arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.10045cs.CVcs.LGstat.MEstat.ML
收藏

用于实例分割的共形预测集

Conformal Prediction Sets for Instance Segmentation

Laboratory for Information and Decision Systems, MIT(麻省理工学院信息与决策系统实验室);Department of Electrical Engineering and Computer Science, MIT(麻省理工学院电子工程与计算机科学系);Department of Mechanical Engineering, MIT(麻省理工学院机械工程系);Institute for Data, Systems, and Society, MIT(麻省理工学院数据、系统与社会研究所)

Kerri Lu, Dan M. Kluger, Stephen Bates, Sherrie Wang

AI总结:

研究针对实例分割模型缺乏不确定性量化的问题,引入共形预测算法生成自适应置信集,应用于多领域实例分割,其预测集因查询难度而异且达目标覆盖率,优于基线,还提供不同保证版本,首次捕捉实例分割中的结构不确定性。

摘要:

当前的实例分割模型在平均预测上表现良好,但缺乏有原则的不确定性量化:其输出未校准,且无法保证预测掩码接近真实情况。为解决此限制,我们引入一种共形预测算法为实例分割生成自适应置信集。给定图像和像素坐标查询,算法为该像素生成实例预测的置信集,并对至少一个预测与真实对象实例掩码具有高交并比(IoU)的概率有可证明的保证。我们将算法应用于农业领域划分、细胞分割和车辆检测中的实例分割示例。实证发现,我们的预测集大小因查询难度而异并达到目标覆盖率,优于基线方法。我们提供了具有渐近和有限样本保证的算法版本。我们的工作首次通过构建不同分割预测的置信集来捕捉实例分割中的结构不确定性。

英文摘要:

Current instance segmentation models achieve high performance on average predictions, but lack principled uncertainty quantification: their outputs are not calibrated, and there is no guarantee that a predicted mask is close to the ground truth. To address this limitation, we introduce a conformal prediction algorithm to generate adaptive confidence sets for instance segmentation. Given an image and a pixel coordinate query, our algorithm generates a confidence set of instance predictions for that pixel, with a provable guarantee for the probability that at least one of the predictions has high Intersection-Over-Union (IoU) with the true object instance mask. We apply our algorithm to instance segmentation examples in agricultural field delineation, cell segmentation, and vehicle detection. Empirically, we find that our prediction sets vary in size based on query difficulty and attain the target coverage, outperforming baselines (naive best parameter and morphological dilation-based methods). We provide versions of the algorithm with asymptotic and finite sample guarantees. Our work is the first to capture structural uncertainty in instance segmentation by constructing confidence sets of diverse segmentation predictions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑