep Learning Applications
Divergence measures play a central role and become increasingly essential in deep learning, yet efficient measures for multiple (more than two) distributions are rarely explored.
Cauchy-Schwarz Divergence Information Bottleneck for Regression
The information bottleneck (IB) approach is popular to improve the generalization, robustness and explainability of deep neural networks.
View it like a radiologist: Shifted windows for deep learning augmentation of CT images
Our method outperforms classical intensity augmentations as well as the intensity augmentation pipeline of the popular nn-UNet on multiple datasets.
On the Effects of Self-supervision and Contrastive Alignment in Deep Multi-view Clustering
To address this, we present DeepMVC, a unified framework for deep MVC that includes many recent methods as instances.
Hubs and Hyperspheres: Reducing Hubness and Improving Transductive Few-shot Learning with Hyperspherical Embeddings
Distance-based classification is frequently used in transductive few-shot learning (FSL).
The Conditional Cauchy-Schwarz Divergence with Applications to Time-Series Data and Sequential Decision Making
The Cauchy-Schwarz (CS) divergence was developed by Pr\'{i}ncipe et al. in 2000.
ProtoVAE: A Trustworthy Self-Explainable Prototypical Variational Model
The need for interpretable models has fostered the development of self-explainable classifiers.
A clinically motivated self-supervised approach for content-based image retrieval of CT liver images
We address these limitations by (1) proposing a self-supervised learning framework that incorporates domain-knowledge into the training procedure and (2) providing the first representation learning explainability analysis in the context of CBIR of CT liver images.
Principle of Relevant Information for Graph Sparsification
Graph sparsification aims to reduce the number of edges of a graph while maintaining its structural properties.
The Kernelized Taylor Diagram
Our proposed kernelized Taylor diagram is capable of visualizing similarities between populations with minimal assumptions of the data distributions.
BrainIB: Interpretable Brain Network-based Psychiatric Diagnosis with Graph Information Bottleneck
Developing a new diagnostic models based on the underlying biological mechanisms rather than subjective symptoms for psychiatric disorders is an emerging consensus.
Mixing Up Contrastive Learning: Self-Supervised Representation Learning for Time Series
The lack of labeled data is a key challenge for learning useful representation from time series data.
Anomaly Detection-Inspired Few-Shot Medical Image Segmentation Through Self-Supervision With Supervoxels
Motivated by this, and the observation that the foreground class (e. g., one organ) is relatively homogeneous, we propose a novel anomaly detection-inspired approach to few-shot medical image segmentation in which we refrain from modeling the background explicitly.
Demonstrating The Risk of Imbalanced Datasets in Chest X-ray Image-based Diagnostics by Prototypical Relevance Propagation
The recent trend of integrating multi-source Chest X-Ray datasets to improve automated diagnostics raises concerns that models learn to exploit source-specific correlations to improve performance by recognizing the source domain of an image rather than the medical pathology.
RELAX: Representation Learning Explainability
Our approach can also model the uncertainty in its explanations, which is essential to produce trustworthy explanations.
Multi-modal land cover mapping of remote sensing images using pyramid attention and gated fusion networks
To this end, we propose a new multi-modality network (MultiModNet) for land cover mapping of multi-modal remote sensing data based on a novel pyramid attention fusion (PAF) module and a gated fusion unit (GFU).
Discriminative Multimodal Learning via Conditional Priors in Generative Models
Deep generative models with latent variables have been used lately to learn joint representations and generative processes from multi-modal data.
This looks more like that: Enhancing Self-Explaining Models by Prototypical Relevance Propagation
Current machine learning models have shown high efficiency in solving a wide variety of real-world problems.
On the Use of Time Series Kernel and Dimensionality Reduction to Identify the Acquisition of Antimicrobial Multidrug Resistance in the Intensive Care Unit
The acquisition of Antimicrobial Multidrug Resistance (AMR) in patients admitted to the Intensive Care Units (ICU) is a major global concern.
Reconsidering Representation Alignment for Multi-view Clustering
Aligning distributions of view representations is a core component of today's state of the art models for deep multi-view clustering.
Measuring Dependence with Matrix-based Entropy Functional
Measuring the dependence of data plays a central role in statistics and machine learning.
Joint Optimization of an Autoencoder for Clustering and Embedding
That simple neural network, referred to as the clustering module, can be integrated into a deep autoencoder resulting in a deep clustering model able to jointly learn a clustering and an embedding.
Uncertainty-Aware Deep Ensembles for Reliable and Explainable Predictions of Clinical Time Series
A measure of uncertainty in the relevance scores is computed by taking the standard deviation across the relevance scores produced by each model in the ensemble, which in turn is used to make the explanations more reliable.
SCG-Net: Self-Constructing Graph Neural Networks for Semantic Segmentation
Capturing global contextual representations by exploiting long-range pixel-pixel dependencies has shown to improve semantic segmentation performance.
Multi-view Self-Constructing Graph Convolutional Networks with Adaptive Class Weighting Loss for Semantic Segmentation
We propose a novel architecture called the Multi-view Self-Constructing Graph Convolutional Networks (MSCG-Net) for semantic segmentation.
The 1st Agriculture-Vision Challenge: Methods and Results
The first Agriculture-Vision Challenge aims to encourage research in developing novel and effective algorithms for agricultural pattern recognition from aerial images, especially for the semantic segmentation task associated with our challenge dataset.
Code-Aligned Autoencoders for Unsupervised Change Detection in Multimodal Remote Sensing Images
We propose to extract relational pixel information captured by domain-specific affinity matrices at the input and use this to enforce alignment of the code spaces and reduce the impact of change pixels on the learning objective.
Self-Constructing Graph Convolutional Networks for Semantic Labeling
Here, we propose a novel architecture called the Self-Constructing Graph (SCG), which makes use of learnable latent variables to generate embeddings and to self-construct the underlying graphs directly from the input features without relying on manually built prior knowledge graphs.
A Kernel to Exploit Informative Missingness in Multivariate Time Series from EHRs
A large fraction of the electronic health records (EHRs) consists of clinical measurements collected over time, such as lab tests and vital signs, which provide important information about a patient's health status.
Leveraging tensor kernels to reduce objective function mismatch in deep clustering
In this work we study OFM in deep clustering, and find that the popular autoencoder-based approach to deep clustering can lead to both reduced clustering performance, and a significant amount of OFM between the reconstruction and clustering objectives.
Deep Image Translation with an Affinity-Based Change Prior for Unsupervised Multimodal Change Detection
Image translation with convolutional neural networks has recently been used as an approach to multimodal change detection.
LS-Net: Fast Single-Shot Line-Segment Detector
In recent years, many vision-based techniques have been proposed to detect power lines to facilitate self-driving UAVs and automatic obstacle avoidance.
Information Plane Analysis of Deep Neural Networks via Matrix--Based Renyi's Entropy and Tensor Kernels
In this paper, we propose an IP analysis using the new matrix--based R\'enyi's entropy coupled with tensor kernels over convolutional layers, leveraging the power of kernel methods to represent properties of the probability distribution independently of the dimensionality of the data.
Information Plane Analysis of Deep Neural Networks via Matrix-Based Renyi's Entropy and Tensor Kernels
In this paper, we propose an IP analysis using the new matrix--based R\'enyi's entropy coupled with tensor kernels over convolutional layers, leveraging the power of kernel methods to represent properties of the probability distribution independently of the dimensionality of the data.
Road Mapping In LiDAR Images Using A Joint-Task Dense Dilated Convolutions Merging Network
This pushes the network towards learning more robust representations that are expected to boost the ultimate performance of the main task.
Dense Dilated Convolutions Merging Network for Semantic Mapping of Remote Sensing Images
We propose a network for semantic mapping called the Dense Dilated Convolutions Merging Network (DDCM-Net) to provide a deep learning approach that can recognize multi-scale and complex shaped objects with similar color and textures, such as buildings, surfaces/roads, and trees in very high resolution remote sensing images.
Time series cluster kernels to exploit informative missingness and incomplete label information
To overcome this limitation, we present a kernel capable of exploiting the potentially rich information in the missing values and patterns, as well as the information from the observed data.
Deep Generative Models for Reject Inference in Credit Scoring
Reject inference is the process of attempting to infer the creditworthiness status of the rejected applications.
Learning Latent Representations of Bank Customers With The Variational Autoencoder
We show that it is possible to steer the latent representations in the latent space of the VAE using the Weight of Evidence and forming a specific grouping of the data that reflects the customers' creditworthiness.
Noisy multi-label semi-supervised dimensionality reduction
With the proposed Noisy multi-label semi-supervised dimensionality reduction (NMLSDR) method, the noisy multi-labels are denoised and unlabeled data are labeled simultaneously via a specially designed label propagation algorithm.
Deep Divergence-Based Approach to Clustering
A promising direction in deep learning research consists in learning representations and simultaneously discovering cluster structure in unlabeled data by optimizing a discriminative loss function.
Recurrent Deep Divergence-based Clustering for simultaneous feature learning and clustering of variable length time series
The task of clustering unlabeled time series and sequences entails a particular set of challenges, namely to adequately model temporal relations and variable sequence lengths.
Multivariate Extension of Matrix-based Renyi's α-order Entropy Functional
The matrix-based Renyi's \alpha-order entropy functional was recently introduced using the normalized eigenspectrum of a Hermitian matrix of the projected data in a reproducing kernel Hilbert space (RKHS).
The Deep Kernelized Autoencoder
Autoencoders learn data representations (codes) in such a way that the input is reproduced at the output of the network.
Segment-Based Credit Scoring Using Latent Clusters in the Variational Autoencoder
We use the VAE and show that transforming the input data into a meaningful representation, it is possible to steer configurations in the latent space of the VAE.
Learning representations for multivariate time series with missing data using Temporal Kernelized Autoencoders
In this work, we propose a novel autoencoder architecture based on recurrent neural networks to generate compressed representations of MTS.
Understanding Convolutional Neural Networks with Information Theory: An Initial Exploration
The matrix-based Renyi's \alpha-entropy functional and its multivariate extension were recently developed in terms of the normalized eigenspectrum of a Hermitian matrix of the projected data in a reproducing kernel Hilbert space (RKHS).
Reservoir computing approaches for representation and classification of multivariate time series
The architectures are compared to other MTS classifiers, including deep learning models and time series kernels.
An Unsupervised Multivariate Time Series Kernel Approach for Identifying Patients with Surgical Site Infection from Blood Samples
A large fraction of the electronic health records consists of clinical measurements collected over time, such as blood tests, which provide important information about the health status of a patient.
Bidirectional deep-readout echo state networks
We propose a deep architecture for the classification of multivariate time series.
Classification of postoperative surgical site infections from blood measurements with missing data using recurrent neural networks
Clinical measurements that can be represented as time series constitute an important fraction of the electronic health records and are often both uncertain and incomplete.
Learning compressed representations of blood samples time series with missing data
Clinical measurements collected over time are naturally represented as multivariate time series (MTS), which often contain missing data.
Urban Land Cover Classification with Missing Data Modalities Using Deep Convolutional Neural Networks
Techniques to improve urban land cover classification performance in remote sensing include fusion of data from different sensors with different data modalities.
An overview and comparative analysis of Recurrent Neural Networks for Short Term Load Forecasting
Recently, new important families of recurrent architectures have emerged and their applicability in the context of load forecasting has not been investigated completely yet.
Time Series Cluster Kernel for Learning Similarities between Multivariate Time Series with Missing Data
An ensemble learning approach is exploited to ensure robustness to parameters by combining the clustering results of many GMM to form the final kernel.
Spectral Clustering using PCKID - A Probabilistic Cluster Kernel for Incomplete Data
In this paper, we propose PCKID, a novel, robust, kernel function for spectral clustering, specifically designed to handle incomplete data.
A clustering approach to heterogeneous change detection
Change detection in heterogeneous multitemporal satellite images is a challenging and still not much studied topic in remote sensing and earth observation.
Deep Kernelized Autoencoders
In this paper we introduce the deep kernelized autoencoder, a neural network model that allows an explicit approximation of (i) the mapping from an input space to an arbitrary, user-specified kernel space and (ii) the back-projection from such a kernel space to input space.
Temporal Overdrive Recurrent Neural Network
In this work we present a novel recurrent neural network architecture designed to model systems characterized by multiple characteristic timescales in their dynamics.
Multiplex visibility graphs to investigate recurrent neural networks dynamics
We show that topological properties of such a multiplex reflect important features of RNN dynamics and are used to guide the tuning procedure.
Training Echo State Networks with Regularization through Dimensionality Reduction
In this paper we introduce a new framework to train an Echo State Network to predict real valued time-series.
Manifold unwrapping using density ridges
Research on manifold learning within a density ridge estimation framework has shown great potential in recent work for both estimation and de-noising of manifolds, building on the intuitive and well-defined notion of principal curves and surfaces.
Optimized Kernel Entropy Components
Results show that 1) OKECA returns projections with more expressive power than KECA, 2) the most successful rule for estimating the kernel parameter is based on maximum likelihood, and 3) OKECA is more robust to the selection of the length-scale parameter in kernel density estimation.
