Bob) update her actions in the odd rounds so that, regardless of Bob's

PAnoramic Semantic Segmentation (PASS) isanimportant task incomputer vision, as it enables semantic understanding of a 360 environment. Currently, most of existing works have focused on addressing the distortion issues in 2D panoramic images without considering spatial properties of indoor scene. This restricts PASS methods inperceiving contextual attributestodealwith theambiguity when working with monocular images. In this paper, we propose anovel approach for indoor panoramic semantic segmentation. Unlike previous works, we consider the panoramic image as a composition of segment groups:oversampled segments,representing planar structures suchasfloorsandceilings, and under-sampled segments, representing other scene elements.

The Probabilistic Watershed isasemi-supervised learning algorithm applied on undirected graphs.

However, such datasets also pose significant challenges in terms of computational and storage resources. It is important to note that these datasets may contain redundant or noisy samples that are either irrelevant or harmful to the model's performance.

Existing MIPL algorithms often overlook the margins for attention scores andpredicted probabilities, leading tosuboptimal generalization performance.