Institut für Informationsverarbeitung (TNT)

In a joint project with the LUHAI, our Reinforcement Learning Benchmark CARL was accepted to the Transactions on Machine Learning Research (TMLR). Try your RL algorithms on our benchmark with the published code on Github!
Our work Compensation Learning in Semantic Segmentation will be presented at The 2nd Workshop Challenge on Vision Datasets Understanding (VDU) at The IEEE/CVF Conference on Computer Vision and Pattern Recognition 2023 (CVPR)
Our work PEKORA: High-Performance 3D Genome Reconstruction Using K-th Order Spearman's Rank Correlation Approximation will be presented at HiTSeq COSI track at ISMB/ECCB 2023
Our work POLTER: Policy Trajectory Ensemble Regularization for Unsupervised Reinforcement Learning has been accepted at the Transactions on Machine Learning Research (TMLR)!
We are happy to announce that our work in collaboration with IENT RWTH Aachen titled GVC: Efficient Random Access Compression for Gene Sequence Variations has been published in the journal BMC Bioinformatics. The code is available on GitHub.

The “Institut für Informationsverarbeitung” (Institute for Information Processing) is the home of machine learning at the Leibniz University Hannover. We focus on three main research directions, namely (I) computer vision & representation learning, (II) signal processing & -coding and (III) automated machine learning. Our methods range from deep learning, automated machine learning, reinforcement learning, image analysis, remote sensing and compression of audio, image, video as well as DNA to biomedical data. Our efforts are directed towards making efficient use of multi-modal and high dimensional data for reliable predictions, ultimately supporting end-users, developers and decision makers in a vast range of applications.

Since the foundation in 1973, the institute holds a strong tradition of cultivating connections to industry partners and jointly developing solutions to automatically process and harness information. Some of the developed methodology were successfully spun-off commercially as for instance with driver assistance modules, cochlear implants or component testing. The institute is also well known for being actively involved in the standardization of MP3, MPEG-2, AVC (H.264), HEVC (H.265) as well as MPEG-G.

Do you want to join us? We have open positions.

Current Spotlight

Tracking and motion classification with digital in-line holographic microscopy data (more...)

Algorithm Configuration (AC) aims to optimize algorithm performance by automating important decisions like hyperparameter settings and algorithm choice. Both theoretical and empirical results have shown, however, that only making these decisions once at the beginning of an algorithm run is often not optimal. Instead, the best configuration often depends on the current timestep and algorithm's state. Therefore Dynamic Algorithm Configuration (DAC) learn configuration schedules that fit the current state to improve overall performance. (more...)

Learning to play (collectible) card games (more...)

The way to go for easy-to-use, efficient and state-of-the-art development and optimization of machine learning applications.

Extraction and Processing of Information from Audio Signals for Damage Detection, Hearing Devices, Language disorders and Human-Machine Interaction.

Personalized medicine turns reality through advanced medical information processing

More than just playing games! Advance the capabilities of AI agents while teaching them to solve complex decision-making tasks in a variety of games.

Multimedia coding enables efficient storage, distribution, and streaming of image, video, audio, genomics, 3D, and other data

Teaching Computers to Perceive the World.

Enable the machines to teach themselves and let them do the work – faster, better, more reliably.

Active, weather-independent images with a resolution independent of distance: We compute sharp images of moving and static scenes

Human motion, the science of capturing human pose and movement, and its applications in movie production, computer animation, medical analysis, sports sciences, surveillance, action recognition, and human-computer interaction are being explored at TNT.