When Oracle Conditioning Misleads Deployment: Conditioning-Availability Bias in Echocardiographic Segmentation 文章

ArXiv CS.CV2026-08-05PAPERen作者: Dang P. M. Cao, Hieu D. Pham, Hieu Pham

详细信息

来源站点
ArXiv CS.CV
作者
Dang P. M. Cao, Hieu D. Pham, Hieu Pham
文章类型
PAPER
语言
en
发布日期
2026-08-05

摘要

arXiv:2608.03342v1 Announce Type: new Abstract: Conditional segmentation models may be trained and evaluated with auxiliary signals cleaner than those available at deployment. We study this protocol-level manifestation of shortcut learning and auxiliary-variable shift in phase-conditioned echocardiographic segmentation. The complementary gap pair measures loss on the deployable oracle-estimated pathway and probes sensitivity on the oracle-random pathway. On held-out CAMUS data, one strong-cyclic, oracle-selected run fails severely with estimated phase, while sensitivity to incorrect phase persists across three runs. On EchoNet-Dynamic, the current estimator remains usable, but random-phase testing reveals strong latent sensitivity. Deployment-aware checkpoint selection and phase perturbation reduce both gaps with little change in mean Dice.

相关事件

暂无数据

相关公司

暂无数据

相关人物

暂无数据

相关技术

暂无数据