Shifted Autoencoders for Point Annotation Restoration in Object Counting

arXiv:2312.07190v2 Announce Type: replace
Abstract: Object counting typically uses 2D point annotations. The complexity of object shapes and the subjectivity of annotators may lead to annotation inconsistency, potentially confusing counting model training. Some sophisticated noise-resistance counting methods have been proposed to alleviate this issue. Differently, we aim to directly refine the initial point annotations before training counting models. For that, we propose the Shifted Autoencoders (SAE), which enhances annotation consistency. Specifically, SAE applies random shifts to initial point annotations and …

abstract aim annotation annotations arxiv autoencoders complexity cs.cv issue noise object refine training type