.png){kind=icon}
返回
CISO: Co-iteration semi-supervised learning for visual object detection
.png){kind=icon}
OA
AI
DOI：10.1007/s11042-023-16915-4.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 learning offers a solution to the high cost and limited availability of manually labeled samples in supervised learning. In semi-supervised visual object detection, the use of unlabeled data can significantly enhance the performance of deep learning models. In this paper, we introduce an end-to-end framework, named CISO (Co-Iteration Semi-Supervised Learning for Object Detection), which integrates a knowledge distillation approach and a collaborative, iterative semi-supervised learning strategy. To maximize the utilization of pseudo-label data and address the scarcity of pseudo-label data due to high threshold settings, we propose a mean iteration approach where all unlabeled data is applied to each training iteration. Pseudo-label data with high confidence is extracted based on an ever-changing threshold (average intersection over union of all pseudo-labeled data). This strategy not only ensures the accuracy of the pseudo-label but also optimizes the use of unlabeled data. Subsequently, we apply a weak-strong data augmentation strategy to update the model. Lastly, we evaluate CISO using Swin Transformer model and conduct comprehensive experiments on MS-COCO. Our framework showcases impressive results, outperforms the state-of-the-art methods by 2.16 mAP and 1.54 mAP with 10% and 5% labeled data, respectively.
Keyword:
Semi-supervised
Data augmentation
Transformer
CISO
期刊
IF:
3
论文数:
1.9W
被引数:
3.2W
机构
引用论文
Inflexibility of mental planning: A characteristic disorder with prefrontal lobe lesions?心理计划的僵化: 前额叶病变的特征性障碍？
.png){kind=icon}
PREAI
分享收藏
查看更多内容