Object Detection and Segmentation Auto-Labeling

Objective

Developed automatic and manual labeling pipeline for detection and segmentation datasets.

Stack

Delivery highlights

• Implemented automatic labeling with GroundingDINO for text-guided detection and SAM for segmentation masks, Converted generated masks to YOLO-format annotations for training YOLOv8 and YOLOv8-seg models, and Implemented manual labeling loop: seed annotation, model-assisted labeling, review, correction, and retraining.