Remote Sensing Teacher: Cross-Domain Detection Transformer with Learnable Frequency-Enhanced Feature Alignment in Remote Sensing Imagery
J Han, W Yang, Y Wang, L Chen… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Unsupervised domain adaptation (UDA) is critical for remote sensing object detection in real
applications, aiming to address the significant performance degradation issue caused by the …
applications, aiming to address the significant performance degradation issue caused by the …
A Simple Baseline for Open-World Tracking via Self-training
Open-World Tracking (OWT) presents a challenging yet emerging problem, aiming to track
every object of any category. Different from traditional Multi-Object Tracking (MOT), OWT …
every object of any category. Different from traditional Multi-Object Tracking (MOT), OWT …
MVCRNet: A Semi-Supervised Multi-View Framework for Robust Animal Pose Estimation with Minimal Labeled Data
X Zeng, J Zhang, Z Zhu, D Guo - 2024 - researchsquare.com
Due to its high dependence on labeled data, animal pose estimation faces significant
challenges in practical applications. Effectively utilizing large amounts of unlabeled data to …
challenges in practical applications. Effectively utilizing large amounts of unlabeled data to …
Semi-Supervised Learning with Dense Target Producer for End-to-End Lightweight Polyp Detection
NH Son, NT Huyen, DV Sang - 2023 15th International …, 2023 - ieeexplore.ieee.org
Semi-Supervised Object Detection (SSOD) can greatly enhance the performance of object
detectors by leveraging a vast amount of unlabeled data. Despite great successes, most …
detectors by leveraging a vast amount of unlabeled data. Despite great successes, most …
[PDF][PDF] Cross-Domain Comparisons of YOLOv5 Network Optimization Strategies
D Zhao, J Smith, D Ivanov, J Wang, A Petrov, S Volkov - researchgate.net
Abstract The YOLOv5 (You Only Look Once version 5) network has gained attention for its
performance in object detection tasks. This study focuses on optimizing YOLOv5 across …
performance in object detection tasks. This study focuses on optimizing YOLOv5 across …