Keeping track of generated images using watermarking.
Image Provenance — SynthIDConformal calibration with uncertain ground truth.
Monte Carlo Conformal PredictionPhD thesis on uncertainty estimation and (adversarial) robustness in deep learning.
PhD Thesis: Uncertainty and RobustnessEnd-to-end training of deep neural networks and conformal predictors to reduce confidence set size and optimizer application-specific objectives.
Conformal TrainingRobust generalization and overfitting linked to flatness of robust loss surface in weight space.
Robust Generalization and FlatnessRandom and adversarial bit error robustness of DNNs for energy-efficient and secure DNN accelerators.
Random and Adversarial Bit Robustness Random Bit Error RobustnessConfidence calibration of adversarial training for "generalizable" robustness.
Confidence-Calibrated Adversarial TrainingDisentangling the relationship between adversarial robustness and generalization.
Adversarial Robustness and GeneralizationLearning 3D shape completion under weak supervision; on ShapeNet, ModelNet, KITTI and Kinect data; published at CVPR and on ArXiv.
Improved Shape Completion Shape CompletionA comprehensive comparison and evaluation of 28 superpixel algorithms on 5 different datasets; published in CVIU and GCPR.
Superpixel Benchmark (2016) Superpixel Benchmark (2014)Revised C++ implementations of two popular superpixel algorithms, SEEDS and FH, which are shown to outperform the original implementations.
Superpixel AlgorithmsEfficient C++ implementation for hierarchical graph-based image segmentation.
Video SegmentationEfficient C++ implementation of iPiano, a proximal algorithm with inertial force for non-convex and non-smooth optimization; including applications to image segmentation.
Non-Convex OptimizationAchieving accuracy, fair and private image classification.
Fair and Accurate Differential PrivacyReport of the 2020 Max Planck PhDNet survey results.
PhDNet Survey Report 2020Improving corruption and adversarial robustness by enhancing weak sub-networks.
Enhancing Weak SubnetsAdversarial training on location-optimized adversarial patches.
Adversarial Patch TrainingSeries of articles discussing adversarial robustness and adversarial training in PyTorch.
Adversarial Robustness in PyTorch Article SeriesA template for extending PyTorch using C/CUDA operations.
PyTorch C/CUDA Module Template3D mesh fusion, voxelization and evaluation for computer vision research.
Mesh Fusion, Voxelization & EvaluationTorch/CUDA implementation of batch normalization for OctNets.
OctNet Batch NormalizationBasic and advanced torch examples, template for implementing custom C/CUDA modules and implementations of variational auto-encoders.
Torch Examples, Guides and ResourcesAn example of a custom TensorFlow operation implemented in C++.
Custom Tensorflow Operations in C++Examples, tools and resources for using Caffe's Python interface pyCaffe.
pyCaffe Tools, Examples and ResourcesPython implementation of probabilistic principal component analysis (PPCA).
Probabilistic PCAThe Berkeley Segmentation Benchmark extended by superpixel metrics.
Extended Berkeley Segmentation BenchmarkTools to pre-process the NYU Depth v2 segmentations for evaluation.
NYU Depth v2 Segmentation ToolsSome plugins for Twitter Bootstrap and jQuery; including a multiselect plugin and a password strength meter.
Twitter Bootstrap PluginsModules for the HMVC framework Kohana; including modules for user authentication, access control, form generation and validation, CSS and JS assets and more.
Kohana ModulesPlugins for CMSimple XH, a lightweight content management system; including, among others, news article, image gallery and YouTube plugins.
CMSimple Plugins and ThemesExperimental Wordpress plugins and themes; including this theme and plugins for author biographies and live data from GitHub.
Wordpress Plugins and ThemesWeb applications for employee and work scheduling.
Employee Scheduling Web ApplicationsA repository with LaTeX examples, templates and tricks.
LaTeX Resources and ExamplesTutorials for (deep convolutional) neural networks.
(Convolutional) Neural Network TutorialsA two-layer perceptron for digit classification on MNIST implemented in MatLab.
MatLab Two-Layer PerceptronSeveral mathematical impage processing exercises implemented in C++ and MatLab.
Image Processing Exercises in MatLab/C++Common matrix decompositions, including LU, Cholesky and QR decompositions, implemented in PHP; also includes an interactive application to demonstrate and explain the material.
PHP Matrix DecompositionsRelational databases can be described in terms of functional dependencies; this project implements functional dependencies as well as second and third normal form in PHP.
Functional Dependencies