1‐Lipschitz Neural Distance Fields
G Coiffier, L Béthune - Computer Graphics Forum, 2024 - Wiley Online Library
Neural implicit surfaces are a promising tool for geometry processing that represent a solid
object as the zero level set of a neural network. Usually trained to approximate a signed …
object as the zero level set of a neural network. Usually trained to approximate a signed …
[HTML][HTML] Memoryless Multimodal Anomaly Detection via Student–Teacher Network and Signed Distance Learning
Z Sun, X Li, Y Li, Y Ma - Electronics, 2024 - mdpi.com
Unsupervised anomaly detection is a challenging computer vision task, in which 2D-based
anomaly detection methods have been extensively studied. However, multimodal anomaly …
anomaly detection methods have been extensively studied. However, multimodal anomaly …
DP-SGD with weight clipping
A Barczewski, J Ramon - arXiv preprint arXiv:2310.18001, 2023 - arxiv.org
Recently, due to the popularity of deep neural networks and other methods whose training
typically relies on the optimization of an objective function, and due to concerns for data …
typically relies on the optimization of an objective function, and due to concerns for data …
Killing It With Zero-Shot: Adversarially Robust Novelty Detection
Novelty Detection (ND) plays a crucial role in machine learning by identifying new or unseen
data during model inference. This capability is especially important for the safe and reliable …
data during model inference. This capability is especially important for the safe and reliable …
RODEO: Robust Outlier Detection via Exposing Adaptive Out-of-Distribution Samples
In recent years, there have been significant improvements in various forms of image outlier
detection. However, outlier detection performance under adversarial settings lags far behind …
detection. However, outlier detection performance under adversarial settings lags far behind …
Deep learning with Lipschitz constraints
L Béthune - 2024 - theses.hal.science
This thesis explores the characteristics and applications of Lipschitz networks in machine
learning tasks. First, the framework of" optimization as a layer" is presented, showcasing …
learning tasks. First, the framework of" optimization as a layer" is presented, showcasing …
Revisiting the Static Model in Robust Reinforcement Learning
Designing control policies whose performance level is guaranteed to remain above a given
threshold in a span of environments is a critical feature for the adoption of reinforcement …
threshold in a span of environments is a critical feature for the adoption of reinforcement …