Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
Design and Behavior of Sparse Mixture-of-Experts Layers in CNN-based Semantic Segmentation
Svetlana Pavlitska, Haixi Fan, Konstantin Ditschuneit +1
Sparse mixture-of-experts (MoE) layers have been shown to substantially increase model capacity without a proportional increase in computational cost and are widely used in transfo…
cs.CV2025
Robust Experts: the Effect of Adversarial Training on CNNs with Sparse Mixture-of-Experts Layers
Svetlana Pavlitska, Haixi Fan, Konstantin Ditschuneit +1
Robustifying convolutional neural networks (CNNs) against adversarial attacks remains challenging and often requires resource-intensive countermeasures. We explore the use of spars…