SOURCE-LINKED INTELLIGENCE

CoViT: Instance-Correspondence Contrastive Learning for Vision Transformer

arXiv · AI, language, vision and robotics · article · Sep 1, 2026 · UTC

Vision Transformers (ViT) excel in semantic understanding but fail to discriminate between object instances (e.g., identical embeddings for two dogs), limiting their use in instance-level tasks such as object detection and instance segmentation. We propose Contrastive Vision Transformer (CoViT), a self-supervised learning framework that injects instance-awareness into ViT through geometry-guided contrastive learning. CoViT uniquely coordinates ViT's attention maps and embeddings by constructing triplets: (1) Attention-guided masking: Refine multi-head attention via adaptive thresholding and mo

Read original source ↗ Open in workspace

recordType

paper

region

Global