Instance Scale Normalization for image understanding

20 Aug 2019Zewen HeHe HuangYudong WuGuan HuangWensheng Zhang

Scale variation remains a challenging problem for object detection. Common paradigms usually adopt multiscale training & testing (image pyramid) or FPN (feature pyramid network) to process objects in a wide scale range... (read more)

PDF Abstract

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods used in the Paper