arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2210.04783cs.LGcs.CVphysics.app-ph
收藏

校准在半监督学习中的重要性

On the Importance of Calibration in Semi-supervised Learning

MIT-IBM Watson AI Lab(麻省理工学院-IBM沃森人工智能实验室);Rutgers University(罗格斯大学)

Charlotte Loh, Rumen Dangovski, Shivchander Sudalairaj, Seungwook Han, Ligong Han, Leonid Karlinsky, Marin Soljacic, Akash Srivastava

摘要:

最先进的(SOTA)半监督学习(SSL)方法通过结合一致性正则化和伪标记技术,在利用标记和未标记数据的混合方面非常成功。在伪标记过程中,模型对未标记数据的预测用于训练,因此,模型校准在减轻确认偏差方面很重要。然而,许多SOTA方法针对模型性能进行了优化,很少关注改善模型校准。在这项工作中,我们的经验表明,模型校准与模型性能密切相关,并建议通过近似贝叶斯技术来提高校准。我们引入了一系列新的SSL模型,这些模型针对校准进行了优化,并在CIFAR-10、CIFAR-100和ImageNet的标准视觉基准测试中证明了它们的有效性,测试精度提高了15.9%。此外,我们还证明了它们在其他现实和具有挑战性的问题中的有效性,例如类不平衡数据集和光子科学。

英文摘要:

State-of-the-art (SOTA) semi-supervised learning (SSL) methods have been highly successful in leveraging a mix of labeled and unlabeled data by combining techniques of consistency regularization and pseudo-labeling. During pseudo-labeling, the model's predictions on unlabeled data are used for training and thus, model calibration is important in mitigating confirmation bias. Yet, many SOTA methods are optimized for model performance, with little focus directed to improve model calibration. In this work, we empirically demonstrate that model calibration is strongly correlated with model performance and propose to improve calibration via approximate Bayesian techniques. We introduce a family of new SSL models that optimizes for calibration and demonstrate their effectiveness across standard vision benchmarks of CIFAR-10, CIFAR-100 and ImageNet, giving up to 15.9% improvement in test accuracy. Furthermore, we also demonstrate their effectiveness in additional realistic and challenging problems, such as class-imbalanced datasets and in photonics science.

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。

↑