Name: Martin Mundt
Type: User
Company: TU Darmstadt, Hessian.AI
Bio: DEPTH junior research group leader on Open World Lifelong Learning (owll-lab.com) - Hessian.AI & TU Darmstadt
Twitter: mundt_martin
Location: Frankfurt Germany
Blog: martin-mundt.com
Martin Mundt's Projects
Template website for ContinualAI Unconference
PyTorch code for our paper: Open Set Recognition Through Deep Neural Network Uncertainty: Does Out-of-Distribution Detection Require Generative Classifiers? https://arxiv.org/abs/1908.09625
Implementation of our CVPR-W CLVision paper "Neural Architecture Search of Deep Priors: Towards Continual Learning without Catastrophic Interference"
Open-source code for our CVPR19 paper "Meta-learning Convolutional Neural Architectures for Multi-target Concrete Defect Classification with the COncrete DEfect BRidge IMage Dataset".
Open-source code for our paper: Unified Probabilistic Deep Continual Learning through Generative Replay and Open Set Recognition
PyTorch implementation of our paper "Rethinking Layer-wise Feature Amounts in Convolutional Neural Network Architectures"