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 2512.12906cs.CV
收藏

语义一致的分布外检测预测样本分配

Predictive Sample Assignment for Semantically Coherent Out-of-Distribution Detection

Nankai University(南开大学)

Zhimao Peng, Enguang Wang, Xialei Liu, Ming-Ming Cheng

AI总结:

本文提出基于预测样本分配的SCOOD框架,通过双阈值三元样本分配策略和概念对比表示学习损失提升ID和分布外样本的区分能力,实验表明优于现有方法。

摘要:

语义一致的分布外检测(SCOOD)是一种最近提出的现实中的分布外检测设置:给定标记的分布内(ID)数据和混合分布内和分布外未标记数据作为训练数据,SCOOD旨在使训练后的模型能够准确识别测试数据中的分布外样本。当前SCOOD方法主要采用各种基于聚类的分布内样本过滤(IDF)策略来选择干净的ID样本,将剩余样本作为辅助分布外数据,这不可避免地在训练中引入大量噪声样本。为了解决上述问题,我们提出了一种基于预测样本分配(PSA)的简洁SCOOD框架。PSA包括基于预测能量分数的双阈值三元样本分配策略,该策略可以通过将不确定的未标记数据分配到额外的丢弃样本集来显著提高所选ID和分布外样本集的纯度,并且引入了一个概念对比表示学习损失以进一步扩大ID和分布外样本在表示空间中的距离以帮助ID/分布外识别。此外,我们还引入了一种重训练策略以帮助模型完全拟合所选的辅助ID/分布外样本。在两个标准SCOOD基准上的实验表明,我们的方法在显著的幅度上优于最先进的方法。

英文摘要:

Semantically coherent out-of-distribution detection (SCOOD) is a recently proposed realistic OOD detection setting: given labeled in-distribution (ID) data and mixed in-distribution and out-of-distribution unlabeled data as the training data, SCOOD aims to enable the trained model to accurately identify OOD samples in the testing data. Current SCOOD methods mainly adopt various clustering-based in-distribution sample filtering (IDF) strategies to select clean ID samples from unlabeled data, and take the remaining samples as auxiliary OOD data, which inevitably introduces a large number of noisy samples in training. To address the above issue, we propose a concise SCOOD framework based on predictive sample assignment (PSA). PSA includes a dual-threshold ternary sample assignment strategy based on the predictive energy score that can significantly improve the purity of the selected ID and OOD sample sets by assigning unconfident unlabeled data to an additional discard sample set, and a concept contrastive representation learning loss to further expand the distance between ID and OOD samples in the representation space to assist ID/OOD discrimination. In addition, we also introduce a retraining strategy to help the model fully fit the selected auxiliary ID/OOD samples. Experiments on two standard SCOOD benchmarks demonstrate that our approach outperforms the state-of-the-art methods by a significant margin.

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。

↑