Search Results for author:
Found 14 papers, 7 papers with code
Extracting a functional representation from a dictionary for non-rigid shape matching
Shape matching is a fundamental problem in computer graphics with many applications.
Multi-body Depth and Camera Pose Estimation from Multiple Views
Traditional and deep Structure-from-Motion (SfM) methods typically operate under the assumption that the scene is rigid, i. e., the environment is static or consists of a single moving object.
Class Distribution Monitoring for Concept Drift Detection
We introduce Class Distribution Monitoring (CDM), an effective concept-drift detection scheme that monitors the class-conditional distributions of a datastream.
Composite Layers for Deep Anomaly Detection on 3D Point Clouds
Moreover, our CompositeNets substantially outperform existing solutions for anomaly detection on point clouds.
Deep Open-Set Recognition for Silicon Wafer Production Monitoring
Here we address WDM monitoring as an open-set recognition problem to accurately classify WDM in known categories and promptly detect novel patterns.
Deep Autoencoders for Anomaly Detection in Textured Images using CW-SSIM
Detecting anomalous regions in images is a frequently encountered problem in industrial monitoring.
Nonparametric and Online Change Detection in Multivariate Datastreams using QuantTree
Like many change-detection algorithms, QT-EWMA builds a model of the data distribution, in our case a QuantTree histogram, from a stationary training set.
Perception Visualization: Seeing Through the Eyes of a DNN
Results of our user study demonstrate that humans can better understand and predict the system's decisions when perception visualizations are available, thus easing the debugging and deployment of deep models as trusted systems.
Adversarial Scratches: Deployable Attacks to CNN Classifiers
We present Adversarial Scratches: a novel L0 black-box attack, which takes the form of scratches in images, and which possesses much greater deployability than other state-of-the-art attacks.
MultiLink: Multi-Class Structure Recovery via Agglomerative Clustering and Model Selection
We address the problem of recovering multiple structures of different classes in a dataset contaminated by noise and outliers.
Synchronization of Group-Labelled Multi-Graphs
MultiSynch is a general solution that can cope with any linear group and we show to be profitably usable both on synthetic and real problems.
Scratch that! An Evolution-based Adversarial Attack against Neural Networks
We study black-box adversarial attacks for image classifiers in a constrained threat model, where adversaries can only modify a small fraction of pixels in the form of scratches on an image.
QuantTree: Histograms for Change Detection in Multivariate Data Streams
Our experiments show that the proposed histograms are very effective in detecting changes in high dimensional data streams, and that the resulting thresholds can effectively control the false positive rate, even when the number of training samples is relatively small.
Change Detection in Multivariate Datastreams: Likelihood and Detectability Loss
We address the problem of detecting changes in multivariate datastreams, and we investigate the intrinsic difficulty that change-detection methods have to face when the data dimension scales.
