.png){kind=icon}
.png){kind=icon}
Return
Multi-source-free Domain Adaptive Object Detection
.png){kind=icon}
PRE
AI
DOI：10.1007/s11263-024-02170-z.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
To enhance the transferability of object detection models in real-world scenarios where data is sampled from disparate distributions, considerable attention has been devoted to domain adaptive object detection (DAOD). Researchers have also investigated multi-source DAOD to confront the challenges posed by training samples originating from different source domains. Guiguang Ding as another corresponding author. However, existing methods encounter difficulties when source data is unavailable due to privacy preservation policies or transmission cost constraints. To address these issues, we introduce and address the problem of Multi-source-free Domain Adaptive Object Detection (MSFDAOD), which seeks to perform domain adaptation for object detection using multi-source-pretrained models without any source data or target labels. Specifically, we propose a novel Divide-and-Aggregate Contrastive Adaptation (DACA) framework. First, multiple mean-teacher detection models perform effective knowledge distillation and class-wise contrastive learning within each source domain feature space, denoted as Divide. Meanwhile, DACA integrates proposals, obtains unified pseudo-labels, and assigns dynamic weights to student prediction aggregation, denoted as Aggregate. The two-step process of Divide and Aggregate enables our method to efficiently leverage the advantages of multiple source-free models and aggregate their contributions to adaptation in a self-supervised manner. Extensive experiments are conducted on multiple popular benchmark datasets, and the results demonstrate that the proposed DACA framework significantly outperforms state-of-the-art approaches for MSFDAOD tasks.
Keywords:
Domain adaptive object detection
Multi-source domain adaptation
Source-free domain adaptation
Contrastive learning
Journal
IF:
9.3
Papers:
3.9K
Citations:
2.8W