Towards Good Practices for Instance Segmentation

Download PDF
Open Webpage

Dongdong Yu, Zehuan Yuan, Jinlai Liu, Kun Yuan, Changhu Wang

Published: 01 Jan 2019, Last Modified: 15 Nov 2024CoRR 2019EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Instance Segmentation is an interesting yet challenging task in computer vision. In this paper, we conduct a series of refinements with the Hybrid Task Cascade (HTC) Network, and empirically evaluate their impact on the final model performance through ablation studies. By taking all the refinements, we achieve 0.47 on the COCO test-dev dataset and 0.47 on the COCO test-challenge dataset.