1st Place Solution for the UVO Challenge on Image-based Open-World Segmentation 2021
This work addresses open-world segmentation for computer vision applications, but it is incremental as it builds on existing two-stage methods.
The authors tackled open-world instance segmentation by proposing a two-stage class-agnostic framework, achieving first place in the UVO 2021 challenge.
We describe our two-stage instance segmentation framework we use to compete in the challenge. The first stage of our framework consists of an object detector, which generates object proposals in the format of bounding boxes. Then, the images and the detected bounding boxes are fed to the second stage, where a segmentation network is applied to segment the objects in the bounding boxes. We train all our networks in a class-agnostic way. Our approach achieves the first place in the UVO 2021 Image-based Open-World Segmentation Challenge.