
-
Interpretable and Fine-Grained Visual Explanations for Convolutional Neural Networks
To verify and validate networks, it is essential to gain insight into th...
read it
-
On-manifold Adversarial Data Augmentation Improves Uncertainty Calibration
Uncertainty estimates help to identify ambiguous, novel, or anomalous in...
read it
-
An Evaluation of Knowledge Graph Embeddings for Autonomous Driving Data: Experience and Practice
The autonomous driving (AD) industry is exploring the use of knowledge g...
read it
-
Defending against Universal Perturbations with Shared Adversarial Training
Classifiers such as deep neural networks have been shown to be vulnerabl...
read it
-
When are Neural ODE Solutions Proper ODEs?
A key appeal of the recently proposed Neural Ordinary Differential Equat...
read it
-
Unifying Model Explainability and Robustness via Machine-Checkable Concepts
As deep neural networks (DNNs) get adopted in an ever-increasing number ...
read it
-
Grid Saliency for Context Explanations of Semantic Segmentation
Recently, there has been a growing interest in developing saliency metho...
read it
-
Short-Term Prediction and Multi-Camera Fusion on Semantic Grids
An environment representation (ER) is a substantial part of every autono...
read it
-
The Functional Neural Process
We present a new family of exchangeable stochastic processes, the Functi...
read it
-
Wasserstein Adversarial Imitation Learning
Imitation Learning describes the problem of recovering an expert policy ...
read it
-
Mono-SF: Multi-View Geometry Meets Single-View Depth for Monocular Scene Flow Estimation of Dynamic Traffic Scenes
Existing 3D scene flow estimation methods provide the 3D geometry and 3D...
read it
-
Deep Multiple Instance Feature Learning via Variational Autoencoder
We describe a novel weakly supervised deep learning framework that combi...
read it
-
SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks
We introduce the SE(3)-Transformer, a variant of the self-attention modu...
read it
-
Compression for Smooth Shape Analysis
Most 3D shape analysis methods use triangular meshes to discretize both ...
read it
-
Simple And Efficient Architecture Search for Convolutional Neural Networks
Neural networks have recently had a lot of success for many tasks. Howev...
read it
-
Prediction Scores as a Window into Classifier Behavior
Most multi-class classifiers make their prediction for a test sample by ...
read it
-
Universal Adversarial Perturbations Against Semantic Image Segmentation
While deep learning is remarkably successful on perceptual tasks, it was...
read it
-
Adversarial Examples for Semantic Image Segmentation
Machine learning methods in general and Deep Neural Networks in particul...
read it
-
Efficient Stochastic Inference of Bitwise Deep Neural Networks
Recently published methods enable training of bitwise neural networks wh...
read it
-
Do Convolutional Neural Networks Learn Class Hierarchy?
Convolutional Neural Networks (CNNs) currently achieve state-of-the-art ...
read it
-
Very Deep Convolutional Neural Networks for Raw Waveforms
Learning acoustic models directly from the raw waveform data with minima...
read it
-
Concept Drift Detection and Adaptation with Hierarchical Hypothesis Testing
In a streaming environment, there is often a need for statistical predic...
read it
-
Efficient Approximate Solutions to Mutual Information Based Global Feature Selection
Mutual Information (MI) is often used for feature selection when develop...
read it
-
Learning Filter Banks Using Deep Learning For Acoustic Signals
Designing appropriate features for acoustic event recognition tasks is a...
read it
-
Weakly-supervised localization of diabetic retinopathy lesions in retinal fundus images
Convolutional neural networks (CNNs) show impressive performance for ima...
read it
-
Coupled Support Vector Machines for Supervised Domain Adaptation
Popular domain adaptation (DA) techniques learn a classifier for the tar...
read it
-
Model-Based Policy Search for Automatic Tuning of Multivariate PID Controllers
PID control architectures are widely used in industrial applications. De...
read it
-
Directional Decision Lists
In this paper we introduce a novel family of decision lists consisting o...
read it
-
Concept Drift Detection for Streaming Data
Common statistical prediction models often require and assume stationari...
read it
-
Multimodal Task-Driven Dictionary Learning for Image Classification
Dictionary learning algorithms have been successfully used for both reco...
read it
-
Detecting Table Region in PDF Documents Using Distant Supervision
Superior to state-of-the-art approaches which compete in table recogniti...
read it
-
Multiple Instance Deep Learning for Weakly Supervised Audio Event Detection
State-of-the-art audio event detection (AED) systems rely on supervised ...
read it
-
Model Order Reduction for Rotating Electrical Machines
The simulation of electric rotating machines is both computationally exp...
read it
-
Effective Building Block Design for Deep Convolutional Neural Networks using Search
Deep learning has shown promising results on many machine learning tasks...
read it
-
Multiple Instance Deep Learning for Weakly Supervised Small-Footprint Audio Event Detection
State-of-the-art audio event detection (AED) systems rely on supervised ...
read it
-
Building robust prediction models for defective sensor data using Artificial Neural Networks
Predicting the health of components in complex dynamic systems such as a...
read it
-
Communication channels in safety analysis: An industrial exploratory case study
Safety analysis is a predominant activity in developing safety-critical ...
read it
-
Simplified SPARQL REST API - CRUD on JSON Object Graphs via URI Paths
Within the Semantic Web community, SPARQL is one of the predominant lang...
read it
-
Scaling provable adversarial defenses
Recent work has developed methods for learning deep network classifiers ...
read it
-
Evidential Deep Learning to Quantify Classification Uncertainty
Deterministic neural nets have been shown to learn effective predictors ...
read it
-
Learning Front-end Filter-bank Parameters using Convolutional Neural Networks for Abnormal Heart Sound Detection
Automatic heart sound abnormality detection can play a vital role in the...
read it
-
An Ensemble of Transfer, Semi-supervised and Supervised Learning Methods for Pathological Heart Sound Classification
In this work, we propose an ensemble of classifiers to distinguish betwe...
read it
-
Neural Semi-Markov Conditional Random Fields for Robust Character-Based Part-of-Speech Tagging
Character-level models of tokens have been shown to be effective at deal...
read it
-
Neural Architecture Search: A Survey
Deep Learning has enabled remarkable progress over the last years on a v...
read it
-
A Trio Neural Model for Dynamic Entity Relatedness Ranking
Measuring entity relatedness is a fundamental task for many natural lang...
read it
-
How Robust is 3D Human Pose Estimation to Occlusion?
Occlusion is commonplace in realistic human-robot shared environments, y...
read it
-
Synthetic Occlusion Augmentation with Volumetric Heatmaps for the 2018 ECCV PoseTrack Challenge on 3D Human Pose Estimation
In this paper we present our winning entry at the 2018 ECCV PoseTrack Ch...
read it
-
A 5G Architecture for The Factory of the Future
Factory automation and production are currently undergoing massive chang...
read it
-
Probing Attacks on Physical Layer Key Agreement for Automotive Controller Area Networks (Extended Version)
Efficient key management for automotive networks (CAN) is a critical ele...
read it
-
Learning Gaussian Processes by Minimizing PAC-Bayesian Generalization Bounds
Gaussian Processes (GPs) are a generic modelling tool for supervised lea...
read it