.png){kind=icon}
返回
Normalized Cyclic Loop Network for Rail Surface Defect Detection Using Knowledge Distillation
.png){kind=icon}
PRE
AI
DOI：10.1109/TITS.2024.3421355.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In recent years, the application of computer vision for detecting rail defects has shown promising results. However, as the accuracy of the models improves, they become more complex with a large number of parameters, making it challenging to use them in practical scenarios. Although some lightweight models have been proposed to reduce the number of parameters, maintaining satisfactory performance remains difficult. Therefore, we propose a normalized cyclic loop network (NCLNet) using knowledge distillation (KD), called NCLNet-S*, for rail surface defect detection (RSDD). This model aims to be as lightweight as possible while preserving excellent accuracy. It achieves this by constructing an inter-modal feature cyclic enhancement structure to maximize the use of complementary features between modalities, incorporating a normalized fusion filter module for adaptive weighting of useful knowledge, and transferring knowledge from the teacher network (NCLNet-T) to the student network (NCLNet-S) using our proposed KD framework. Additionally, to enhance the performance and robustness of the NCLNet-S* model, we introduce intermodal cross-layer self-distillation. Extensive experimental results demonstrate that our proposed NCLNet-S* (NCLNet-S with KD) achieves high accuracy while remaining lightweight compared to state-of-the-art models. Furthermore, we conduct experiments on the publicly available RGBD-SOD datasets and achieve satisfactory performance, demonstrating the generality of our NCLNet-S* .
Keyword:
Cyclic enhancement structure
normalized fusion filter module
knowledge distillation
self-distillation
rail surface defect detection
Cyclic enhancement structure
normalized fusion filter module
knowledge distillation
self-distillation
rail surface defect detection
期刊
IF:
8.4
论文数:
9.7K
被引数:
6.3W
机构
暂无机构信息
引用论文
分享收藏
ADRNet-S*: Asymmetric depth registration network via contrastive knowledge distillation for RGB-D mirror segmentation.png)
INFORMATION FUSION
INFORMATION FUSIONIF15.5
PREAI
分享收藏A Self-Distillation Embedded Supervised Affinity Attention Model for Few-Shot Segmentation一种用于少镜头分割的自蒸馏嵌入式监督亲和力注意模型
OAAI
OAAI分享收藏
查看更多内容