Feature boosting with efficient attention for scene parsing

arXiv:2402.19250v1 Announce Type: new
Abstract: The complexity of scene parsing grows with the number of object and scene classes, which is higher in unrestricted open scenes. The biggest challenge is to model the spatial relation between scene elements while succeeding in identifying objects at smaller scales. This paper presents a novel feature-boosting network that gathers spatial context from multiple levels of feature extraction and computes the attention weights for each level of representation to generate the final class labels. A …

abstract arxiv attention boosting challenge complexity cs.cv feature novel objects paper parsing spatial type