| EL | Electroluminescence |
| WASR | Wavelet-Aware Selective Reconstruction Network |
| WADE | Wavelet-Aware Downsampling Encoder |
| CCFM | Cross-Scale Context Fusion Module |
| SRD-Head | Selective Reconstruction Detection Head |
| mAP@0.5 | Mean average precision at an IoU threshold of 0.5 |
| FPS | Frames per second |
| PV | Photovoltaic |
| SVM | Support Vector Machine |
| R-CNN | Region-based Convolutional Neural Network |
| YOLO | You Only Look Once |
| SSD | Single Shot MultiBox Detector |
| CBAM | Convolutional Block Attention Module |
| GAM | Global Attention Mechanism |
| PVEL-AD | Photovoltaic Electroluminescence Vision Algorithm Defects |
| Params | Parameters |
| IoU | Intersection over union |
| SCDown | Spatial-Channel Downsampling |
| SHSA | Single-Head Self-Attention |
| DWT | Discrete Wavelet Transform |
| CNN | Convolutional Neural Network |
| SHViT | Single-Head Vision Transformer |
| Q | Query |
| K | Key |
| V | Value |
| H | Height |
| W | Width |
| C | Channel |
| PAN | Path Aggregation Network |
| ScConv | Spatial and Channel Reconstruction Convolution |
| SRU | Spatial Reconstruction Unit |
| CRU | Channel Reconstruction Unit |
| DWConv | Depthwise Convolution |
| CPU | Central Processing Unit |
| GPU | Graphics Processing Unit |
| VRAM | Video Random Access Memory |
| IDE | Integrated Development Environment |
| SGD | Stochastic Gradient Descent |
| P | Precision |
| R | Recall |
| AP | Average Precision |
| P–R | Precision–recall |
| FLOPs | Floating Point Operations |
| TP | True Positive |
| FP | False Positive |
| FN | False Negative |
| CUDA | Compute Unified Device Architecture |
| RTX | Ray Tracing Texel eXtreme |