弱標籤引導的自訓練方法用於弱監督領域自適應三維物體檢測

Abstract

在領域自適應三維物體檢測中，大部分的研究都專注於無監督領域自適應。然而，在缺乏任何目標領域的標註資訊下，無監督領域自適應的方法與在目標領域中完全監督的方法之間仍存在著明顯的性能差距，這對於現實世界的應用來說是不切實際的。另一方面，弱監督領域自適應是一個很少被研究但具有實際應用價值的任務，因為他只需要在目標領域進行少量的標註工作。為了以經濟有效的方式來提高領域自適應性能，我們提出了一個專門為弱監督領域自適應三維物體檢測設計的 WLST 框架，同時他也是一個通用的弱標籤引導的自訓練方法。透過將自動標註器整合進現有的自訓練流程中，該方法能夠生成更穩健且更一致的偽標籤，這將有助於後續在目標領域上的訓練。此外，大量的實驗證實了我們 WLST 框架的有效性、穩健性和對檢測器的獨立性。值得注意的是，他在所有領域自適應的任務上表現都優於先前最先進的方法。

In the field of domain adaptation (DA) on 3D object detection, most of the work is dedicated to unsupervised domain adaptation (UDA). Yet, without any target annotations, the performance gap between the UDA approaches and the fully-supervised approach is still noticeable, which is impractical for real-world applications. On the other hand, weakly-supervised domain adaptation (WDA) is an underexplored yet practical task that only requires few labeling effort on the target domain. To improve the DA performance in a cost-effective way, we propose a general weak labels guided self-training framework, WLST, designed for WDA on 3D object detection. By incorporating autolabeler, which can generate 3D pseudo labels from 2D bounding boxes, into the existing self-training pipeline, our method is able to generate more robust and consistent pseudo labels that would benefit the training process on the target domain. Extensive experiments demonstrate the effectiveness, robustness, and detector-agnosticism of our WLST framework. Notably, it outperforms previous state-of-the-art methods on all evaluation tasks.