Hard Labels In! Rethinking the Role of Hard Labels in Mitigating Local Semantic Drift 事件

Hard Labels In! Rethinking the Role of Hard Labels in Mitigating Local Semantic Drift arXiv:2512.15647v3 Announce Type: replace Abstract: Soft labels from teacher models are a de facto practice for knowledge transfer and large-scale dataset distillation (e.g., SRe2L, LPLD). However, when we limit the number of crops per image to reduce the substantial cost of storing precomputed soft labels, these methods suffer severely from local semantic drift: visually ambiguous crops can cause soft supervi