Multi-Source Domain Adaptation for Object Detection

06/30/2021
by   Xingxu Yao, et al.
0

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.

READ FULL TEXT

page 1

page 3

page 8

research
09/09/2021

Generation, augmentation, and alignment: A pseudo-source domain based method for source-free domain adaptation

Conventional unsupervised domain adaptation (UDA) methods need to access...
research
01/11/2023

Adversarial Alignment for Source Free Object Detection

Source-free object detection (SFOD) aims to transfer a detector pre-trai...
research
04/17/2022

Target-Relevant Knowledge Preservation for Multi-Source Domain Adaptive Object Detection

Domain adaptive object detection (DAOD) is a promising way to alleviate ...
research
03/31/2022

Multi-Granularity Alignment Domain Adaptation for Object Detection

Domain adaptive object detection is challenging due to distinctive data ...
research
02/06/2019

Adversarial Domain Adaptation for Stance Detection

This paper studies the problem of stance detection which aims to predict...
research
07/04/2023

SRCD: Semantic Reasoning with Compound Domains for Single-Domain Generalized Object Detection

This paper provides a novel framework for single-domain generalized obje...
research
11/22/2019

Domain Adaptation for Object Detection via Style Consistency

We propose a domain adaptation approach for object detection. We introdu...

Please sign up or login with your details

Forgot password? Click here to reset