• Home
  • Search
  • Foreground Feature Selection and Alignment for Adaptive Object Detection
  • Cite Icon3
  • https://doi.org/10.1007/978-3-030-88004-0_14Copy DOI Icon

Foreground Feature Selection and Alignment for Adaptive Object Detection

  • Jan 1, 2021
  • Zixuan Huang +2 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Recently, remarkable progress has been witnessed in adaptive object detection, which aims to mitigate the distributional shifts between source domain and target domain. Domain-adversarial learning methods align the features of different levels to minimize the domain discrepancy, which have been proven effective for adapting object detectors. Most domain adaptation methods align whole-image features. Therefore, foreground alignment may be interfered by the backgrounds. In this work, we propose Foreground Feature Alignment Framework (FFAF) that strengthens the foreground alignment. One of our key contributions is the Foreground Selection Module (FSM), which captures the foreground features that are crucial for object detection and helpful for subsequent feature alignment. Additionally, we align the foreground features by integrating multi-level domain classifiers. Multi-level Domain adaptation (MDA) can simultaneously bridge the domain gap at various representation levels. We evaluate our method with multiple experiments, whose results demonstrate that our method achieves significant improvements in different cross-domain object detection tasks.

Similar Papers
  • Research Article
  • Citations2

Structural consistency learning for unsupervised domain adaptive object detection.

  • Nov 01, 2025
  • Neural networks : the official journal of the International Neural Network Society
  • Zhiyu Jiang +2
  • Research Article
  • Citations33

FADA: Feature Aligned Domain Adaptive Object Detection in Remote Sensing Imagery

  • Jan 01, 2022
  • IEEE Transactions on Geoscience and Remote Sensing
  • Tao Xu +5
  • PDF
  • Research Article
  • Citations22

Multi-Scale Feature Enhanced Domain Adaptive Object Detection For Power Transmission Line Inspection

  • Jan 01, 2020
  • IEEE Access
  • Pengyu Zhang +5
  • Research Article
  • Citations33

RFA-Net: Reconstructed Feature Alignment Network for Domain Adaptation Object Detection in Remote Sensing Imagery

  • Jan 01, 2022
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • Yangguang Zhu +4
  • PDF
  • Research Article
  • Citations47

DRNet: Disentanglement and Recombination Network for Few-Shot Semantic Segmentation

  • Jul 01, 2024
  • IEEE Transactions on Circuits and Systems for Video Technology
  • Zhaobin Chang +4
  • Research Article
  • Citations4

FIE-Net: Foreground Instance Enhancement Network for Domain Adaptation Object Detection in Remote Sensing Imagery

  • Jan 01, 2025
  • IEEE Transactions on Geoscience and Remote Sensing
  • Jun Zhang +4
  • Research Article
  • Citations22

Domain Adaptation of Anchor-Free object detection for urban traffic

  • Mar 05, 2024
  • Neurocomputing
  • Xiaoyong Yu +1
  • Research Article
  • Citations5

Domain‐specific feature recalibration and alignment for multi‐source unsupervised domain adaptation

  • Aug 27, 2022
  • IET Computer Vision
  • Mengzhu Wang +6
  • Research Article
  • Citations24

Partial adversarial domain adaptation by dual-domain alignment for fault diagnosis of rotating machines

  • Nov 28, 2022
  • ISA Transactions
  • Xuan Wang +4
  • Research Article
  • Citations1

DWANet: Focus on Foreground Features for More Accurate Location

  • Jan 01, 2022
  • IEEE Access
  • Jiwei Hu +3
  • Book Chapter

Unsupervised Domain Adaptive Object Detection with Class Label Shift Weighted Local Features

  • Jan 01, 2023
  • Andong Tan +4
  • Research Article
  • Citations13

Joint local and statistical discriminant learning via feature alignment

  • Nov 04, 2019
  • Signal, Image and Video Processing
  • Elahe Gholenji +1
  • Research Article

Geometry-Insensitive RPN Prototypes for Domain Adaptive 3D Object Detection

  • Jan 19, 2026
  • ACM Transactions on Multimedia Computing, Communications, and Applications
  • Jiazhong Chen +6
  • Research Article
  • Citations12

LIDA‐YOLO: An unsupervised low‐illumination object detection based on domain adaptation

  • Dec 17, 2023
  • IET Image Processing
  • Yun Xiao +1
  • Conference Article
  • Citations103

Exploring Sequence Feature Alignment for Domain Adaptive Detection Transformers

  • Oct 17, 2021
  • Wen Wang +6
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.