Using Mixture of Expert Models to Gain Insights Into Semantic Segmentation

Pavlitskaya, Svetlana and Hubschneider, Christian and Weber, Michael and Moritz, Ruby and Huger, Fabian and Schlicht, Peter and Zollner, Marius
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops
Not only correct scene understanding, but also abilityto understand the decision making process of neural net-works is essential for safe autonomous driving. Currentwork mainly focuses on uncertainty measures, often basedon Monte Carlo dropout, to gain at least some insight intoa models confidence. We investigate a mixture of expertsarchitecture to achieve additional interpretability while re-taining comparable result quality.By being able to use both the overall model output aswell as retaining the possibility to take into account individ-ual expert outputs, the agreement or disagreement betweenthose individual outputs can be used to gain insights into thedecision process. Expert networks are trained by splittingthe input data into semantic subsets,e.g. corresponding todifferent driving scenarios, to become experts in those do-mains. An additional gating network that is also trained onthe same input data is consequently used to weight the out-put of individual experts. We evaluate this mixture of expertsetup on the A2D2 dataset and achieve similar results to abaseline FRRN network trained on all available data, whilegetting additional information.
Download .bib
Download .bib
Eingetragen von
Svetlana Pavlitskaya