Sparse Generation: Making Pseudo Labels Sparse for weakly supervision with points

arXiv:2403.19306v1 Announce Type: new
Abstract: In recent years, research on point weakly supervised object detection (PWSOD) methods in the field of computer vision has attracted people's attention. However, existing pseudo labels generation methods perform poorly in a small amount of supervised annotation data and dense object detection tasks. We consider the generation of weakly supervised pseudo labels as the result of model's sparse output, and propose a method called Sparse Generation to make pseudo labels sparse. It constructs dense tensors …

abstract annotation arxiv attention computer computer vision cs.cv data detection however labels making object people research small supervision tasks type vision