반응형
Per-Pixel Classification is Not All You Need for Semantic Segmentation
https://arxiv.org/abs/2107.06278
Per-Pixel Classification is Not All You Need for Semantic Segmentation
Modern approaches typically formulate semantic segmentation as a per-pixel classification task, while instance-level segmentation is handled with an alternative mask classification. Our key insight: mask classification is sufficiently general to solve both
arxiv.org
semantic segmentation task image를 pixel-wise하게 classification 한다는 고정관념을 깬 논문.
instance segmentation 과 같이 region을 추출하고 region에 대하여 prediction을 진행한다.
반응형