Csabi is a 4th year DPhil student working in the Torr Vision Group, focusing on self-supervision and continual learning.
He earned his degree in computer science and bionic engineering at Pázmány Péter Catholic University and has been awarded best student paper two times.
Recently he presented his work on Dynamic Routing models at ECCV 2022, on the 3rd Visual Inductive Priors for Data-Efficient Deep Learning Workshop.
Currently he is collaborating with Intel Lab’s Embodied AI team to understand model fine-tuning under evolving data distributions.

Abstract:
Deep learning models for vision tasks are trained on large datasets under the assumption that there exists a universal representation that can be used to make predictions for all samples. Whereas high complexity models are proven to be capable of learning such representations, a mixture of experts trained on specific subsets of the data can infer the labels more efficiently. However, using mixture of experts poses two new problems, namely (i) assigning the correct expert at inference time when a new unseen sample is presented. (ii) Finding the optimal partitioning of the training data, such that the experts rely the least on common features. In Dynamic Routing (DR) a novel architecture is proposed where each layer is composed of a set of experts, however without addressing the two challenges we demonstrate that the model reverts to using the same subset of experts.
In our method, Diversified Dynamic Routing (DivDR) the model is explicitly trained to solve the challenge of finding relevant partitioning of the data and assigning the correct experts in an unsupervised approach. We conduct several experiments on semantic segmentation on Cityscapes and object detection and instance segmentation on MS-COCO showing improved performance over several baselines.