Improving Detection in Aerial Images by Capturing Inter-Object Relationships

arXiv:2404.04140v1 Announce Type: cross
Abstract: In many image domains, the spatial distribution of objects in a scene exhibits meaningful patterns governed by their semantic relationships. In most modern detection pipelines, however, the detection proposals are processed independently, overlooking the underlying relationships between objects. In this work, we introduce a transformer-based approach to capture these inter-object relationships to refine classification and regression outcomes for detected objects. Building on two-stage detectors, we tokenize the region of interest (RoI) proposals to be processed …

abstract aerial arxiv cs.cv cs.lg detection distribution domains however image images improving modern object objects patterns pipelines proposals relationships semantic spatial transformer type work