Galaxy Merger Classification via DANN
Sim-to-real domain adaptation with multimodal fusion between IllustrisTNG simulations and CEERS observations.
Highlights
- Designed a Gated Multimodal Unit (GMU) to fuse simulation (IllustrisTNG) with observational data (CEERS).
- Implemented Domain Adversarial Neural Networks (DANN) to bridge sim-to-real gap under severe class imbalance.
- Built a scalable training pipeline to support rapid iteration and controlled experimentation (ongoing).
Demo
Next: embed a Hugging Face Space here (or custom inference UI).