Author:
Cao Xinzhi,Guo Yinsai,Yang Wenbin,Luo Xiangfeng,Xie Shaorong
Abstract
Purpose
Unsupervised domain adaptation object detection not only mitigates model terrible performance resulting from domain gap, but also has the ability to apply knowledge trained on a definite domain to a distinct domain. However, aligning the whole feature may confuse the object and background information, making it challenging to extract discriminative features. This paper aims to propose an improved approach which is called intrinsic feature extraction domain adaptation (IFEDA) to extract discriminative features effectively.
Design/methodology/approach
IFEDA consists of the intrinsic feature extraction (IFE) module and object consistency constraint (OCC). The IFE module, designed on the instance level, mainly solves the issue of the difficult extraction of discriminative object features. Specifically, the discriminative region of the objects can be paid more attention to. Meanwhile, the OCC is deployed to determine whether category prediction in the target domain brings into correspondence with it in the source domain.
Findings
Experimental results demonstrate the validity of our approach and achieve good outcomes on challenging data sets.
Research limitations/implications
Limitations to this research are that only one target domain is applied, and it may change the ability of model generalization when the problem of insufficient data sets or unseen domain appeared.
Originality/value
This paper solves the issue of critical information defects by tackling the difficulty of extracting discriminative features. And the categories in both domains are compelled to be consistent for better object detection.
Subject
Computer Networks and Communications,Information Systems
Reference52 articles.
1. Cross-domain car detection using unsupervised image-to-image translation: from day to night,2019
2. T-SNE-CUDA: GPU-accelerated t-sne and its applications to modern data,2018
3. Structure-sensitive saliency detection via multilevel rank analysis in intrinsic feature space;IEEE Transactions on Image Processing,2015
4. Domain adaptive faster R-CNN for object detection in the wild,2018
5. Scale-aware domain adaptive faster R-CNN;International Journal of Computer Vision,2021
Cited by
5 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献