ViewPCL: a point cloud based active learning method for multi-view segmentation
This work addresses data efficiency in multi-view segmentation for computer vision applications, but it appears incremental as it builds on existing active learning and point cloud techniques.
The authors tackled the problem of multi-view semantic segmentation by proposing an active learning framework that uses a novel score based on point cloud distribution discrepancies, resulting in a data-efficient and explainable method.
We propose a novel active learning framework for multi-view semantic segmentation. This framework relies on a new score that measures the discrepancy between point cloud distributions generated from the extra geometrical information derived from the model's prediction across different views. Our approach results in a data efficient and explainable active learning method. The source code is available at https://github.com/chilai235/viewpclAL.