Deep spatial context: when attention-based models meet spatial regression

arXiv:2401.10044v2 Announce Type: replace
Abstract: We propose 'Deep spatial context' (DSCon) method, which serves for investigation of the attention-based vision models using the concept of spatial context. It was inspired by histopathologists, however, the method can be applied to various domains. The DSCon allows for a quantitative measure of the spatial context's role using three Spatial Context Measures: $SCM_{features}$, $SCM_{targets}$, $SCM_{residuals}$ to distinguish whether the spatial context is observable within the features of neighboring regions, their target values (attention scores) …

abstract arxiv attention concept context cs.cv domains however investigation quantitative regression spatial type vision vision models