CAT: Exploiting Inter-Class Dynamics for Domain Adaptive Object Detection

Page view(s)
17
Checked on Oct 15, 2024
CAT: Exploiting Inter-Class Dynamics for Domain Adaptive Object Detection
Title:
CAT: Exploiting Inter-Class Dynamics for Domain Adaptive Object Detection
Journal Title:
The IEEE/CVF Conference on Computer Vision and Pattern Recognition 2024
DOI:
Publication Date:
17 June 2024
Citation:
NA
Abstract:
Domain adaptive object detection aims to adapt detection models to domains where annotated data is unavailable. Existing methods have been proposed to address the domain gap using the semi-supervised student-teacher framework. However, a fundamental issue arises from the class imbalance in the labelled training set, which can result in inaccurate pseudo-labels. The relationship between classes, especially where one class is a majority and the other minority, has a large impact on class bias. We propose Class-Aware Teacher (CAT) to address the class bias issue in the domain adaptation setting. In our work, we approximate the class relationships with our Inter-Class Relation module (ICRm) and exploit it to reduce the bias within the model. In this way, we are able to apply augmentations to highly related classes, both inter- and intra-domain, to boost the performance of minority classes while having minimal impact on majority classes. We further reduce the bias by implementing a class-relation weight to our classification loss. Experiments conducted on various datasets and ablation studies show that our method is able to address the class bias in the domain adaptation setting. On the Cityscapes → Foggy Cityscapes dataset, we attained a 52.5 mAP, a substantial improvement over the 51.2 mAP achieved by the state-of-the-art method.
License type:
Publisher Copyright
Funding Info:
There was no specific funding for the research done
Description:
© 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
ISSN:
NA
Files uploaded:

File Size Format Action
kennerley-cat-exploiting-inter-class-dynamics-for-domain-adaptive-object-detection-cvpr-2024-paper.pdf 1.36 MB PDF Request a copy