MLSA-UNet: End-to-End Multi-Level Spatial Attention Guided UNet for Industrial Defect Segmentation

Lin, Dongyun; Cheng, Yi; Li, Yiqun; Prasad, Shitala; Guo, Aiyuan

doi:10.1109/icip46576.2022.9897416

Cited by 5 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As shown in Figure 3, the CA [19] attention mechanism not only achieves long-term dependency in the spatial direction, but also takes into account the position information, enhancing the expression of the feature position information. Compared to CBAM (Convolutional Block Attention Module) [20], it combines spatial attention [21] and Channel attention [22]. The output layer is the final layer of the network responsible for generating the results of the object detection.…”

Section: Separate Ca-yolov5 Network Modelmentioning

confidence: 99%

Surface Defect Detection for Automated Tape Laying and Winding Based on Improved YOLOv5

Wen

Jia-jun³

2023

Materials

View full text Add to dashboard Cite

To address the issues of low detection accuracy, slow detection speed, high missed detection rate, and high false detection rate in the detection of surface defects on pre-impregnated composite materials during the automated tape laying and winding process, an improved YOLOv5 (You Only Look Once version 5) algorithm model was proposed to achieve the high-precision, real-time detection of surface defects. By leveraging this improvement, the necessity for frequent manual interventions, inspection interventions, and subsequent rework during the automated lay-up process of composite materials can be significantly reduced. Firstly, to improve the detection accuracy, an attention mechanism called “CA (coordinate attention)” was introduced to enhance the feature extraction ability, and a Separate CA structure was used to improve the detection speed. Secondly, we used an improved loss function “SIoU (SCYLLA-Intersection over Union) loss” to replace the original “CIoU (Complete-Intersection over Union) loss”, which introduced an angle loss as a penalty term to consider the directional factor and improve the stability of the target box regression. Finally, Soft-SIoU-NMS was used to replace the original NMS (non-maximum suppression) of YOLOv5 to improve the detection of overlapping defects. The results showed that the improved model had a good detection performance for surface defects on pre-impregnated composite materials during the automated tape laying and winding process. The FPS (frames per second) increased from 66.7 to 72.1, and the mAP (mean average precision) of the test set increased from 92.6% to 97.2%. These improvements ensured that the detection accuracy, as measured by the mAP, surpassed 95%, while maintaining a detection speed of over 70 FPS, thereby meeting the requirements for real-time online detection.

show abstract

Section: Separate Ca-yolov5 Network Modelmentioning

confidence: 99%

Surface Defect Detection for Automated Tape Laying and Winding Based on Improved YOLOv5

Wen

Jia-jun³

2023

Materials

View full text Add to dashboard Cite

show abstract

“…By using an encoder-decoder architecture with skip connections to combine hierarchical features, UNet has been shown to provide good semantic segmentation performance for many tasks. Due to it's success and widespread adoption, many variants have been developed for different segmentation domains [3][4][5], such as Attention UNet [6], DenseUNet [7], and UNet++ [8]. Attention UNet filters features passed through skip connections at each scale with a mechanism called an attention gate.…”

Section: Introductionmentioning

confidence: 99%

Visual Prompting based Incremental Learning forSemantic Segmentation of MultiplexImmuno-Flourescence Microscopy Imagery

Faulkenberry,

Prasad,

Maric

et al. 2023

Preprint

View full text Add to dashboard Cite

Deep learning approaches are state-of-the-art for semantic segmentation of medical images, but unlike many deep learning applications, medical segmentation is characterized by small amounts of annotated training data. Thus, while mainstream deep learning approaches focus on performance in domains with large training sets, researchers in the medical imaging field must apply new methods in creative ways to meet the more constrained requirements of medical datasets. We propose a framework for incrementally fine-tuning a multi-class segmentation of a high-resolution multiplex (multi-channel) immuno-flourescence image of a rat brain section, using a minimal amount of labelling from a human expert. Our framework begins with a modified Swin-UNet architecture that treats each biomarker in the multiplex image separately and learns an initial ''global'' segmentation (\emph{pre-training}). This is followed by incremental learning and refinement of each class using a very limited amount of additional labeled data provided by a human expert for each region and its surroundings. This incremental learning utilizes the multi-class weights as an initialization and uses the additional labels to steer the network and optimize it for each region in the image. In this way, an expert can identify errors in the multi-class segmentation and rapidly correct them by supplying the model with additional annotations hand-picked from the region. In addition to increasing the speed of annotation and reducing the amount of labelling, we show that our proposed method outperforms a traditional multi-class segmentation by a large margin.

show abstract

Image-Based Transient Detection Algorithm for Gravitational-Wave Optical Transient Observer (GOTO) Sky Survey

Cortez,

Boongoen,

Iam-On

et al. 2024

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

MLSA-UNet: End-to-End Multi-Level Spatial Attention Guided UNet for Industrial Defect Segmentation

Cited by 5 publications

References 12 publications

Surface Defect Detection for Automated Tape Laying and Winding Based on Improved YOLOv5

Surface Defect Detection for Automated Tape Laying and Winding Based on Improved YOLOv5

Visual Prompting based Incremental Learning forSemantic Segmentation of MultiplexImmuno-Flourescence Microscopy Imagery

Image-Based Transient Detection Algorithm for Gravitational-Wave Optical Transient Observer (GOTO) Sky Survey

Contact Info

Product

Resources

About