Human-Centered Unsupervised Segmentation Fusion
This addresses the need for reliable ground truth segmentation in computer vision, particularly for tasks like image annotation and evaluation, though it appears incremental as it builds on existing fusion approaches.
The paper tackles the problem of generating a single ground truth segmentation from multiple human annotations, which is challenging due to segmentation's ill-posed nature and lack of methods that consider confidence per human segmentation. It introduces a new unsupervised segmentation fusion model based on K-Modes clustering, which outperforms state-of-the-art methods on publicly available datasets with human ground truth segmentations.
Segmentation is generally an ill-posed problem since it results in multiple solutions and is, therefore, hard to define ground truth data to evaluate algorithms. The problem can be naively surpassed by using only one annotator per image, but such acquisition doesn't represent the cognitive perception of an image by the majority of people. Nowadays, it is not difficult to obtain multiple segmentations with crowdsourcing, so the only problem that stays is how to get one ground truth segmentation per image. There already exist numerous algorithmic solutions, but most methods are supervised or don't consider confidence per human segmentation. In this paper, we introduce a new segmentation fusion model that is based on K-Modes clustering. Results obtained from publicly available datasets with human ground truth segmentations clearly show that our model outperforms the state-of-the-art on human segmentations.