Training a Student Expert via Semi-Supervised Foundation Model Distillation
通过半监督基础模型蒸馏训练学生专家
机构 * Texas A&M University(德克萨斯农工大学)
AI总结 本文提出半监督知识蒸馏框架,利用有限标注和大量未标注数据压缩预训练视觉基础模型,提升实例分割性能,通过对比学习和多目标损失提升学生模型效果。
Comments Accepted to the 2026 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). 14 pages, 9 figures