SF-FSDA: Source-Free Few-Shot Domain Adaptive Object Detection with Efficient Labeled Data Factory

TL;DR

This paper introduces SF-FSDA, a practical source-free few-shot domain adaptive object detection method that synthesizes target-like images and annotations without source data, improving detection performance under privacy and data scarcity constraints.

Contribution

Proposes an efficient data factory approach to generate labeled target-like images and annotations without source data, enabling robust object detection in source-free, few-shot domain adaptation scenarios.

Findings

Outperforms state-of-the-art methods on SF-FSDA benchmarks.

Effectively mitigates domain shift with synthesized data.

Reduces reliance on source data and pseudo-labels.

Abstract

Domain adaptive object detection aims to leverage the knowledge learned from a labeled source domain to improve the performance on an unlabeled target domain. Prior works typically require the access to the source domain data for adaptation, and the availability of sufficient data on the target domain. However, these assumptions may not hold due to data privacy and rare data collection. In this paper, we propose and investigate a more practical and challenging domain adaptive object detection problem under both source-free and few-shot conditions, named as SF-FSDA. To overcome this problem, we develop an efficient labeled data factory based approach. Without accessing the source domain, the data factory renders i) infinite amount of synthesized target-domain like images, under the guidance of the few-shot image samples and text description from the target domain; ii) corresponding bounding box and category annotations, only demanding minimum human effort, i.e., a few manually labeled examples. On the one hand, the synthesized images mitigate the knowledge insufficiency brought by the few-shot condition. On the other hand, compared to the popular pseudo-label technique, the generated annotations from data factory not only get rid of the reliance on the source pretrained object detection model, but also alleviate the unavoidably pseudo-label noise due to domain shift and source-free condition. The generated dataset is further utilized to adapt the source pretrained object detection model, realizing the robust object detection under SF-FSDA. The experiments on different settings showcase that our proposed approach outperforms other state-of-the-art methods on SF-FSDA problem. Our codes and models will be made publicly available.