I-JEPA predictor width decides which shared image factors stay readable
On 0.7M-parameter encoders, a half-width I-JEPA predictor scored about 40% of SimCLR, and matching encoder width reversed that at every seed.
Stories per day · 30 days
2 stories, newest first · one card per story
Stories tagged #simclr
A Width-Matched Comparison of Hybrid Quantum-Classical Self-Supervised Learning for Fingerprint Recognition
Hybrid quantum SSL beats matched classical models on fingerprints only for contrastive objectives, not reliably for BYOL.