In the domain of graph neural networks (GNNs), pooling operators are fundamental to reduce the size of the graph by simplifying graph structures and vertex features. Recent advances have shown that well-designed pooling operators, coupled with message-passing...
Models with similar performances exhibit significant disagreement in the predictions of individual samples, referred to as prediction churn. Our work explores this phenomenon in graph neural networks by investigating differences between models differing only in their...
Statistical heterogeneity, especially feature distribution skewness, among the distributed data is a common phenomenon in practice, which is a challenging problem in federated learning that can lead to a degradation in the performance of the aggregated global model....
Due to the high variation in the application requirements of sound event detection (SED) systems, it is not sufficient to evaluate systems only in a single operating point. Therefore, the community recently adopted the polyphonic sound detection score (PSDS) as an...
Domain adaptation is especially important for robotics applications, where target domain training data is usually scarce and annotations are costly to obtain. We present a method for self-supervised domain adaptation for the scenario where annotated source domain data...
We introduce SLCF-Net, a novel approach for the Semantic Scene Completion (SSC) task that sequentially fuses LiDAR and camera data. It jointly estimates missing geometry and semantics in a scene from sequences of RGB images and sparse LiDAR measurements. The images...