Locality-Aware Inter-and Intra-Video Reconstruction for Self-Supervised Correspondence Learning

Understand

Our target is to learn visual correspondence from unlabeled videos.

• We develop LIIR, a locality-aware inter-and intra-video reconstruction framework that fills in three missing pieces, i.e., instance discrimination, location awareness, and spatial compactness, of self-supervised correspondence learning puzzle.
• First, instead of most existing efforts focusing on intra-video self-supervision only, we exploit cross video affinities as extra negative samples within a unified, inter-and intra-video reconstruction scheme.
• This enables instance discriminative representation learning by contrasting desired intra-video pixel association against negative inter-video correspondence.