论文标题
对比度视图设计策略，以增强下游对象检测中域移动的鲁棒性
Contrastive View Design Strategies to Enhance Robustness to Domain Shifts in Downstream Object Detection
论文作者
论文摘要
对比学习已成为一种竞争预处理的方法检测方法。尽管取得了这种进步，但面对域移动时，对近对外检测器的鲁棒性进行了最少的研究。为了解决这一差距，我们对对比度学习和室外对象检测进行了经验研究，研究了对比视图设计如何影响鲁棒性。特别是，我们对以检测为借口的任务实例本地化（INSLOC）进行案例研究，并提出策略来增强视图并增强外观偏移和上下文切换的场景的鲁棒性。在这些策略中，我们提出更改裁剪的更改，例如改变所使用的百分比，增加限制和集成基于显着性的对象先验。我们还探讨了添加捷径减速的增加，例如泊松混合物，质地扁平和弹性变形。我们将这些策略基于抽象，天气和上下文域的转移，并在单对象和多对象图像数据集上进行预处理，并说明结合它们的强大方法。总体而言，我们的结果和见解表明了如何通过在对比学习中选择观点来确保鲁棒性。
Contrastive learning has emerged as a competitive pretraining method for object detection. Despite this progress, there has been minimal investigation into the robustness of contrastively pretrained detectors when faced with domain shifts. To address this gap, we conduct an empirical study of contrastive learning and out-of-domain object detection, studying how contrastive view design affects robustness. In particular, we perform a case study of the detection-focused pretext task Instance Localization (InsLoc) and propose strategies to augment views and enhance robustness in appearance-shifted and context-shifted scenarios. Amongst these strategies, we propose changes to cropping such as altering the percentage used, adding IoU constraints, and integrating saliency based object priors. We also explore the addition of shortcut-reducing augmentations such as Poisson blending, texture flattening, and elastic deformation. We benchmark these strategies on abstract, weather, and context domain shifts and illustrate robust ways to combine them, in both pretraining on single-object and multi-object image datasets. Overall, our results and insights show how to ensure robustness through the choice of views in contrastive learning.
