IDeaL (ECCV 2026): distill 4 vision teachers into one student using zero real images

mbsariyildiz · x · 2026-09-01

The authors' ECCV 2026 paper IDeaL asks: can you distill knowledge from 4 vision teachers into a single student using zero real images? The answer is yes, and surprisingly well — using optimized structured noise as training data, IDeaL closes most of the gap with real-image distillation, offering a viable route to knowledge distillation without real data.

Related event: ECCV Paper IDeaL Distills Four Vision Teachers with Zero Real Images(4 posts)→

Original post →

More from Models

Models channel →