Objects as context for detecting their semantic parts
This addresses the challenging problem of part detection in computer vision, offering a domain-specific improvement for tasks like object understanding.
The paper tackles semantic part detection by leveraging object information, such as appearance and class, to predict part locations, achieving a +5 mAP improvement on the PASCAL-Part dataset compared to using part appearance alone.
We present a semantic part detection approach that effectively leverages object information.We use the object appearance and its class as indicators of what parts to expect. We also model the expected relative location of parts inside the objects based on their appearance. We achieve this with a new network module, called OffsetNet, that efficiently predicts a variable number of part locations within a given object. Our model incorporates all these cues to detect parts in the context of their objects. This leads to considerably higher performance for the challenging task of part detection compared to using part appearance alone (+5 mAP on the PASCAL-Part dataset). We also compare to other part detection methods on both PASCAL-Part and CUB200-2011 datasets.