BlenDA: Domain Adaptive Object Detection through diffusion-based blending
CoRR(2024)
摘要
Unsupervised domain adaptation (UDA) aims to transfer a model learned using
labeled data from the source domain to unlabeled data in the target domain. To
address the large domain gap issue between the source and target domains, we
propose a novel regularization method for domain adaptive object detection,
BlenDA, by generating the pseudo samples of the intermediate domains and their
corresponding soft domain labels for adaptation training. The intermediate
samples are generated by dynamically blending the source images with their
corresponding translated images using an off-the-shelf pre-trained
text-to-image diffusion model which takes the text label of the target domain
as input and has demonstrated superior image-to-image translation quality.
Based on experimental results from two adaptation benchmarks, our proposed
approach can significantly enhance the performance of the state-of-the-art
domain adaptive object detector, Adversarial Query Transformer (AQT).
Particularly, in the Cityscapes to Foggy Cityscapes adaptation, we achieve an
impressive 53.4
state-of-the-art by 1.5
applicable to various paradigms of domain adaptive object detection. The code
is available at:https://github.com/aiiu-lab/BlenDA
更多查看译文
关键词
object detection,domain adaptation,unsupervised domain adaptation,blended images,target domain
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要