Meriel von Stein's repositories
DeepManeuver
Tool, paper, and study data for DeepManeuver: Adversarial Test Generation for Trajectory Manipulation of Autonomous Vehicles.
openpilot-falsification
Finding Property Violations through Network Falsification: Challenges, Adaptations and Lessons Learned from OpenPilot
ROSbot_data_collection
ROS workspace for collecting human navigation data of Husarion ROSbot 2.0
MissMeriel.github.io
Personal website
SoftAn-Project2
Installation guidelines, instructions, grading rubric and template source code for UVA Software Analysis Project 2: Analyzing software changes and versions
clone-anonymous4open
clone/download codes from https://anonymous.4open.science/
inference_engine
Probabilistic inference engine for time series data traces
CSGSG-Orientation-2023
Latex slides and cost of living chart script
DAVE2-Keras
Implementation of Nvidia's DAVE2 NN in Keras, with some enhancements
deeplearning-input-rectification
Input rectification for deep learning systems
Defects4DL
Reproducing system-level autonomous driving failures caused by deep learning faults in small test cases
dnnv
A Framework for Deep Neural Network Verification
FrankenImage
Online image adjustment for misbehavior-inducing DNN input for robotic control
IFAN
[CVPR 2021] Official PyTorch Implementation for "Iterative Filter Adaptive Network for Single Image Defocus Deblurring"
learning-to-drive-in-5-minutes
Implementation of reinforcement learning approach to make a car learn to drive smoothly in minutes
pytorch-grad-cam
Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.
robot-nav-model-zoo
Model architectures and scripts for DNN-driven robot navigation and perception tasks
rosbot-navstack
Basic routines and DNN-driven navigation for ROSbot 2.0
supervised-universal-transformation
Learning transformations between vision datasets to overcome sensor hardware versioning
Unsupervised-Classification
SCAN: Learning to Classify Images without Labels (ECCV 2020), incl. SimCLR.
UnsupervisedMT
Phrase-Based & Neural Unsupervised Machine Translation