# Bronze Medal | DinoV3

Overview
I used a tag team approach for this biomass challenge. DINOv3 did the heavy lifting as the primary model, while SigLIP acted as a supporting engine to give the predictions a sanity check boost. I topped it off with a bit of biological math so the outputs stayed consistent with how biomass components should add up in the real world.
Models
DINOv3 (primary model)
This was the main model. It processed each pasture image in two halves and then fused the information with a mamba layer to form a single understanding of the full scene. It was strong at capturing fine-grained texture cues, which matters a lot for separating subtle biomass differences.
SigLIP (support model)
Instead of full training, I used SigLIP as a semantic feature extractor. The goal was to capture high-level signals, for example whether the image looks closer to bare ground, sparse pasture, or lush green. I did this by comparing image embeddings to text prompts, then using those similarity scores as extra guidance.
How they were combined
Weighted mix
The final prediction leaned heavily toward DINOv3, with SigLIP contributing a smaller share mainly to stabilize edge cases and reduce obviously odd predictions.
Clover handled by DINOv3
DINOv3 was consistently the most reliable for clover, so I let it handle clover predictions directly instead of mixing it with the supporting branch.
Post-processing for biological consistency
Models can sometimes output physically inconsistent numbers, like components exceeding the total. I applied simple constraint-based post-processing to enforce mass-balance relationships, so Green plus Clover matches GDM, and GDM plus Dead matches Total. In practice, this step nudges predictions into a biologically valid space without changing them aggressively.
Main takeaway
When the backbone is strong and local validation is consistent, it is worth trusting the primary model more.