CVOct 28, 2019
Towards Good Practices for Instance Segmentation
arXiv:1911.07939v1
Originality Synthesis-oriented
AI Analysis
This work addresses instance segmentation for computer vision applications, but it is incremental as it focuses on refinements to an existing method.
The paper tackles instance segmentation by refining the Hybrid Task Cascade Network, achieving a performance of 0.47 on both the COCO test-dev and test-challenge datasets.
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.