Ji-Tao Hu

SPARC: SuperPixel-Aware Region Contrastive Learning for Self-Supervised Dense Prediction

SPARC is proposed, a region-level contrastive learning framework that leverages superpixels to establish explicit correspondence between augmented image views, and introduces a region contrastive branch that performs superpixel-based feature pooling and optimizes a region-level contrastive objective jointly with a glob...