Tobias Koch

Tobias Koch

I am an external PhD candidate in the Multimedia Security Group and work in cooperation with GmbH. My research interests include classical machine and deep learning, with a focus on online learning and open-set recognition. The scope of my work covers biometrics, such as face recognition and face anti-spoofing, as well as image classification in general.


LORD: Leveraging Open-Set Recognition with Unknown Data (ICCVW 2023)

Handling entirely unknown data is a challenge for any deployed classifier. Classification models are typically trained on a static pre-defined dataset and are kept in the dark for the open unassigned feature space. As a result, they struggle to deal with out-of-distribution data during inference. Addressing this task on the class-level is termed open-set recognition (OSR). However, most OSR methods are inherently limited, as they train closed-set classifiers and only adapt the downstream predictions to OSR. This work presents LORD, a framework to Leverage Open-set Recognition by exploiting unknown Data. LORD explicitly models open space during classifier training and provides a systematic evaluation for such approaches. We identify three model-agnostic training strategies that exploit background data and applied them to well-established classifiers. Due to LORD’s extensive evaluation protocol, we consistently demonstrate improved recognition of unknown data. The benchmarks facilitate in-depth analysis across various requirement levels. To mitigate dependency on extensive and costly background datasets, we explore mixup as an off-the-shelf data generation technique. Our experiments highlight mixup’s effectiveness as a substitute for background datasets. Lightweight constraints on mixup synthesis further improve OSR performance.

Paper | Preprint

Exploring the Open World Using Incremental Extreme Value Machines (ICPR 2022)

Dynamic environments require adaptive applications. One particular machine learning problem in dynamic environments is open-world recognition. It characterizes a continuously changing domain where only some classes are seen in one batch of the training data and such batches can only be learned incrementally. We introduce a modification of the widely known Extreme Value Machine (EVM) to enable open-world recognition. Our proposed method extends the EVM with a partial model fitting function by neglecting unaffected space during an update. In addition, we provide a modified model reduction using weighted maximum K-set cover to strictly bound the model complexity and reduce the computational effort.

Below is the code base for the incremental EVM. Although this is not the original code, it should help to reproduce our work and develop further ideas.

Paper | Preprint | GitHub