shamisa-self-supervised-image-quality

【数据与研究】Replace standard VICReg invariance loss with graph-weighted learnable adjacency matrix to enable self-supervised no-reference image quality assessment without human labels. Improves SRCC by +0.017 (2% relative) on six-dataset average and shows stronger cross-dataset transfer. Use when training quality assessment models without paired quality labels.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准