注意骨干网络:最小化骨干网络失真以实现鲁棒的目标检测
Mind the Backbone: Minimizing Backbone Distortion for Robust Object Detection
AI总结:
提出用相对梯度范数(RGN)衡量骨干网络特征失真风险,通过正则化和架构选择最小化梯度更新,防止微调丢失可泛化特征,显著提升目标检测的分布外鲁棒性。
摘要:
构建对域偏移具有鲁棒性的目标检测器对现实世界应用至关重要。先前的方法对预训练骨干网络进行微调,存在使其过拟合于分布内(ID)数据并扭曲对分布外(OOD)泛化有用的特征的风险。我们提出使用相对梯度范数(RGN)作为衡量骨干网络对特征失真脆弱性的方法,并表明高RGN确实与较低的OOD性能相关。我们对RGN的分析得出了有趣的发现:一些骨干网络在微调过程中失去了OOD鲁棒性,但另一些则获得了鲁棒性,因为其架构阻止了参数相对于初始模型发生过大变化。基于这些发现,我们提出了提升两类骨干网络OOD鲁棒性的方案。具体而言,我们研究了正则化和架构选择,以最小化梯度更新,从而防止微调后的骨干网络丢失可泛化特征。我们提出的技术相互补充,并在多样化的架构和数据集上相比基线显示出显著改进。代码可在 https://github.com/VisionLearningGroup/mind_back 获取。
英文摘要:
Building object detectors that are robust to domain shifts is critical for real-world applications. Prior approaches fine-tune a pre-trained backbone and risk overfitting it to in-distribution (ID) data and distorting features useful for out-of-distribution (OOD) generalization. We propose to use Relative Gradient Norm (RGN) as a way to measure the vulnerability of a backbone to feature distortion, and show that high RGN is indeed correlated with lower OOD performance. Our analysis of RGN yields interesting findings: some backbones lose OOD robustness during fine-tuning, but others gain robustness because their architecture prevents the parameters from changing too much from the initial model. Given these findings, we present recipes to boost OOD robustness for both types of backbones. Specifically, we investigate regularization and architectural choices for minimizing gradient updates so as to prevent the tuned backbone from losing generalizable features. Our proposed techniques complement each other and show substantial improvements over baselines on diverse architectures and datasets. Code is available at https://github.com/VisionLearningGroup/mind_back.
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。