Deep Learning – DFKI – Interactive Machine Learning Lab

Google Research Grant for End-to-End Active Learning Framework for Medical Image Annotation

We develop a modularized active learning framework within the Google Cloud Platform, facilitating large-scale medical image annotation in a cost-effective manner while ensuring data sovereignty and privacy. Our work emphasizes a federated learning use case for healthcare data, taking into consideration data protection and security aspects. Our goal is to Read more…

By Franziska Scheurer, 3 weeksNovember 13, 2023 ago

IML extends GPU infrastructure
with NVIDIA DGX-A100

The research department IML extends its GPU infrastructure with a powerful DGX-A100 (640 GB) to accelerate end-to-end GPU workflows, transfer learning, and interactive machine learning. The system is hosted at DFKI’s large deep learning center in Kaiserslautern. The new NVIDIA DGX-A100 (640 GB) is expected to significantly accelerate AI research Read more…

By Franziska Scheurer, 2 yearsSeptember 10, 2021 ago

Machine Learning

Active Learning in Image Captioning

In this present day and age of smart phones, ipads and other smart devices a digital camera has become an integral part of our daily experience. This combined with our desire to capture moments in images has lead to a vast repository of myriad images on the internet. In this Read more…

By Michael Barz, 5 yearsMay 15, 2019 ago

HCI & Virtual Reality

Interactive Image Labelling in VR

We present a virtual reality (VR) application that enables interactive image clustering and fine-tuning of a deep neural network by using natural hand gestures. Using a pre-trained AlexNet, we apply PCA and t-SNE dimensionality reduction techniques to project image data sets into the 3D VR space. Resulting spatial clusters of Read more…

By Alexander Prange, 5 yearsAugust 23, 2018 ago

Multimodality

Modelling Visual Attention for Generating an Artificial Episodic Memory

Visual Attention and the Artificial Episodic Memory Recent advances in mobile eye tracking technologies opened the way to design novel attention-aware intelligent user interaction. In particular, the gaze signal can be used to create or improve artificial episodic memories for offline processing, but also real-time processing. We investigate different methods Read more…

By Michael Barz, 6 yearsApril 20, 2018 ago