2026
DDSF: Robust Few-Shot Learning via Disentangled Subspaces with Determinantal Point Process
CVPR 2026
The performance of mean-based prototypical methods in few-shot learning is frequently compromised by noise and hard positives, where entangled feature representations cause prototype instability. We present a novel "Filter-Repair-Expand" framework grounded in Determinantal Point Process (DPP) theory