.png){kind=icon}
返回
Consistency-based semi-supervised learning for oriented object detection
.png){kind=icon}
PRE
AI
DOI：10.1016/j.knosys.2024.112534.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Semi-Supervised Object Detection (SSOD) has emerged as a potent framework that leverages unlabeled data to reduce annotation costs while enhancing model performance. Nevertheless, existing SSOD methods primarily concentrate on the conventional localization of horizontal objects, overlooking the common arbitrary-oriented objects in aerial scenes. Extending semi-supervised learning to oriented object detection still encounters two major challenges: (1) There is an inconsistency between classification and localization in oriented object detectors, which means that pseudo-labels selected solely based on classification scores cannot properly represent the localization quality. (2) The static and monotonic pseudo-label selection process fails to dynamically filter pseudo-labels for different tasks and categories throughout the iteration process, inevitably introducing accumulated noise and bias into the supervisory signals for the student model. To mitigate this problems, we proposed a novel consistency-based semi-supervised oriented object detection framework, named CSLO-Det. Specifically, Task Alignment Learning (TAL) is proposed to improve the consistency in terms of both features and learning objectives, thereby facilitating a more robust selection of pseudo-labels. Noise- Resistant Pseudo-label Mining (NR-PM) is introduced to separately and dynamically exploits positives for the classification and localization task. Moreover, diverging from the conventional semi-supervised learning frameworks that utilize pseudo-boxes, our method applies pixel-level dense supervision during unsupervised training, which improves detection performance. Comprehensive experiment results reveal that the proposed CSLO-Det attains state-of-the-art performance under multiple semi-supervised datasets.
Keyword:
Remote sensing
Oriented object detection
Semi-supervised learning
Label mining strategy
期刊
K
IF:
7.6
论文数:
1.2W
被引数:
4.5W
机构
引用论文
Aggressive Aneuploid Acute Myeloid Leukemia Is Dependent on Alterations of P53, Gain of APC and PLK1 and Loss of RAD50.png)
Blood
BloodIF0
PREAI
分享收藏Tissue sampling from live blue mussels, Mytilus edulis. A field study from the Swedish west coast
PREAI
分享收藏A General Gaussian Heatmap Label Assignment for Arbitrary-Oriented Object Detection面向任意对象检测的通用高斯热图标签分配
OAAI
OAAI分享收藏Generation of hydroxyl radicals by urban suspended particulate air matter. The role of iron ions城市悬浮颗粒物产生羟基自由基。铁离子的作用:
PREAI
分享收藏
查看更多内容