INSPECT (Image-Text Network for Systematic Pest Classification Task), Multimodal Few-Shot Crop Pest & Disease Recognition with Image-Text Alignment & Fusion.
Dataset engineering on IP102 and benchmark of 8 detectors (YOLOv7-v11, SSD, Faster R-CNN); YOLOv11s exported to TFLite
Code for my Master's Thesis in Data Science: Pest Insect Classification on the IP102 Dataset. The paper focuses on improving classification performance on this dataset by addressing two of its major issues, namely class imbalance and intra-class variance.
About Insect pests significantly impact agricultural yields, and accurate recognition helps prevent economic losses. This project uses transfer learning on the IP102 dataset with ResNet-50 pre-trained on ImageNet.
Small insect pest detection on IP102: VOC to COCO, data-driven anchor sizing, small-anchor Faster/Mask R-CNN, NMS vs Soft-NMS. Rebuilt from M.Sc. coursework.
To associate your repository with the ip102 topic, visit your repo's landing page and select "manage topics."