Multi-Person Pose Estimation Evaluation Using Optimal Transportation and Improved Pose Matching
This work addresses a specific evaluation issue in computer vision for researchers, but it is incremental as it modifies existing metrics rather than introducing a new paradigm.
The paper tackled the problem of evaluating multi-person pose estimation by proposing OCpose, a metric based on optimal transportation that equally evaluates all detected poses regardless of confidence scores, resulting in a fairer assessment that accounts for false positives.
In Multi-Person Pose Estimation, many metrics place importance on ranking of pose detection confidence scores. Current metrics tend to disregard false-positive poses with low confidence, focusing primarily on a larger number of high-confidence poses. Consequently, these metrics may yield high scores even when many false-positive poses with low confidence are detected. For fair evaluation taking into account a tradeoff between true-positive and false-positive poses, this paper proposes Optimal Correction Cost for pose (OCpose), which evaluates detected poses against pose annotations as an optimal transportation. For the fair tradeoff between true-positive and false-positive poses, OCpose equally evaluates all the detected poses regardless of their confidence scores. In OCpose, on the other hand, the confidence score of each pose is utilized to improve the reliability of matching scores between the estimated pose and pose annotations. As a result, OCpose provides a different perspective assessment than other confidence ranking-based metrics.