Bi-Dimensional Feature Alignment for Cross-Domain Object Detection

11/14/2020
by   Zhen Zhao, et al.
0

Recently the problem of cross-domain object detection has started drawing attention in the computer vision community. In this paper, we propose a novel unsupervised cross-domain detection model that exploits the annotated data in a source domain to train an object detector for a different target domain. The proposed model mitigates the cross-domain representation divergence for object detection by performing cross-domain feature alignment in two dimensions, the depth dimension and the spatial dimension. In the depth dimension of channel layers, it uses inter-channel information to bridge the domain divergence with respect to image style alignment. In the dimension of spatial layers, it deploys spatial attention modules to enhance detection relevant regions and suppress irrelevant regions with respect to cross-domain feature alignment. Experiments are conducted on a number of benchmark cross-domain detection datasets. The empirical results show the proposed method outperforms the state-of-the-art comparison methods.

READ FULL TEXT
research
08/28/2021

Uncertainty-Aware Model Adaptation for Unsupervised Cross-Domain Object Detection

This work tackles the unsupervised cross-domain object detection problem...
research
03/30/2020

Cross-Domain Document Object Detection: Benchmark Suite and Method

Decomposing images of document pages into high-level semantic regions (e...
research
08/19/2023

Prototypical Cross-domain Knowledge Transfer for Cervical Dysplasia Visual Inspection

Early detection of dysplasia of the cervix is critical for cervical canc...
research
05/31/2023

Cross-Domain Car Detection Model with Integrated Convolutional Block Attention Mechanism

Car detection, particularly through camera vision, has become a major fo...
research
11/07/2022

Cross-Domain Local Characteristic Enhanced Deepfake Video Detection

As ultra-realistic face forgery techniques emerge, deepfake detection ha...
research
06/10/2021

AFAN: Augmented Feature Alignment Network for Cross-Domain Object Detection

Unsupervised domain adaptation for object detection is a challenging pro...
research
04/05/2020

Deeply Aligned Adaptation for Cross-domain Object Detection

Cross-domain object detection has recently attracted more and more atten...

Please sign up or login with your details

Forgot password? Click here to reset