用深度不确定性提升人体姿态形状估计的可靠性。
CUPS: Improving Human Pose-Shape Estimators with Conformalized Deep Uncertainty
- 训练时生成多假设并评分，端到端学习不确定性函数。
- 在多个数据集上达到最佳性能，且输出有概率保证。
- 适合需要可信预测结果的应用场景。
我们提出CUPS，一种从RGB视频中学习序列到序列3D人体形状与姿态的新方法，并包含不确定性量化。为改进现有工作，我们设计了一种在训练过程中生成并评分多个假设的机制，将不确定性量化融入学习过程，得到一个端到端训练的深度不确定性函数。训练后，该模型作为校准分数，用于构建置信区间，评估预测质量。由于人体姿态-形状数据不具备完全可交换性，我们还提出了两个实用的覆盖率偏差边界，为模型不确定性提供了理论支持。实验表明，结合深度不确定性与置信区间预测，本方法在多个指标和数据集上达到当前最优表现，同时继承了置信区间预测的概率保障。
原文摘要 · Abstract (English)
We introduce CUPS, a novel method for learning sequence-to-sequence 3D human shapes and poses from RGB videos with uncertainty quantification. To improve on top of prior work, we develop a method to generate and score multiple hypotheses during training, effectively integrating uncertainty quantification into the learning process. This process results in a deep uncertainty function that is trained end-to-end with the 3D pose estimator. Post-training, the learned deep uncertainty model is used as the conformity score, which can be used to calibrate a conformal predictor in order to assess the quality of the output prediction. Since the data in human pose-shape learning is not fully exchangeable, we also present two practical bounds for the coverage gap in conformal prediction, developing theoretical backing for the uncertainty bound of our model. Our results indicate that by taking advantage of deep uncertainty with conformal prediction, our method achieves state-of-the-art performance across various metrics and datasets while inheriting the probabilistic guarantees of conformal prediction.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。