Simplifying Source-Free Domain Adaptation for Object Detection: Effective Self-Training Strategies and Performance Insights

TL;DR

This paper demonstrates that simple adaptation strategies, such as adapting only batch normalization layers and using fixed pseudo-labels, can outperform complex source-free domain adaptation methods for object detection.

Contribution

The work introduces a strong baseline by adapting only batch normalization statistics and proposes SF-UT, a simple Mean Teacher extension with strong-weak augmentation, outperforming prior methods.

Findings

Adapting only batch normalization layers is effective.

SF-UT outperforms most complex SFOD methods.

Training on fixed pseudo-labels is competitive and efficient.

Abstract

This paper focuses on source-free domain adaptation for object detection in computer vision. This task is challenging and of great practical interest, due to the cost of obtaining annotated data sets for every new domain. Recent research has proposed various solutions for Source-Free Object Detection (SFOD), most being variations of teacher-student architectures with diverse feature alignment, regularization and pseudo-label selection strategies. Our work investigates simpler approaches and their performance compared to more complex SFOD methods in several adaptation scenarios. We highlight the importance of batch normalization layers in the detector backbone, and show that adapting only the batch statistics is a strong baseline for SFOD. We propose a simple extension of a Mean Teacher with strong-weak augmentation in the source-free setting, Source-Free Unbiased Teacher (SF-UT), and show that it actually outperforms most of the previous SFOD methods. Additionally, we showcase that an even simpler strategy consisting in training on a fixed set of pseudo-labels can achieve similar performance to the more complex teacher-student mutual learning, while being computationally efficient and mitigating the major issue of teacher-student collapse. We conduct experiments on several adaptation tasks using benchmark driving datasets including (Foggy)Cityscapes, Sim10k and KITTI, and achieve a notable improvement of 4.7\% AP50 on Cityscapes$\rightarrow$Foggy-Cityscapes compared with the latest state-of-the-art in SFOD. Source code is available at https://github.com/EPFL-IMOS/simple-SFOD.