Visual Contrastive Self-Distillation
On-policy self-distillation (OPSD) is promising as it removes the external teacher required by on-policy distillation (OPD), yet it still needs asymmetric information between teacher and student to ensure that the self-teacher provides a stronger learning signal than the student. Existing methods create this asymmetry either through privileged answers or visual evidence. We ask whether both can be removed, yielding a simpler form of OPSD driven purely by input conditioning. For this purpose, we propose Visual Contrastive Self-Distillation, namely VCSD, which converts image-content removal into
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 51%Embarrassingly Simple Self-Distillation Improves Code Generation - Apple Machine Learning Research →
- FuzzyOverlapping authors or contributors · 62%sgl-project/sglang →
“Shared author/contributor keys: zhou”
- LinkedLinked via arxiv author · 85%Yijun Liang →
“Visual Contrastive Self-Distillation”
- LinkedLinked via arxiv author · 85%Yunjie Tian →
“Visual Contrastive Self-Distillation”
- LinkedLinked via arxiv author · 85%Yijiang Li →
“Visual Contrastive Self-Distillation”
- LinkedLinked via arxiv author · 85%Yuqi Jia →
“Visual Contrastive Self-Distillation”
- LinkedLinked via arxiv author · 85%Furong Huang →
“Visual Contrastive Self-Distillation”
- LinkedLinked via arxiv author · 85%Tianyi Zhou →
“Visual Contrastive Self-Distillation”