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 2404.08392cs.CVcs.LG
收藏

NC-TTT: 一种用于测试时训练的噪声对比方法

NC-TTT: A Noise Contrastive Approach for Test-Time Training

ÉTS Montréal(蒙特利尔工程学院);MILA(蒙特利尔学习算法研究所);CNRS(法国国家科学研究中心);Université Paris-Saclay(巴黎萨克雷大学);CentraleSupélec(中央理工-高等电力学院)

David Osowiechi, Gustavo A. Vargas Hakim, Mehrdad Noori, Milad Cheraghalikhani, Ali Bahri, Moslem Yazdanpanah, Ismail Ben Ayed, Christian Desrosiers

AI总结:

针对深度学习模型测试时域偏移性能下降问题,提出基于带噪特征图判别的无监督测试时训练方法NC-TTT,在多个基准上优于现有方法。

摘要:

尽管深度学习模型在视觉任务中表现出色,但在测试阶段遇到域偏移时往往性能不佳。测试时训练(Test-Time Training, TTT)方法近年来受到广泛关注,这类方法通过添加与主任务联合优化的辅助目标来提升模型的鲁棒性。该辅助目标完全无监督,可在测试阶段无需标签即可用于模型适配。本文提出噪声对比测试时训练(Noise-Contrastive Test-Time Training, NC-TTT),这是一种基于带噪特征图判别机制的新型无监督TTT技术。通过学习对投影特征图的带噪视图进行分类,再在新域上对模型进行相应适配,分类性能可得到大幅恢复。在多个主流测试时适配基准上的实验表明,与该领域现有方法相比,本文方法更具优势。代码可访问:https://github.com/GustavoVargasHakim/NCTTT.git

英文摘要:

Despite their exceptional performance in vision tasks, deep learning models often struggle when faced with domain shifts during testing. Test-Time Training (TTT) methods have recently gained popularity by their ability to enhance the robustness of models through the addition of an auxiliary objective that is jointly optimized with the main task. Being strictly unsupervised, this auxiliary objective is used at test time to adapt the model without any access to labels. In this work, we propose Noise-Contrastive Test-Time Training (NC-TTT), a novel unsupervised TTT technique based on the discrimination of noisy feature maps. By learning to classify noisy views of projected feature maps, and then adapting the model accordingly on new domains, classification performance can be recovered by an important margin. Experiments on several popular test-time adaptation baselines demonstrate the advantages of our method compared to recent approaches for this task. The code can be found at:https://github.com/GustavoVargasHakim/NCTTT.git

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。

↑