arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2107.06668cs.LGcs.AI
收藏

回想:Task-SpecificOut-of-Distribution检测

Thinkback: Task-SpecificOut-of-Distribution Detection

Huawei Technologies(华为技术有限公司)

Lixuan Yang, Dario Rossi

摘要:

深度学习(DL)的日益成功最近引发了许多不同行业领域的DL模型的大规模部署。然而,监督模型的一个关键弱点是处理分布外样本的固有困难,即,属于在训练时未呈现给模型的类的样本。本文提出了一种新的方法来制定的分布外检测问题,适合DL模型。我们的方法不需要对训练数据进行微调处理,但对于分布外检测,比现有技术更准确。

英文摘要:

The increased success of Deep Learning (DL) has recently sparked large-scale deployment of DL models in many diverse industry segments. Yet, a crucial weakness of supervised model is the inherent difficulty in handling out-of-distribution samples, i.e., samples belonging to classes that were not presented to the model at training time. We propose in this paper a novel way to formulate the out-of-distribution detection problem, tailored for DL models. Our method does not require fine tuning process on training data, yet is significantly more accurate than the state of the art for out-of-distribution detection.

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。

↑