Understanding and adapting transformer-based architectures for object detection
Adapted ViTDet architecture using PyTorch, gaining practical knowledge of vision transformers
A practical reconstruction of a Vision Transformer detection pipeline using Detectron2 and ViTDet concepts.
Context
This was research-oriented engineering: understanding how transformer-based object detection works by rebuilding the moving pieces rather than only consuming a high-level API. The value was in the implementation detail and evaluation discipline.
Build
I adapted ViTDet-style components with Detectron2, worked through COCO-style data handling and evaluation, and connected the detection stack to familiar Mask R-CNN and Cascade R-CNN techniques. The project sharpened the bridge between papers, frameworks, and working code.
Engineering
Adapted ViTDet architecture using PyTorch, gaining practical knowledge of vision transformers
Implemented a detection pipeline incorporating Cascade R-CNN and Mask R-CNN techniques
Developed comprehensive data handling and basic evaluation workflows
Outcome
Stack