Multi-Source Domain Adaptation for Object Detection

TL;DR

This paper introduces a unified framework for multi-source domain adaptation in object detection, improving transfer learning by aligning features and learning from multiple labeled sources.

Contribution

It proposes the Divide-and-Merge Spindle Network (DMSN), a novel method that handles multiple source domains and enhances domain invariance in object detection.

Findings

Effective in various adaptation scenarios

Improves domain invariance and discriminative power

Outperforms existing single-source methods

Abstract

To reduce annotation labor associated with object detection, an increasing number of studies focus on transferring the learned knowledge from a labeled source domain to another unlabeled target domain. However, existing methods assume that the labeled data are sampled from a single source domain, which ignores a more generalized scenario, where labeled data are from multiple source domains. For the more challenging task, we propose a unified Faster R-CNN based framework, termed Divide-and-Merge Spindle Network (DMSN), which can simultaneously enhance domain invariance and preserve discriminative power. Specifically, the framework contains multiple source subnets and a pseudo target subnet. First, we propose a hierarchical feature alignment strategy to conduct strong and weak alignments for low- and high-level features, respectively, considering their different effects for object detection. Second, we develop a novel pseudo subnet learning algorithm to approximate optimal parameters of pseudo target subset by weighted combination of parameters in different source subnets. Finally, a consistency regularization for region proposal network is proposed to facilitate each subnet to learn more abstract invariances. Extensive experiments on different adaptation scenarios demonstrate the effectiveness of the proposed model.