[KongchangAI]
ConceptFormula-Driven Supervised Learning

FDSL

A method that generates synthetic images from mathematical formulas such as fractals and performs pretraining with discretized-label classification. It enables pretraining of vision models without real data.

Timeline (last 90 days)

Oct 30

FDSL (Formula-Driven Supervised Learning) generates images from fractal formulas and discretizes labels to accomplish classification-style pretraining.

Unverified50%
Oct 30

FDSL's discrete label classification approach discards the continuous relational information contained in the image generation parameters, limiting the model's ability to learn fine-grained relationships, especially affecting tasks that depend on relative ordering such as image retrieval.

Unverified50%

All Facts (2)

Source Articles